diff --git a/api/r/cellxgene.census/DESCRIPTION b/api/r/cellxgene.census/DESCRIPTION
index 7aaa77a0b..7ebb62784 100644
--- a/api/r/cellxgene.census/DESCRIPTION
+++ b/api/r/cellxgene.census/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: cellxgene.census
 Title: CZ CELLxGENE Discover Cell Census
-Version: 1.5.2
+Version: 1.6.0
 Authors@R: 
     person("Chan Zuckerberg Initiative", email = "soma@chanzuckerberg.com",
            role = c("aut", "cre", "cph", "fnd"))
diff --git a/api/r/cellxgene.census/docs/404.html b/api/r/cellxgene.census/docs/404.html
index 6a931f2da..a3615b37e 100644
--- a/api/r/cellxgene.census/docs/404.html
+++ b/api/r/cellxgene.census/docs/404.html
@@ -30,7 +30,7 @@
     
     <a class="navbar-brand me-2" href="index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/LICENSE-text.html b/api/r/cellxgene.census/docs/LICENSE-text.html
index 539ddf528..ab3b1ef5b 100644
--- a/api/r/cellxgene.census/docs/LICENSE-text.html
+++ b/api/r/cellxgene.census/docs/LICENSE-text.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/LICENSE.html b/api/r/cellxgene.census/docs/LICENSE.html
index 136263701..224d2daa5 100644
--- a/api/r/cellxgene.census/docs/LICENSE.html
+++ b/api/r/cellxgene.census/docs/LICENSE.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/census_compute_over_X.html b/api/r/cellxgene.census/docs/articles/census_compute_over_X.html
index 61660363d..475098d97 100644
--- a/api/r/cellxgene.census/docs/articles/census_compute_over_X.html
+++ b/api/r/cellxgene.census/docs/articles/census_compute_over_X.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/census_dataset_presence.html b/api/r/cellxgene.census/docs/articles/census_dataset_presence.html
index e16db8977..a99339b80 100644
--- a/api/r/cellxgene.census/docs/articles/census_dataset_presence.html
+++ b/api/r/cellxgene.census/docs/articles/census_dataset_presence.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/census_datasets.html b/api/r/cellxgene.census/docs/articles/census_datasets.html
index 8175acb94..1305efc48 100644
--- a/api/r/cellxgene.census/docs/articles/census_datasets.html
+++ b/api/r/cellxgene.census/docs/articles/census_datasets.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/census_query_extract.html b/api/r/cellxgene.census/docs/articles/census_query_extract.html
index 287074ad5..5a6fe3866 100644
--- a/api/r/cellxgene.census/docs/articles/census_query_extract.html
+++ b/api/r/cellxgene.census/docs/articles/census_query_extract.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/comp_bio_census_info.html b/api/r/cellxgene.census/docs/articles/comp_bio_census_info.html
index 70abe662e..f77ffee3d 100644
--- a/api/r/cellxgene.census/docs/articles/comp_bio_census_info.html
+++ b/api/r/cellxgene.census/docs/articles/comp_bio_census_info.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/comp_bio_data_integration.html b/api/r/cellxgene.census/docs/articles/comp_bio_data_integration.html
index 25ef22ab1..2a93a17e3 100644
--- a/api/r/cellxgene.census/docs/articles/comp_bio_data_integration.html
+++ b/api/r/cellxgene.census/docs/articles/comp_bio_data_integration.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -293,20 +293,20 @@ <h4 id="integration-across-datasets-using-dataset_id-and-controlling-for-batch-u
 <span><span class="co"># Run the standard workflow for visualization and clustering</span></span>
 <span><span class="va">seurat_obj.combined</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://satijalab.org/seurat/reference/RunPCA.html" class="external-link">RunPCA</a></span><span class="op">(</span><span class="va">seurat_obj.combined</span>, npcs <span class="op">=</span> <span class="fl">30</span>, verbose <span class="op">=</span> <span class="cn">FALSE</span><span class="op">)</span></span>
 <span><span class="va">seurat_obj.combined</span> <span class="op">&lt;-</span> <span class="fu"><a href="https://satijalab.org/seurat/reference/RunUMAP.html" class="external-link">RunUMAP</a></span><span class="op">(</span><span class="va">seurat_obj.combined</span>, reduction <span class="op">=</span> <span class="st">"pca"</span>, dims <span class="op">=</span> <span class="fl">1</span><span class="op">:</span><span class="fl">30</span><span class="op">)</span></span>
-<span><span class="co">#&gt; 18:25:53 UMAP embedding parameters a = 0.9922 b = 1.112</span></span>
-<span><span class="co">#&gt; 18:25:53 Read 10153 rows and found 30 numeric columns</span></span>
-<span><span class="co">#&gt; 18:25:53 Using Annoy for neighbor search, n_neighbors = 30</span></span>
-<span><span class="co">#&gt; 18:25:53 Building Annoy index with metric = cosine, n_trees = 50</span></span>
+<span><span class="co">#&gt; 13:30:46 UMAP embedding parameters a = 0.9922 b = 1.112</span></span>
+<span><span class="co">#&gt; 13:30:46 Read 10153 rows and found 30 numeric columns</span></span>
+<span><span class="co">#&gt; 13:30:46 Using Annoy for neighbor search, n_neighbors = 30</span></span>
+<span><span class="co">#&gt; 13:30:46 Building Annoy index with metric = cosine, n_trees = 50</span></span>
 <span><span class="co">#&gt; 0%   10   20   30   40   50   60   70   80   90   100%</span></span>
 <span><span class="co">#&gt; [----|----|----|----|----|----|----|----|----|----|</span></span>
 <span><span class="co">#&gt; **************************************************|</span></span>
-<span><span class="co">#&gt; 18:25:54 Writing NN index file to temp file /var/folders/9q/j_1zpqns7vz_s5n9l6_b943r0000gr/T//RtmpaMpqKs/file9d602f8d4d28</span></span>
-<span><span class="co">#&gt; 18:25:54 Searching Annoy index using 1 thread, search_k = 3000</span></span>
-<span><span class="co">#&gt; 18:25:57 Annoy recall = 100%</span></span>
-<span><span class="co">#&gt; 18:25:57 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30</span></span>
-<span><span class="co">#&gt; 18:25:58 Initializing from normalized Laplacian + noise (using irlba)</span></span>
-<span><span class="co">#&gt; 18:25:58 Commencing optimization for 200 epochs, with 410804 positive edges</span></span>
-<span><span class="co">#&gt; 18:26:03 Optimization finished</span></span></code></pre></div>
+<span><span class="co">#&gt; 13:30:47 Writing NN index file to temp file /var/folders/9q/j_1zpqns7vz_s5n9l6_b943r0000gr/T//RtmpwHKO6w/file16d2113ba6e8</span></span>
+<span><span class="co">#&gt; 13:30:47 Searching Annoy index using 1 thread, search_k = 3000</span></span>
+<span><span class="co">#&gt; 13:30:51 Annoy recall = 100%</span></span>
+<span><span class="co">#&gt; 13:30:51 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30</span></span>
+<span><span class="co">#&gt; 13:30:52 Initializing from normalized Laplacian + noise (using irlba)</span></span>
+<span><span class="co">#&gt; 13:30:53 Commencing optimization for 200 epochs, with 410804 positive edges</span></span>
+<span><span class="co">#&gt; 13:30:59 Optimization finished</span></span></code></pre></div>
 <p>Plot the UMAP.</p>
 <div class="sourceCode" id="cb21"><pre class="downlit sourceCode r">
 <code class="sourceCode R"><span><span class="co"># By assay</span></span>
diff --git a/api/r/cellxgene.census/docs/articles/comp_bio_normalizing_full_gene_sequencing.html b/api/r/cellxgene.census/docs/articles/comp_bio_normalizing_full_gene_sequencing.html
index 189104703..c91232c4e 100644
--- a/api/r/cellxgene.census/docs/articles/comp_bio_normalizing_full_gene_sequencing.html
+++ b/api/r/cellxgene.census/docs/articles/comp_bio_normalizing_full_gene_sequencing.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/comp_bio_summarize_axis_query.html b/api/r/cellxgene.census/docs/articles/comp_bio_summarize_axis_query.html
index c2ce48a59..6c4a6ddab 100644
--- a/api/r/cellxgene.census/docs/articles/comp_bio_summarize_axis_query.html
+++ b/api/r/cellxgene.census/docs/articles/comp_bio_summarize_axis_query.html
@@ -32,7 +32,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/articles/index.html b/api/r/cellxgene.census/docs/articles/index.html
index 357f55f2c..e793c2d6a 100644
--- a/api/r/cellxgene.census/docs/articles/index.html
+++ b/api/r/cellxgene.census/docs/articles/index.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/authors.html b/api/r/cellxgene.census/docs/authors.html
index a8229be6e..94f570da8 100644
--- a/api/r/cellxgene.census/docs/authors.html
+++ b/api/r/cellxgene.census/docs/authors.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -74,13 +74,13 @@ <h2 id="citation">Citation</h2>
 
       <p>Chan Zuckerberg Initiative (2023).
 <em>cellxgene.census: CZ CELLxGENE Discover Cell Census</em>.
-R package version 1.5.2, <a href="https://github.com/chanzuckerberg/cellxgene-census" class="external-link">https://github.com/chanzuckerberg/cellxgene-census</a>. 
+R package version 1.6.0, <a href="https://github.com/chanzuckerberg/cellxgene-census" class="external-link">https://github.com/chanzuckerberg/cellxgene-census</a>. 
 </p>
       <pre>@Manual{,
   title = {cellxgene.census: CZ CELLxGENE Discover Cell Census},
   author = {{Chan Zuckerberg Initiative}},
   year = {2023},
-  note = {R package version 1.5.2},
+  note = {R package version 1.6.0},
   url = {https://github.com/chanzuckerberg/cellxgene-census},
 }</pre>
     </div>
diff --git a/api/r/cellxgene.census/docs/index.html b/api/r/cellxgene.census/docs/index.html
index aea3151f4..a4383a8fb 100644
--- a/api/r/cellxgene.census/docs/index.html
+++ b/api/r/cellxgene.census/docs/index.html
@@ -36,7 +36,7 @@
     
     <a class="navbar-brand me-2" href="index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/pkgdown.yml b/api/r/cellxgene.census/docs/pkgdown.yml
index d00526d10..f8fe25710 100644
--- a/api/r/cellxgene.census/docs/pkgdown.yml
+++ b/api/r/cellxgene.census/docs/pkgdown.yml
@@ -10,5 +10,5 @@ articles:
   comp_bio_data_integration: comp_bio_data_integration.html
   comp_bio_normalizing_full_gene_sequencing: comp_bio_normalizing_full_gene_sequencing.html
   comp_bio_summarize_axis_query: comp_bio_summarize_axis_query.html
-last_built: 2023-08-29T00:57Z
+last_built: 2023-09-06T20:04Z
 
diff --git a/api/r/cellxgene.census/docs/reference/download_source_h5ad.html b/api/r/cellxgene.census/docs/reference/download_source_h5ad.html
index 938d004d8..4a656b15c 100644
--- a/api/r/cellxgene.census/docs/reference/download_source_h5ad.html
+++ b/api/r/cellxgene.census/docs/reference/download_source_h5ad.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/get_census_version_description.html b/api/r/cellxgene.census/docs/reference/get_census_version_description.html
index 286d48d4a..c0448fa8d 100644
--- a/api/r/cellxgene.census/docs/reference/get_census_version_description.html
+++ b/api/r/cellxgene.census/docs/reference/get_census_version_description.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/get_census_version_directory.html b/api/r/cellxgene.census/docs/reference/get_census_version_directory.html
index a6d810067..577130b13 100644
--- a/api/r/cellxgene.census/docs/reference/get_census_version_directory.html
+++ b/api/r/cellxgene.census/docs/reference/get_census_version_directory.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
@@ -83,7 +83,7 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
     <div class="sourceCode"><pre class="sourceCode r"><code><span class="r-in"><span><span class="fu">get_census_version_directory</span><span class="op">(</span><span class="op">)</span></span></span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>            release_date release_build</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> stable                     2023-07-25</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> latest                     2023-08-25</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> latest                     2023-09-04</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-05-15                 2023-05-15</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-17                 2023-07-17</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-24                 2023-07-24</span>
@@ -93,9 +93,10 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-14                 2023-08-14</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-22                 2023-08-22</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-25                 2023-08-25</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> 2023-09-04                 2023-09-04</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>                                                           soma.uri</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> stable     s3://cellxgene-data-public/cell-census/2023-07-25/soma/</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> latest     s3://cellxgene-data-public/cell-census/2023-08-25/soma/</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> latest     s3://cellxgene-data-public/cell-census/2023-09-04/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/soma/</span>
@@ -105,9 +106,10 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/soma/</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> 2023-09-04 s3://cellxgene-data-public/cell-census/2023-09-04/soma/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>                        soma.relative_uri soma.s3_region</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> stable     /cell-census/2023-07-25/soma/      us-west-2</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> latest     /cell-census/2023-08-25/soma/      us-west-2</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> latest     /cell-census/2023-09-04/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-05-15 /cell-census/2023-05-15/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-17 /cell-census/2023-07-17/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-24 /cell-census/2023-07-24/soma/      us-west-2</span>
@@ -117,9 +119,10 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-14 /cell-census/2023-08-14/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-22 /cell-census/2023-08-22/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-25 /cell-census/2023-08-25/soma/      us-west-2</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> 2023-09-04 /cell-census/2023-09-04/soma/      us-west-2</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>                                                           h5ads.uri</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> stable     s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> latest     s3://cellxgene-data-public/cell-census/2023-08-25/h5ads/</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> latest     s3://cellxgene-data-public/cell-census/2023-09-04/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/h5ads/</span>
@@ -129,9 +132,10 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/h5ads/</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> 2023-09-04 s3://cellxgene-data-public/cell-census/2023-09-04/h5ads/</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span>                        h5ads.relative_uri h5ads.s3_region do_not_delete  alias</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> stable     /cell-census/2023-07-25/h5ads/       us-west-2          TRUE stable</span>
-<span class="r-out co"><span class="r-pr">#&gt;</span> latest     /cell-census/2023-08-25/h5ads/       us-west-2         FALSE latest</span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> latest     /cell-census/2023-09-04/h5ads/       us-west-2         FALSE latest</span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-05-15 /cell-census/2023-05-15/h5ads/       us-west-2          TRUE       </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-17 /cell-census/2023-07-17/h5ads/       us-west-2            NA       </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-07-24 /cell-census/2023-07-24/h5ads/       us-west-2            NA       </span>
@@ -141,6 +145,7 @@ <h2 id="ref-examples">Examples<a class="anchor" aria-label="anchor" href="#ref-e
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-14 /cell-census/2023-08-14/h5ads/       us-west-2         FALSE       </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-22 /cell-census/2023-08-22/h5ads/       us-west-2         FALSE       </span>
 <span class="r-out co"><span class="r-pr">#&gt;</span> 2023-08-25 /cell-census/2023-08-25/h5ads/       us-west-2         FALSE       </span>
+<span class="r-out co"><span class="r-pr">#&gt;</span> 2023-09-04 /cell-census/2023-09-04/h5ads/       us-west-2         FALSE       </span>
 </code></pre></div>
     </div>
   </main><aside class="col-md-3"><nav id="toc"><h2>On this page</h2>
diff --git a/api/r/cellxgene.census/docs/reference/get_presence_matrix.html b/api/r/cellxgene.census/docs/reference/get_presence_matrix.html
index 624f531b0..a892f3663 100644
--- a/api/r/cellxgene.census/docs/reference/get_presence_matrix.html
+++ b/api/r/cellxgene.census/docs/reference/get_presence_matrix.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/get_seurat.html b/api/r/cellxgene.census/docs/reference/get_seurat.html
index dcf9cff63..10e709113 100644
--- a/api/r/cellxgene.census/docs/reference/get_seurat.html
+++ b/api/r/cellxgene.census/docs/reference/get_seurat.html
@@ -12,7 +12,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/get_single_cell_experiment.html b/api/r/cellxgene.census/docs/reference/get_single_cell_experiment.html
index 32347f93a..41ef6c9cd 100644
--- a/api/r/cellxgene.census/docs/reference/get_single_cell_experiment.html
+++ b/api/r/cellxgene.census/docs/reference/get_single_cell_experiment.html
@@ -12,7 +12,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/get_source_h5ad_uri.html b/api/r/cellxgene.census/docs/reference/get_source_h5ad_uri.html
index addb024f9..af159ca26 100644
--- a/api/r/cellxgene.census/docs/reference/get_source_h5ad_uri.html
+++ b/api/r/cellxgene.census/docs/reference/get_source_h5ad_uri.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/index.html b/api/r/cellxgene.census/docs/reference/index.html
index c7bd30e96..4edbf9d44 100644
--- a/api/r/cellxgene.census/docs/reference/index.html
+++ b/api/r/cellxgene.census/docs/reference/index.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/new_SOMATileDBContext_for_census.html b/api/r/cellxgene.census/docs/reference/new_SOMATileDBContext_for_census.html
index a93487581..7bf5dd082 100644
--- a/api/r/cellxgene.census/docs/reference/new_SOMATileDBContext_for_census.html
+++ b/api/r/cellxgene.census/docs/reference/new_SOMATileDBContext_for_census.html
@@ -16,7 +16,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/reference/open_soma.html b/api/r/cellxgene.census/docs/reference/open_soma.html
index 5c16ac82e..9bc49bd9f 100644
--- a/api/r/cellxgene.census/docs/reference/open_soma.html
+++ b/api/r/cellxgene.census/docs/reference/open_soma.html
@@ -10,7 +10,7 @@
     
     <a class="navbar-brand me-2" href="../index.html">cellxgene.census</a>
 
-    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.5.2</small>
+    <small class="nav-text text-muted me-auto" data-bs-toggle="tooltip" data-bs-placement="bottom" title="">1.6.0</small>
 
     
     <button class="navbar-toggler" type="button" data-bs-toggle="collapse" data-bs-target="#navbar" aria-controls="navbar" aria-expanded="false" aria-label="Toggle navigation">
diff --git a/api/r/cellxgene.census/docs/search.json b/api/r/cellxgene.census/docs/search.json
index b1e4b57f7..40b2ecbe4 100644
--- a/api/r/cellxgene.census/docs/search.json
+++ b/api/r/cellxgene.census/docs/search.json
@@ -1 +1 @@
-[{"path":"/LICENSE.html","id":null,"dir":"","previous_headings":"","what":"MIT License","title":"MIT License","text":"Copyright (c) 2023 Chan Zuckerberg Initiative Permission hereby granted, free charge, person obtaining copy software associated documentation files (“Software”), deal Software without restriction, including without limitation rights use, copy, modify, merge, publish, distribute, sublicense, /sell copies Software, permit persons Software furnished , subject following conditions: copyright notice permission notice shall included copies substantial portions Software. SOFTWARE PROVIDED “”, WITHOUT WARRANTY KIND, EXPRESS IMPLIED, INCLUDING LIMITED WARRANTIES MERCHANTABILITY, FITNESS PARTICULAR PURPOSE NONINFRINGEMENT. EVENT SHALL AUTHORS COPYRIGHT HOLDERS LIABLE CLAIM, DAMAGES LIABILITY, WHETHER ACTION CONTRACT, TORT OTHERWISE, ARISING , CONNECTION SOFTWARE USE DEALINGS SOFTWARE.","code":""},{"path":"/articles/census_compute_over_X.html","id":"incremental-mean-calculation","dir":"Articles","previous_headings":"","what":"Incremental mean calculation","title":"Computing on X using online (incremental) algorithms","text":"Many statistics, marginal means, easy calculate incrementally. Let’s begin query X$raw sparse matrix unnormalized read counts, return results shards incrementally accumulate read count gene, divide cell count get mean reads per cell gene. First define query - case slice obs axis cells specific tissue & sex value, genes var axis. query$X() method returns iterator results, Arrow Table. table contain sparse X data obs/var coordinates, using standard SOMA names: soma_data - X values (float32) soma_dim_0 - obs coordinate (int64) soma_dim_1 - var coordinate (int64) Important: X matrices joined var/obs axis DataFrames integer join “id” (aka soma_joinid). positionally indexed, given cell gene may soma_joinid value (e.g., large integer). words, given X value, soma_dim_0 corresponds soma_joinid obs dataframe, soma_dim_1 coordinate corresponds soma_joinid var dataframe. convenience, query class includes utility simplify operations query slices. query$indexer indexer used wrap output query$X(), converting soma_joinids positional indexing query results. Positions [0, N), N number results query given axis. Key points: expensive query read results - rather make multiple passes data, read perform multiple computations. default, data census indexed soma_joinid positionally.","code":"library(\"tiledbsoma\") library(\"cellxgene.census\") census <- open_soma()  query <- census$get(\"census_data\")$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = SOMAAxisQuery$new(value_filter = \"tissue=='brain' && sex=='male'\") )  genes_df <- query$var(column_names = c(\"feature_id\", \"feature_name\"))$concat() genes_df <- as.data.frame(genes_df) n_genes <- nrow(genes_df)  # accumulator vector (for each gene) for the total count over all cells in X(\"raw\") raw_sum_by_gene <- numeric(n_genes) names(raw_sum_by_gene) <- genes_df$feature_id  # iterate through in-memory shards of query results tables <- query$X(\"raw\")$tables() while (!tables$read_complete()) {   table_part <- tables$read_next()   # table_part is an Arrow table with the columns mentioned above. The result   # order is not guaranteed!    # table_part$soma_dim_1 is the var/gene soma_joinid. But note that these are   # arbitrary int64 id's, and moreover each table_part may exhibit only a subset   # of the values we'll see over all query results. query$indexer helps us map   # any given soma_dim_1 values onto positions in query$var() (genes_df), that is   # the union of all values we'll see.   gene_indexes <- query$indexer$by_var(table_part$soma_dim_1)$as_vector()   stopifnot(sum(gene_indexes >= n_genes) == 0)   # sum(table_part) group by gene, yielding a numeric vector with the gene_index   # in its names   sum_part <- tapply(as.vector(table_part$soma_data), gene_indexes, sum)   # update the accumulator vector   which_genes <- as.integer(names(sum_part)) + 1  # nb: gene_indexes is zero-based   stopifnot(sum(which_genes > n_genes) == 0)   raw_sum_by_gene[which_genes] <- raw_sum_by_gene[which_genes] + sum_part }  # Divide each sum by cell count to get mean reads per cell (for each gene), # implicitly averaging in all zero entries in X even though they weren't included # in the sparse query results. genes_df$raw_mean <- raw_sum_by_gene / query$n_obs genes_df #> # A tibble: 52,392 × 3 #>    feature_id         feature_name   raw_mean #>    <chr>              <chr>             <dbl> #>  1 ENSMUSG00000051951 Xkr4          1.28      #>  2 ENSMUSG00000089699 Gm1992        0         #>  3 ENSMUSG00000102343 Gm37381       0         #>  4 ENSMUSG00000025900 Rp1           0.291     #>  5 ENSMUSG00000025902 Sox17        60.7       #>  6 ENSMUSG00000104328 Gm37323       0.0000570 #>  7 ENSMUSG00000033845 Mrpl15       36.2       #>  8 ENSMUSG00000025903 Lypla1       18.3       #>  9 ENSMUSG00000104217 Gm37988       0         #> 10 ENSMUSG00000033813 Tcea1        39.6       #> # ℹ 52,382 more rows"},{"path":"/articles/census_compute_over_X.html","id":"counting-cells-grouped-by-dataset-and-gene","dir":"Articles","previous_headings":"","what":"Counting cells grouped by dataset and gene","title":"Computing on X using online (incremental) algorithms","text":"goal example count number cells nonzero reads, grouped gene Census dataset_id. result data frame dataset, gene, number cells nonzero reads dataset gene. multi-factor aggregation, ’ll take advantage dplyr routines instead lower-level vector indexer shown . presentation purposes, ’ll limit query four genes, can expanded genes easily. Don’t forget close census.","code":"library(\"dplyr\")  query <- census$get(\"census_data\")$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = SOMAAxisQuery$new(value_filter = \"tissue=='brain'\"),   var_query = SOMAAxisQuery$new(value_filter = \"feature_name %in% c('Malat1', 'Ptprd', 'Dlg2', 'Pcdh9')\") )  obs_tbl <- query$obs(column_names=c(\"soma_joinid\", \"dataset_id\"))$concat() obs_df <- data.frame(   # materialize soma_joinid as character to avoid overflowing R 32-bit integer   cell_id = as.character(obs_tbl$soma_joinid),   dataset_id = obs_tbl$dataset_id$as_vector() ) var_tbl <- query$var(column_names=c(\"soma_joinid\", \"feature_name\"))$concat() var_df <- data.frame(   gene_id = as.character(var_tbl$soma_joinid),   feature_name = var_tbl$feature_name$as_vector() )  # accumulator for # cells by dataset & gene n_cells_grouped <- data.frame(   \"dataset_id\" = character(0),   \"gene_id\" = character(0),   \"n_cells\" = numeric(0) )  # iterate through in-memory shards of query results tables <- query$X(\"raw\")$tables() while (!tables$read_complete()) {   table_part <- tables$read_next()    # prepare a (dataset,gene,1) tuple for each entry in table_part   n_cells_part <- data.frame(     \"cell_id\" = as.character(table_part$soma_dim_0),     \"gene_id\" = as.character(table_part$soma_dim_1),     \"n_cells\" = 1   )   n_cells_part <- left_join(n_cells_part, obs_df, by = \"cell_id\")   stopifnot(sum(is.null(n_cells_part$dataset_id)) == 0)    # fold those into n_cells_grouped   n_cells_grouped <- n_cells_part %>%                      select(-cell_id) %>%                      bind_rows(n_cells_grouped) %>%                       group_by(dataset_id, gene_id) %>%                       summarise(n_cells = sum(n_cells)) %>%                       ungroup() }  # add gene names for display n_cells_grouped <- left_join(n_cells_grouped, var_df, by = \"gene_id\") stopifnot(sum(is.null(n_cells_grouped$feature_name)) == 0) n_cells_grouped[c(\"dataset_id\", \"feature_name\", \"n_cells\")] #> # A tibble: 17 × 3 #>    dataset_id                           feature_name n_cells #>    <chr>                                <chr>          <dbl> #>  1 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Dlg2           79513 #>  2 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Pcdh9          79476 #>  3 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Malat1         79667 #>  4 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Ptprd          79578 #>  5 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Dlg2              81 #>  6 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Pcdh9            125 #>  7 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Malat1         12622 #>  8 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Ptprd            474 #>  9 66ff82b4-9380-469c-bc4b-cfa08eacd325 Dlg2             856 #> 10 66ff82b4-9380-469c-bc4b-cfa08eacd325 Pcdh9           2910 #> 11 66ff82b4-9380-469c-bc4b-cfa08eacd325 Malat1          7102 #> 12 98e5ea9f-16d6-47ec-a529-686e76515e39 Dlg2             908 #> 13 98e5ea9f-16d6-47ec-a529-686e76515e39 Pcdh9           3027 #> 14 98e5ea9f-16d6-47ec-a529-686e76515e39 Malat1         20094 #> 15 c08f8441-4a10-4748-872a-e70c0bcccdba Dlg2              52 #> 16 c08f8441-4a10-4748-872a-e70c0bcccdba Pcdh9            117 #> 17 c08f8441-4a10-4748-872a-e70c0bcccdba Malat1         12992 census$close()"},{"path":"/articles/census_dataset_presence.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Genes measured in each cell (dataset presence matrix)","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version).","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/census_dataset_presence.html","id":"fetching-the-ids-of-the-census-datasets","dir":"Articles","previous_headings":"","what":"Fetching the IDs of the Census datasets","title":"Genes measured in each cell (dataset presence matrix)","text":"Let’s grab table datasets included Census use table combination presence matrix .","code":"# Grab the experiment containing human data, and the measurement therein with RNA human <- census$get(\"census_data\")$get(\"homo_sapiens\") human_rna <- human$ms$get(\"RNA\")  # The census-wide datasets datasets_df <- as.data.frame(census$get(\"census_info\")$get(\"datasets\")$read()$concat()) print(datasets_df) #> # A tibble: 593 × 8 #>    soma_joinid collection_id     collection_name collection_doi dataset_id dataset_title #>          <int> <chr>             <chr>           <chr>          <chr>      <chr>         #>  1           0 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… f171db61-… donor_p13_tr… #>  2           1 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… ecf2e08e-… All donors t… #>  3           2 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… 74cff64f-… All donors a… #>  4           3 f7cecffa-00b4-45… Mapping single… 10.1016/j.cce… 5af90777-… Single-cell … #>  5           4 3f50314f-bdc9-40… Single-cell se… 10.1016/j.cce… bd65a70f-… Single-cell … #>  6           5 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… ff45e623-… Tabula Sapie… #>  7           6 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… f01bdd17-… Tabula Sapie… #>  8           7 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e6a11140-… Tabula Sapie… #>  9           8 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e5c63d94-… Tabula Sapie… #> 10           9 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… d8732da6-… Tabula Sapie… #> # ℹ 583 more rows #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int>"},{"path":"/articles/census_dataset_presence.html","id":"fetching-the-dataset-presence-matrix","dir":"Articles","previous_headings":"","what":"Fetching the dataset presence matrix","title":"Genes measured in each cell (dataset presence matrix)","text":"Now let’s fetch dataset presence matrix. convenience, read entire presence matrix (Homo sapiens) sparse matrix. convenience function providing capability: also need var dataframe, read R data frame convenient manipulation:","code":"presence_matrix <- get_presence_matrix(census, \"Homo sapiens\", \"RNA\") print(dim(presence_matrix)) #> NULL var_df <- as.data.frame(human_rna$var$read()$concat()) print(var_df) #> # A tibble: 60,664 × 4 #>    soma_joinid feature_id      feature_name feature_length #>          <int> <chr>           <chr>                 <int> #>  1           0 ENSG00000121410 A1BG                   3999 #>  2           1 ENSG00000268895 A1BG-AS1               3374 #>  3           2 ENSG00000148584 A1CF                   9603 #>  4           3 ENSG00000175899 A2M                    6318 #>  5           4 ENSG00000245105 A2M-AS1                2948 #>  6           5 ENSG00000166535 A2ML1                  7156 #>  7           6 ENSG00000256661 A2ML1-AS1               452 #>  8           7 ENSG00000184389 A3GALT2                1023 #>  9           8 ENSG00000128274 A4GALT                 3358 #> 10           9 ENSG00000118017 A4GNT                  1779 #> # ℹ 60,654 more rows"},{"path":"/articles/census_dataset_presence.html","id":"identifying-genes-measured-in-a-specific-dataset","dir":"Articles","previous_headings":"","what":"Identifying genes measured in a specific dataset","title":"Genes measured in each cell (dataset presence matrix)","text":"Now dataset table, genes metadata table, dataset presence matrix, can check gene set genes measured specific dataset. Important: presence matrix indexed soma_joinid, positionally indexed. words: first dimension presence matrix dataset’s soma_joinid, stored census_datasets dataframe. second dimension presence matrix feature’s soma_joinid, stored var dataframe. presence matrix method $take() lets slice soma_joinids census_datasets var. full presence matrix, slices , can exported regular matrix method $get_one_based_matrix() Let’s find gene \"ENSG00000286096\" measured dataset id \"97a17473-e2b1-4f31-a544-44a60773e2dd\".","code":"# Get soma_joinid for datasets and genes of interest var_joinid <- var_df$soma_joinid[var_df$feature_id == \"ENSG00000286096\"] dataset_joinid <- datasets_df$soma_joinid[datasets_df$dataset_id == \"97a17473-e2b1-4f31-a544-44a60773e2dd\"]  # Slice presence matrix with datasets and genes of interest presence_matrix_slice <- presence_matrix$take(i = dataset_joinid, j = var_joinid)  # Convert presence matrix to regular matrix presence_matrix_slice <- presence_matrix_slice$get_one_based_matrix()  # Find how if the gene is present in this dataset is_present <- presence_matrix_slice[, , drop = TRUE] cat(paste(\"Feature is\", if (is_present) \"present.\" else \"not present.\")) #> Feature is present."},{"path":"/articles/census_dataset_presence.html","id":"identifying-datasets-that-measured-specific-genes","dir":"Articles","previous_headings":"","what":"Identifying datasets that measured specific genes","title":"Genes measured in each cell (dataset presence matrix)","text":"Similarly, can determine datasets measured specific gene set genes.","code":"# Grab the feature's soma_joinid from the var dataframe var_joinid <- var_df$soma_joinid[var_df$feature_id == \"ENSG00000286096\"]  # The presence matrix is indexed by the joinids of the dataset and var dataframes, # so slice out the feature of interest by its joinid. presence_matrix_slice  <- presence_matrix$take(j = var_joinid)$get_one_based_matrix() measured_datasets <- presence_matrix_slice[, , drop = TRUE] != 0 dataset_joinids <- datasets_df$soma_joinid[measured_datasets]  # From the datasets dataframe, slice out the datasets which have a joinid in the list print(datasets_df[dataset_joinids, ]) #> # A tibble: 42 × 8 #>    soma_joinid collection_id     collection_name collection_doi dataset_id dataset_title #>          <int> <chr>             <chr>           <chr>          <chr>      <chr>         #>  1           4 3f50314f-bdc9-40… Single-cell se… 10.1016/j.cce… bd65a70f-… Single-cell … #>  2           5 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… ff45e623-… Tabula Sapie… #>  3           6 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… f01bdd17-… Tabula Sapie… #>  4           7 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e6a11140-… Tabula Sapie… #>  5           8 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e5c63d94-… Tabula Sapie… #>  6          10 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… d77ec7d6-… Tabula Sapie… #>  7          11 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… cee11228-… Tabula Sapie… #>  8          13 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… a2d4d33e-… Tabula Sapie… #>  9          14 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… a0754256-… Tabula Sapie… #> 10          18 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… 6d41668c-… Tabula Sapie… #> # ℹ 32 more rows #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int>"},{"path":"/articles/census_dataset_presence.html","id":"identifying-all-genes-measured-in-a-dataset","dir":"Articles","previous_headings":"","what":"Identifying all genes measured in a dataset","title":"Genes measured in each cell (dataset presence matrix)","text":"Finally, can find set genes measured cells given dataset.","code":"# Slice the dataset(s) of interest, and get the joinid(s) dataset_joinids <- datasets_df$soma_joinid[datasets_df$collection_id == \"17481d16-ee44-49e5-bcf0-28c0780d8c4a\"]  # Slice the presence matrix by the first dimension, i.e., by dataset presence_matrix_slice <- presence_matrix$take(i = dataset_joinids)$get_one_based_matrix() genes_measured <- Matrix::colSums(presence_matrix_slice) > 0 var_joinids <- var_df$soma_joinid[genes_measured]  print(var_df[var_joinids, ]) #> # A tibble: 27,210 × 4 #>    soma_joinid feature_id      feature_name feature_length #>          <int> <chr>           <chr>                 <int> #>  1           0 ENSG00000121410 A1BG                   3999 #>  2           1 ENSG00000268895 A1BG-AS1               3374 #>  3           2 ENSG00000148584 A1CF                   9603 #>  4           3 ENSG00000175899 A2M                    6318 #>  5           4 ENSG00000245105 A2M-AS1                2948 #>  6           5 ENSG00000166535 A2ML1                  7156 #>  7           7 ENSG00000184389 A3GALT2                1023 #>  8           8 ENSG00000128274 A4GALT                 3358 #>  9           9 ENSG00000118017 A4GNT                  1779 #> 10          10 ENSG00000094914 AAAS                   4727 #> # ℹ 27,200 more rows"},{"path":"/articles/census_dataset_presence.html","id":"close-the-census","dir":"Articles","previous_headings":"Identifying all genes measured in a dataset","what":"Close the census","title":"Genes measured in each cell (dataset presence matrix)","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/census_datasets.html","id":"fetching-the-datasets-table","dir":"Articles","previous_headings":"","what":"Fetching the datasets table","title":"Census Datasets example","text":"Census contains top-level data frame itemizing datasets contained therein. can read SOMADataFrame Arrow Table: R data frame: sum cell counts across datasets match number cells across SOMA experiments (human, mouse).","code":"library(\"cellxgene.census\") census <- open_soma() census_datasets <- census$get(\"census_info\")$get(\"datasets\")$read()$concat() print(census_datasets) #> Table #> 593 rows x 8 columns #> $soma_joinid <int64 not null> #> $collection_id <large_string not null> #> $collection_name <large_string not null> #> $collection_doi <large_string not null> #> $dataset_id <large_string not null> #> $dataset_title <large_string not null> #> $dataset_h5ad_path <large_string not null> #> $dataset_total_cell_count <int64 not null> census_datasets <- as.data.frame(census_datasets) print(census_datasets[, c(   \"dataset_id\",   \"dataset_title\",   \"dataset_total_cell_count\" )]) #> # A tibble: 593 × 3 #>    dataset_id                           dataset_title             dataset_total_cell_c…¹ #>    <chr>                                <chr>                                      <int> #>  1 f171db61-e57e-4535-a06a-35d8b6ef8f2b donor_p13_trophoblasts                     31497 #>  2 ecf2e08e-2032-4a9e-b466-b65b395f4a02 All donors trophoblasts                    67070 #>  3 74cff64f-9da9-4b2a-9b3b-8a04a1598040 All donors all cell stat…                 286326 #>  4 5af90777-6760-4003-9dba-8f945fec6fdf Single-cell transcriptom…                 270855 #>  5 bd65a70f-b274-4133-b9dd-0d1431b6af34 Single-cell sequencing l…                 167283 #>  6 ff45e623-7f5f-46e3-b47d-56be0341f66b Tabula Sapiens - Pancreas                  13497 #>  7 f01bdd17-4902-40f5-86e3-240d66dd2587 Tabula Sapiens - Salivar…                  27199 #>  8 e6a11140-2545-46bc-929e-da243eed2cae Tabula Sapiens - Heart                     11505 #>  9 e5c63d94-593c-4338-a489-e1048599e751 Tabula Sapiens - Bladder                   24583 #> 10 d8732da6-8d1d-42d9-b625-f2416c30054b Tabula Sapiens - Trachea                    9522 #> # ℹ 583 more rows #> # ℹ abbreviated name: ¹​dataset_total_cell_count census_data <- census$get(\"census_data\") all_experiments <- lapply(census_data$to_list(), function(x) census_data$get(x$name)) print(all_experiments) #> $mus_musculus #> <SOMAExperiment> #>   uri: s3://cellxgene-data-public/cell-census/2023-07-25/soma/census_data/mus_musculus  #>   arrays: obs*  #>   groups: ms*  #>  #> $homo_sapiens #> <SOMAExperiment> #>   uri: s3://cellxgene-data-public/cell-census/2023-07-25/soma/census_data/homo_sapiens  #>   arrays: obs*  #>   groups: ms* experiments_total_cells <- sum(sapply(all_experiments, function(x) {   nrow(x$obs$read(column_names = c(\"soma_joinid\"))$concat()) }))  print(paste(\"Found\", experiments_total_cells, \"cells in all experiments.\")) #> [1] \"Found 61656118 cells in all experiments.\" print(paste(   \"Found\", sum(as.vector(census_datasets$dataset_total_cell_count)),   \"cells in all datasets.\" )) #> [1] \"Found 61656118 cells in all datasets.\""},{"path":"/articles/census_datasets.html","id":"fetching-the-expression-data-from-a-single-dataset","dir":"Articles","previous_headings":"","what":"Fetching the expression data from a single dataset","title":"Census Datasets example","text":"Let’s pick one dataset slice census, turn Seurat -memory object. (requires Seurat package installed beforehand.) Create query mouse experiment, “RNA” measurement, dataset_id.","code":"census_datasets[census_datasets$dataset_id == \"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\", ] #> # A tibble: 1 × 8 #>   soma_joinid collection_id      collection_name collection_doi dataset_id dataset_title #>         <int> <chr>              <chr>           <chr>          <chr>      <chr>         #> 1         522 0b9d8a04-bb9d-44d… Tabula Muris S… 10.1038/s4158… 0bd1a1de-… Bone marrow … #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int> library(\"tiledbsoma\") #> Warning: package 'tiledbsoma' was built under R version 4.3.1 obs_query <- SOMAAxisQuery$new(   value_filter = \"dataset_id == '0bd1a1de-3aee-40e0-b2ec-86c7a30c7149'\" ) expt_query <- census_data$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = obs_query ) dataset_seurat <- expt_query$to_seurat(c(counts = \"raw\")) #> The legacy packages maptools, rgdal, and rgeos, underpinning the sp package, #> which was just loaded, will retire in October 2023. #> Please refer to R-spatial evolution reports for details, especially #> https://r-spatial.org/r/2023/05/15/evolution4.html. #> It may be desirable to make the sf package available; #> package maintainers should consider adding sf to Suggests:. #> The sp package is now running under evolution status 2 #>      (status 2 uses the sf package in place of rgdal) print(dataset_seurat) #> An object of class Seurat  #> 52392 features across 40220 samples within 1 assay  #> Active assay: RNA (52392 features, 0 variable features)"},{"path":"/articles/census_datasets.html","id":"downloading-the-original-source-h5ad-file-of-a-dataset","dir":"Articles","previous_headings":"","what":"Downloading the original source H5AD file of a dataset","title":"Census Datasets example","text":"can use cellxgene.census::get_source_h5ad_uri() API fetch URI pointing H5AD associated dataset_id. H5AD can download CZ CELLxGENE Discover, may contain additional data-submitter provided information included Census. can fetch location cloud directly download system. local H5AD file can used R using SeuratDisk’s anndata converter.","code":"# Option 1: Direct download download_source_h5ad(   dataset_id = \"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\",   file = \"/tmp/Tabula_Muris_Senis-bone_marrow.h5ad\",   overwrite = TRUE ) # Option 2: Get location and download via preferred method get_source_h5ad_uri(\"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\") #> $uri #> [1] \"s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/0bd1a1de-3aee-40e0-b2ec-86c7a30c7149.h5ad\" #>  #> $s3_region #> [1] \"us-west-2\""},{"path":"/articles/census_datasets.html","id":"close-the-census","dir":"Articles","previous_headings":"Downloading the original source H5AD file of a dataset","what":"Close the census","title":"Census Datasets example","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/census_query_extract.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the census","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version). can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/census_query_extract.html","id":"querying-cell-metadata-obs","dir":"Articles","previous_headings":"","what":"Querying cell metadata (obs)","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"human gene metadata Census, RNA assays, located census$get(\"census_data\")$get(\"homo_sapiens\")$obs. SOMADataFrame can materialized R data frame (tibble) using .data.frame(obs$read()$concat()). mouse cell metadata census$get(\"census_data\")$get(\"mus_musculus\").obs. slicing cell metadata two relevant arguments can passed read(): column_names — character vector indicating metadata columns fetch. Expressions one comparisons Comparisons one <column> <op> <value> <column> <op> <column> Expressions can combine comparisons using && || op one < | > | <= | >= | == | != %% learn metadata columns available fetching filtering can directly look keys cell metadata. soma_joinid special SOMADataFrame column used join operations. definition columns can found Census schema. can used fetch specific columns specific rows matching condition. latter need know values looking priori. example let’s see possible values available sex. can load cell metadata fetching column sex. can see three different values sex, \"male\", \"female\" \"unknown\". information can fetch cell metatadata specific sex value, example \"unknown\". can use column_names value_filter perform specific queries. example let’s fetch disease column cell_type \"B cell\" tissue_general \"lung\".","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$obs$colnames() #>  [1] \"soma_joinid\"                              #>  [2] \"dataset_id\"                               #>  [3] \"assay\"                                    #>  [4] \"assay_ontology_term_id\"                   #>  [5] \"cell_type\"                                #>  [6] \"cell_type_ontology_term_id\"               #>  [7] \"development_stage\"                        #>  [8] \"development_stage_ontology_term_id\"       #>  [9] \"disease\"                                  #> [10] \"disease_ontology_term_id\"                 #> [11] \"donor_id\"                                 #> [12] \"is_primary_data\"                          #> [13] \"self_reported_ethnicity\"                  #> [14] \"self_reported_ethnicity_ontology_term_id\" #> [15] \"sex\"                                      #> [16] \"sex_ontology_term_id\"                     #> [17] \"suspension_type\"                          #> [18] \"tissue\"                                   #> [19] \"tissue_ontology_term_id\"                  #> [20] \"tissue_general\"                           #> [21] \"tissue_general_ontology_term_id\" unique(as.data.frame(census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(column_names = \"sex\")$concat())) #> # A tibble: 3 × 1 #>   sex     #>   <chr>   #> 1 unknown #> 2 female  #> 3 male as.data.frame(census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(value_filter = \"sex == 'unknown'\")$concat()) #> # A tibble: 3,251,334 × 21 #>    soma_joinid dataset_id  assay assay_ontology_term_id cell_type cell_type_ontology_t…¹ #>          <int> <chr>       <chr> <chr>                  <chr>     <chr>                  #>  1           0 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  2           1 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #>  3           2 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  4           3 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  5           4 f171db61-e… 10x … EFO:0009922            extravil… CL:0008036             #>  6           5 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #>  7           6 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  8           7 f171db61-e… 10x … EFO:0009922            extravil… CL:0008036             #>  9           8 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #> 10           9 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #> # ℹ 3,251,324 more rows #> # ℹ abbreviated name: ¹​cell_type_ontology_term_id #> # ℹ 15 more variables: development_stage <chr>, #> #   development_stage_ontology_term_id <chr>, disease <chr>, #> #   disease_ontology_term_id <chr>, donor_id <chr>, is_primary_data <lgl>, #> #   self_reported_ethnicity <chr>, self_reported_ethnicity_ontology_term_id <chr>, #> #   sex <chr>, sex_ontology_term_id <chr>, suspension_type <chr>, tissue <chr>, … cell_metadata_b_cell <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   value_filter = \"cell_type == 'B cell' & tissue_general == 'lung'\",   column_names = \"disease\" )  cell_metadata_b_cell <- as.data.frame(cell_metadata_b_cell$concat())  table(cell_metadata_b_cell) #> disease #> chronic obstructive pulmonary disease                              COVID-19  #>                                  6369                                  2729  #>          hypersensitivity pneumonitis             interstitial lung disease  #>                                    52                                   376  #>                   lung adenocarcinoma             lung large cell carcinoma  #>                                 62351                                  1534  #>              lymphangioleiomyomatosis         non-small cell lung carcinoma  #>                                   133                                 17484  #>   non-specific interstitial pneumonia                                normal  #>                                   231                                 25461  #>                 pleomorphic carcinoma                             pneumonia  #>                                  1210                                    50  #>                   pulmonary emphysema                    pulmonary fibrosis  #>                                  1512                                  6798  #>                 pulmonary sarcoidosis             small cell lung carcinoma  #>                                     6                                   583  #>          squamous cell lung carcinoma  #>                                 11920"},{"path":"/articles/census_query_extract.html","id":"querying-gene-metadata-var","dir":"Articles","previous_headings":"","what":"Querying gene metadata (var)","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"human gene metadata Census located census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var. Similarly cell metadata, SOMADataFrame thus can also use method read(). mouse gene metadata census$get(\"census_data\")$get(\"mus_musculus\")$ms$get(\"RNA\")$var. Let’s take look metadata available column selection row filtering. exception soma_joinid columns defined Census schema. Similarly cell metadata, can use operations learn fetch gene metadata. example, get feature_name feature_length genes \"ENSG00000161798\" \"ENSG00000188229\" can following.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$colnames() #> [1] \"soma_joinid\"    \"feature_id\"     \"feature_name\"   \"feature_length\" var_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$read(   value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   column_names = c(\"feature_name\", \"feature_length\") )  as.data.frame(var_df$concat()) #> # A tibble: 2 × 2 #>   feature_name feature_length #>   <chr>                 <int> #> 1 AQP5                   1884 #> 2 TUBB4B                 2037"},{"path":"/articles/census_query_extract.html","id":"querying-expression-data-as-seurat","dir":"Articles","previous_headings":"","what":"Querying expression data as Seurat","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"convenient way query fetch expression data use get_seurat method cellxgene.census API. method combines column selection value filtering described obtain slices expression data based metadata queries. method return Seurat object, takes input census object, string organism, cell gene metadata can specify filters column selection described following arguments: obs_column_names — character vector indicating columns select cell metadata. obs_value_filter — expression selection conditions fetch cells meeting criteria. var_column_names — character vector indicating columns select gene metadata. var_value_filter — expression selection conditions fetch genes meeting criteria. example want fetch expression data : Genes \"ENSG00000161798\" \"ENSG00000188229\". \"B cells\" \"lung\" \"COVID-19\". gene metadata adding sex cell metadata. full description refer ?cellxgene.census::get_seurat.","code":"library(\"Seurat\")  seurat_obj <- get_seurat(   census, \"Homo sapiens\",   obs_column_names = c(\"cell_type\", \"tissue_general\", \"disease\", \"sex\"),   var_value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   obs_value_filter = \"cell_type == 'B cell' & tissue_general == 'lung' & disease == 'COVID-19'\" ) seurat_obj #> An object of class Seurat  #> 2 features across 2729 samples within 1 assay  #> Active assay: RNA (2 features, 0 variable features) head(seurat_obj[[]]) #>                orig.ident nCount_RNA nFeature_RNA cell_type tissue_general  disease #> cell5946018 SeuratProject          0            0    B cell           lung COVID-19 #> cell5948526 SeuratProject          1            1    B cell           lung COVID-19 #> cell5949180 SeuratProject          0            0    B cell           lung COVID-19 #> cell5949686 SeuratProject          0            0    B cell           lung COVID-19 #> cell5950730 SeuratProject          0            0    B cell           lung COVID-19 #> cell5952197 SeuratProject          0            0    B cell           lung COVID-19 #>                 sex #> cell5946018    male #> cell5948526 unknown #> cell5949180    male #> cell5949686 unknown #> cell5950730    male #> cell5952197 unknown head(seurat_obj$RNA[[]]) #>                 feature_name feature_length #> ENSG00000161798         AQP5           1884 #> ENSG00000188229       TUBB4B           2037"},{"path":"/articles/census_query_extract.html","id":"querying-expression-data-as-singlecellexperiment","dir":"Articles","previous_headings":"","what":"Querying expression data as SingleCellExperiment","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"Similarly previous section, get_single_cell_experiment method cellxgene.census API. behaves exactly get_seurat returns SingleCellExperiment object. example, repeat query can simply following. full description refer ?cellxgene.census::get_single_cell_experiment.","code":"library(\"SingleCellExperiment\")  sce_obj <- get_single_cell_experiment(   census, \"Homo sapiens\",   obs_column_names = c(\"cell_type\", \"tissue_general\", \"disease\", \"sex\"),   var_value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   obs_value_filter = \"cell_type == 'B cell' & tissue_general == 'lung' & disease == 'COVID-19'\" ) sce_obj #> class: SingleCellExperiment  #> dim: 2 2729  #> metadata(0): #> assays(1): counts #> rownames(2): ENSG00000161798 ENSG00000188229 #> rowData names(2): feature_name feature_length #> colnames(2729): obs5946018 obs5948526 ... obs48038140 obs48038164 #> colData names(4): cell_type tissue_general disease sex #> reducedDimNames(0): #> mainExpName: RNA #> altExpNames(0): head(colData(sce_obj)) #> DataFrame with 6 rows and 4 columns #>              cell_type tissue_general     disease         sex #>            <character>    <character> <character> <character> #> obs5946018      B cell           lung    COVID-19        male #> obs5948526      B cell           lung    COVID-19     unknown #> obs5949180      B cell           lung    COVID-19        male #> obs5949686      B cell           lung    COVID-19     unknown #> obs5950730      B cell           lung    COVID-19        male #> obs5952197      B cell           lung    COVID-19     unknown head(rowData(sce_obj)) #> DataFrame with 2 rows and 2 columns #>                 feature_name feature_length #>                  <character>      <integer> #> ENSG00000161798         AQP5           1884 #> ENSG00000188229       TUBB4B           2037"},{"path":"/articles/census_query_extract.html","id":"close-the-census","dir":"Articles","previous_headings":"Querying expression data as SingleCellExperiment","what":"Close the census","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/comp_bio_census_info.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Learning about the CZ CELLxGENE Census","text":"cellxgene.census R package contains convenient open_soma() API open version Census (stable default). can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/comp_bio_census_info.html","id":"census-organization","dir":"Articles","previous_headings":"","what":"Census organization","title":"Learning about the CZ CELLxGENE Census","text":"Census schema defines structure Census. short, can think Census structured collection items stores different pieces information. items parent collection SOMA objects various types can accessed TileDB-SOMA API (documentation). cellxgene.census package contains convenient wrappers TileDB-SOMA API. example function used open Census: cellxgene_census.open_soma().","code":""},{"path":"/articles/comp_bio_census_info.html","id":"main-census-components","dir":"Articles","previous_headings":"Census organization","what":"Main Census components","title":"Learning about the CZ CELLxGENE Census","text":"command created census, SOMACollection, R6 class providing key-value associative map. get() method can access two top-level collection members, census_info census_data, instances SOMACollection.","code":""},{"path":"/articles/comp_bio_census_info.html","id":"census-summary-info","dir":"Articles","previous_headings":"Census organization","what":"Census summary info","title":"Learning about the CZ CELLxGENE Census","text":"census$get(\"census_info\")$get(\"summary\"): data frame high-level information Census, e.g. build date, total cell count, etc. census$get(\"census_info\")$get(\"datasets\"): data frame datasets CELLxGENE Discover used create Census. census$get(\"census_info\")$get(\"summary_cell_counts\"): data frame cell counts stratified relevant cell metadata Census data Data organism stored independent SOMAExperiment objects specialized form SOMACollection. store data matrix (cell genes), cell metadata, gene metadata, useful components covered notebook. data organized one organism – Homo sapiens: census$get(\"census_data\")$get(\"homo_sapiens\")$obs: Cell metadata census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\"): Data matrices, currently … census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$X$get(\"raw\"): matrix raw counts SOMASparseNDArray census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var: Gene Metadata","code":""},{"path":"/articles/comp_bio_census_info.html","id":"cell-metadata","dir":"Articles","previous_headings":"","what":"Cell metadata","title":"Learning about the CZ CELLxGENE Census","text":"can obtain cell metadata variables directly querying columns corresponding SOMADataFrame. variables can used querying Census case want work specific cells. variables defined CELLxGENE dataset schema except following: soma_joinid: SOMA-defined value use join operations. dataset_id: dataset id encoded census$get(\"census_info\")$get(\"datasets\"). tissue_general tissue_general_ontology_term_id: high-level tissue mapping.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$obs$colnames() #>  [1] \"soma_joinid\"                              #>  [2] \"dataset_id\"                               #>  [3] \"assay\"                                    #>  [4] \"assay_ontology_term_id\"                   #>  [5] \"cell_type\"                                #>  [6] \"cell_type_ontology_term_id\"               #>  [7] \"development_stage\"                        #>  [8] \"development_stage_ontology_term_id\"       #>  [9] \"disease\"                                  #> [10] \"disease_ontology_term_id\"                 #> [11] \"donor_id\"                                 #> [12] \"is_primary_data\"                          #> [13] \"self_reported_ethnicity\"                  #> [14] \"self_reported_ethnicity_ontology_term_id\" #> [15] \"sex\"                                      #> [16] \"sex_ontology_term_id\"                     #> [17] \"suspension_type\"                          #> [18] \"tissue\"                                   #> [19] \"tissue_ontology_term_id\"                  #> [20] \"tissue_general\"                           #> [21] \"tissue_general_ontology_term_id\""},{"path":"/articles/comp_bio_census_info.html","id":"gene-metadata","dir":"Articles","previous_headings":"","what":"Gene metadata","title":"Learning about the CZ CELLxGENE Census","text":"Similarly, can obtain gene metadata variables directly querying columns corresponding SOMADataFrame. variables can use querying Census case specific genes interested . variables defined CELLxGENE dataset schema except following: soma_joinid: SOMA-defined value use join operations. feature_length: length base pairs gene.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$colnames() #> [1] \"soma_joinid\"    \"feature_id\"     \"feature_name\"   \"feature_length\""},{"path":"/articles/comp_bio_census_info.html","id":"census-summary-content-tables","dir":"Articles","previous_headings":"","what":"Census summary content tables","title":"Learning about the CZ CELLxGENE Census","text":"can take quick look high-level Census information looking census$get(\"census_info\")$get(\"summary\"): special interest label-value combinations : total_cell_count total number cells Census. unique_cell_count number unique cells, cells may present twice due meta-analysis consortia-like data. number_donors_homo_sapiens number_donors_mus_musculus number individuals human mouse. guaranteed unique one individual ID may present identical different datasets.","code":"as.data.frame(census$get(\"census_info\")$get(\"summary\")$read()$concat()) #> # A tibble: 7 × 3 #>   soma_joinid label                      value      #>         <int> <chr>                      <chr>      #> 1           0 census_schema_version      1.0.0      #> 2           1 census_build_date          2023-07-25 #> 3           2 dataset_schema_version     3.0.0      #> 4           3 total_cell_count           61656118   #> 5           4 unique_cell_count          37447773   #> 6           5 number_donors_homo_sapiens 13035      #> 7           6 number_donors_mus_musculus 1417"},{"path":"/articles/comp_bio_census_info.html","id":"cell-counts-by-cell-metadata","dir":"Articles","previous_headings":"Census summary content tables","what":"Cell counts by cell metadata","title":"Learning about the CZ CELLxGENE Census","text":"looking census$get(\"census_info)$get(\"summary_cell_counts\") can get general idea cell counts stratified relevant cell metadata. cell metadata included table, can take look cell gene metadata available sections “Cell metadata” “Gene metadata”. line retrieves table casts R data frame: combination organism values category cell metadata can take look total_cell_count unique_cell_count cell counts combination. values category specified ontology_term_id label, value’s IDs labels, respectively.","code":"census_counts <- as.data.frame(census$get(\"census_info\")$get(\"summary_cell_counts\")$read()$concat()) head(census_counts) #> # A tibble: 6 × 7 #>   soma_joinid organism     category ontology_term_id unique_cell_count total_cell_count #>         <int> <chr>        <chr>    <chr>                        <int>            <int> #> 1           0 Homo sapiens all      na                        33364242         56400873 #> 2           1 Homo sapiens assay    EFO:0008722                 264166           279635 #> 3           2 Homo sapiens assay    EFO:0008780                  25652            51304 #> 4           3 Homo sapiens assay    EFO:0008919                  89477           206754 #> 5           4 Homo sapiens assay    EFO:0008931                  78750           188248 #> 6           5 Homo sapiens assay    EFO:0008953                   4693             9386 #> # ℹ 1 more variable: label <chr>"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-metadata-included-in-the-summary-counts-table","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: cell metadata included in the summary counts table","title":"Learning about the CZ CELLxGENE Census","text":"get available cell metadata summary counts table can following. Remember cell metadata available, variables omitted creation table.","code":"t(table(census_counts$organism, census_counts$category)) #>                           #>                           Homo sapiens Mus musculus #>   all                                1            1 #>   assay                             19            9 #>   cell_type                        613          248 #>   disease                           64            5 #>   self_reported_ethnicity           26            1 #>   sex                                3            3 #>   suspension_type                    1            1 #>   tissue                           220           66 #>   tissue_general                    54           27"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-counts-for-each-sequencing-assay-in-human-data","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: cell counts for each sequencing assay in human data","title":"Learning about the CZ CELLxGENE Census","text":"get cell counts sequencing assay type human data, can perform following operations:","code":"human_assay_counts <- census_counts[census_counts$organism == \"Homo sapiens\" & census_counts$category == \"assay\", ] human_assay_counts <- human_assay_counts[order(human_assay_counts$total_cell_count, decreasing = TRUE), ]"},{"path":"/articles/comp_bio_census_info.html","id":"example-number-of-microglial-cells-in-the-census","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: number of microglial cells in the Census","title":"Learning about the CZ CELLxGENE Census","text":"specific term categories shown can directly find number cells term.","code":"census_counts[census_counts$label == \"microglial cell\", ] #> # A tibble: 2 × 7 #>   soma_joinid organism     category  ontology_term_id unique_cell_count total_cell_count #>         <int> <chr>        <chr>     <chr>                        <int>            <int> #> 1          69 Homo sapiens cell_type CL:0000129                  268114           370771 #> 2        1038 Mus musculus cell_type CL:0000129                   48998            62617 #> # ℹ 1 more variable: label <chr>"},{"path":"/articles/comp_bio_census_info.html","id":"understanding-census-contents-beyond-the-summary-tables","dir":"Articles","previous_headings":"","what":"Understanding Census contents beyond the summary tables","title":"Learning about the CZ CELLxGENE Census","text":"using pre-computed tables census$get(\"census_info\") easy quick way understand contents Census, falls short want learn certain slices Census. example, may want learn : cell types available human liver? total number cells lung datasets stratified sequencing technology? sex distribution cells brain mouse? diseases available T cells? questions can answered directly querying cell metadata shown examples .","code":""},{"path":"/articles/comp_bio_census_info.html","id":"example-all-cell-types-available-in-human","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: all cell types available in human","title":"Learning about the CZ CELLxGENE Census","text":"exemplify process accessing slicing cell metadata summary stats, let’s start trivial example take look human cell types available Census: number rows total number cells humans. Now, wish get cell counts per cell type can work data frame. addition, focus cells marked is_primary_data=TRUE ensures de-duplicate cells appear CELLxGENE Discover. number unique cells. Now let’s look counts per cell type: shows abundant cell types “glutamatergic neuron”, “CD8-positive, alpha-beta T cell”, “CD4-positive, alpha-beta T cell”. Now let’s take look number unique cell types: total number different cell types human. information example can quickly obtained summary table census$get(\"census-info\")$get(\"summary_cell_counts\"). examples complex can achieved accessing cell metadata.","code":"obs_df <-   census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(column_names = c(\"cell_type\", \"is_primary_data\")) as.data.frame(obs_df$concat()) #> # A tibble: 56,400,873 × 2 #>    cell_type                     is_primary_data #>    <chr>                         <lgl>           #>  1 syncytiotrophoblast cell      FALSE           #>  2 placental villous trophoblast FALSE           #>  3 syncytiotrophoblast cell      FALSE           #>  4 syncytiotrophoblast cell      FALSE           #>  5 extravillous trophoblast      FALSE           #>  6 placental villous trophoblast FALSE           #>  7 syncytiotrophoblast cell      FALSE           #>  8 extravillous trophoblast      FALSE           #>  9 placental villous trophoblast FALSE           #> 10 syncytiotrophoblast cell      FALSE           #> # ℹ 56,400,863 more rows obs_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = \"cell_type\",   value_filter = \"is_primary_data == TRUE\" )  obs_df <- as.data.frame(obs_df$concat()) nrow(obs_df) #> [1] 33364242 human_cell_type_counts <- table(obs_df$cell_type) sort(human_cell_type_counts, decreasing = TRUE)[1:10] #>  #>                          neuron            glutamatergic neuron  #>                         2673669                         1541605  #> CD4-positive, alpha-beta T cell CD8-positive, alpha-beta T cell  #>                         1258976                         1235987  #>              classical monocyte                          B cell  #>                         1030996                          908651  #>                     native cell             natural killer cell  #>                          889262                          768755  #>                      macrophage                 oligodendrocyte  #>                          721687                          710242 length(human_cell_type_counts) #> [1] 599"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-types-available-in-human-liver","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: cell types available in human liver","title":"Learning about the CZ CELLxGENE Census","text":"Similar example , can learn cell types available specific tissue, e.g. liver. achieve goal just need limit cell metadata tissue. use information cell metadata variable tissue_general. variable contains high-level tissue label cells Census: cell types cell counts human liver.","code":"obs_liver_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = \"cell_type\",   value_filter = \"is_primary_data == TRUE & tissue_general == 'liver'\" )  obs_liver_df <- as.data.frame(obs_liver_df$concat())  sort(table(obs_liver_df$cell_type), decreasing = TRUE)[1:10] #>  #>                          T cell                     hepatoblast  #>                           85739                           58447  #>                 neoplastic cell                    erythroblast  #>                           52431                           45605  #>                        monocyte                      hepatocyte  #>                           31388                           28309  #>             natural killer cell    periportal region hepatocyte  #>                           26871                           23509  #>                      macrophage centrilobular region hepatocyte  #>                           16707                           15819"},{"path":"/articles/comp_bio_census_info.html","id":"example-diseased-t-cells-in-human-tissues","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: diseased T cells in human tissues","title":"Learning about the CZ CELLxGENE Census","text":"example going get counts diseased cells annotated T cells. sake example focus “CD8-positive, alpha-beta T cell” “CD4-positive, alpha-beta T cell”: cell counts annotated indicated disease across human tissues “CD8-positive, alpha-beta T cell” “CD4-positive, alpha-beta T cell”.","code":"obs_t_cells_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = c(\"disease\", \"tissue_general\"),   value_filter = \"is_primary_data == TRUE & disease != 'normal' & cell_type %in% c('CD8-positive, alpha-beta T cell', 'CD4-positive, alpha-beta T cell')\" )  obs_t_cells_df <- as.data.frame(obs_t_cells_df$concat())  print(table(obs_t_cells_df)) #>                                        tissue_general #> disease                                 adipose tissue adrenal gland  blood blood clot #>   B-cell non-Hodgkin lymphoma                        0             0  62499          0 #>   breast cancer                                      0             0      0          0 #>   chronic obstructive pulmonary disease              0             0      0          0 #>   chronic rhinitis                                   0             0      0          0 #>   clear cell renal carcinoma                         0             0   6548          0 #>   COVID-19                                           0             0 819428          0 #>   Crohn disease                                      0             0      0          0 #>   cystic fibrosis                                    0             0      0          0 #>   Down syndrome                                      0             0      0          0 #>   follicular lymphoma                                0             0      0          0 #>   influenza                                          0             0   8871          0 #>   interstitial lung disease                          0             0      0          0 #>   kidney benign neoplasm                             0             0     20          0 #>   kidney oncocytoma                                  0             0     16          0 #>   lung adenocarcinoma                                0           205      0          0 #>                                        tissue_general #> disease                                 bone marrow  brain breast  colon kidney  liver #>   B-cell non-Hodgkin lymphoma                     0      0      0      0      0      0 #>   breast cancer                                   0      0   1850      0      0      0 #>   chronic obstructive pulmonary disease           0      0      0      0      0      0 #>   chronic rhinitis                                0      0      0      0      0      0 #>   clear cell renal carcinoma                      0      0      0      0  20540      0 #>   COVID-19                                        0      0      0      0      0      0 #>   Crohn disease                                   0      0      0  17490      0      0 #>   cystic fibrosis                                 0      0      0      0      0      0 #>   Down syndrome                                 181      0      0      0      0      0 #>   follicular lymphoma                             0      0      0      0      0      0 #>   influenza                                       0      0      0      0      0      0 #>   interstitial lung disease                       0      0      0      0      0      0 #>   kidney benign neoplasm                          0      0      0      0     10      0 #>   kidney oncocytoma                               0      0      0      0   2408      0 #>   lung adenocarcinoma                             0   3274      0      0      0    507 #>                                        tissue_general #> disease                                   lung lymph node   nose pleural fluid #>   B-cell non-Hodgkin lymphoma                0          0      0             0 #>   breast cancer                              0          0      0             0 #>   chronic obstructive pulmonary disease   9382          0      0             0 #>   chronic rhinitis                           0          0    909             0 #>   clear cell renal carcinoma                 0         36      0             0 #>   COVID-19                               30578          0     13             0 #>   Crohn disease                              0          0      0             0 #>   cystic fibrosis                            7          0      0             0 #>   Down syndrome                              0          0      0             0 #>   follicular lymphoma                        0       1089      0             0 #>   influenza                                  0          0      0             0 #>   interstitial lung disease               1803          0      0             0 #>   kidney benign neoplasm                     0          0      0             0 #>   kidney oncocytoma                          0          0      0             0 #>   lung adenocarcinoma                   215013      24969      0         11558 #>                                        tissue_general #> disease                                 respiratory system saliva small intestine #>   B-cell non-Hodgkin lymphoma                            0      0               0 #>   breast cancer                                          0      0               0 #>   chronic obstructive pulmonary disease                  0      0               0 #>   chronic rhinitis                                       0      0               0 #>   clear cell renal carcinoma                             0      0               0 #>   COVID-19                                               4     41               0 #>   Crohn disease                                          0      0           52029 #>   cystic fibrosis                                        0      0               0 #>   Down syndrome                                          0      0               0 #>   follicular lymphoma                                    0      0               0 #>   influenza                                              0      0               0 #>   interstitial lung disease                              0      0               0 #>   kidney benign neoplasm                                 0      0               0 #>   kidney oncocytoma                                      0      0               0 #>   lung adenocarcinoma                                    0      0               0 #>  [ reached getOption(\"max.print\") -- omitted 10 rows ]"},{"path":"/articles/comp_bio_data_integration.html","id":"finding-and-fetching-data-from-mouse-liver-10x-genomics-and-smart-seq2","dir":"Articles","previous_headings":"","what":"Finding and fetching data from mouse liver (10X Genomics and Smart-Seq2)","title":"Integrating multi-dataset slices of data with Seurat","text":"Let’s load packages needed notebook. Now can open Census. notebook use Tabula Muris Senis data liver contains cells 10X Genomics Smart-Seq2 technologies. Let’s query datasets table Census filtering collection_name “Tabula Muris Senis” dataset_title “liver”. Now can use values dataset_id query load Seurat object cells datasets. can check cell counts 10X Genomics Smart-Seq2 data looking assay metadata.","code":"library(\"cellxgene.census\") library(\"Seurat\") census <- open_soma() census_datasets <- census$get(\"census_info\")$get(\"datasets\") census_datasets <- census_datasets$read(value_filter = \"collection_name == 'Tabula Muris Senis'\") census_datasets <- as.data.frame(census_datasets$concat())  # Print rows with liver data census_datasets[grep(\"Liver\", census_datasets$dataset_title), ] #> # A tibble: 2 × 8 #>   soma_joinid collection_id            collection_name collection_doi dataset_id #>         <int> <chr>                    <chr>           <chr>          <chr>      #> 1         525 0b9d8a04-bb9d-44da-aa27… Tabula Muris S… 10.1038/s4158… 4546e757-… #> 2         547 0b9d8a04-bb9d-44da-aa27… Tabula Muris S… 10.1038/s4158… 6202a243-… #> # ℹ 3 more variables: dataset_title <chr>, dataset_h5ad_path <chr>, #> #   dataset_total_cell_count <int> tabula_muris_liver_ids <- c(\"4546e757-34d0-4d17-be06-538318925fcd\", \"6202a243-b713-4e12-9ced-c387f8483dea\")  seurat_obj <- get_seurat(   census,   organism = \"Mus musculus\",   obs_value_filter = \"dataset_id %in% tabula_muris_liver_ids\" ) table(seurat_obj$assay) #>  #>  10x 3' v2 Smart-seq2  #>       7294       2859"},{"path":"/articles/comp_bio_data_integration.html","id":"gene-length-normalization-of-smart-seq2-data-","dir":"Articles","previous_headings":"","what":"Gene-length normalization of Smart-Seq2 data.","title":"Integrating multi-dataset slices of data with Seurat","text":"Smart-seq2 read counts normalized gene length. Lets first get gene lengths var.feature_length. Now can use normalize Smart-seq data. let’s split object assay. normalize Smart-seq slice using gene lengths merge back single object.","code":"smart_seq_gene_lengths <- seurat_obj$RNA[[]]$feature_length seurat_obj.list <- SplitObject(seurat_obj, split.by = \"assay\") seurat_obj.list[[\"Smart-seq2\"]][[\"RNA\"]]@counts <- seurat_obj.list[[\"Smart-seq2\"]][[\"RNA\"]]@counts / smart_seq_gene_lengths seurat_obj <- merge(seurat_obj.list[[1]], seurat_obj.list[[2]])"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-with-seurat","dir":"Articles","previous_headings":"","what":"Integration with Seurat","title":"Integrating multi-dataset slices of data with Seurat","text":"use native integration capabilities Seurat. comprehensive usage best practices Seurat intergation please refer doc site Seurat.","code":""},{"path":"/articles/comp_bio_data_integration.html","id":"inspecting-data-prior-to-integration","dir":"Articles","previous_headings":"Integration with Seurat","what":"Inspecting data prior to integration","title":"Integrating multi-dataset slices of data with Seurat","text":"Let’s take look strength batch effects data. perform embedding visualization via UMAP. Let’s basic data normalization variable gene selection now perform PCA UMAP   can see batch effects strong cells cluster primarily assay cell_type. Properly integrated embedding principle cluster primarily cell_type, assay best randomly distributed.","code":"seurat_obj <- SCTransform(seurat_obj) seurat_obj <- FindVariableFeatures(seurat_obj, selection.method = \"vst\", nfeatures = 2000) seurat_obj <- RunPCA(seurat_obj, features = VariableFeatures(object = seurat_obj)) seurat_obj <- RunUMAP(seurat_obj, dims = 1:30) # By assay p1 <- DimPlot(seurat_obj, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"data-integration-with-seurat","dir":"Articles","previous_headings":"Integration with Seurat","what":"Data integration with Seurat","title":"Integrating multi-dataset slices of data with Seurat","text":"Whenever query fetch Census data multiple datasets integration needs performed evidenced batch effects observed. paramaters Seurat used notebook selected model run quickly. best practices integration single-cell data using Seurat please refer documentation page. seurat_d reading article integrated cell atlas human lung health disease Sikkema et al. perfomed integration 43 datasets Lung. focus metadata Census can batch information integration.","code":""},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id","title":"Integrating multi-dataset slices of data with Seurat","text":"cells Census annotated dataset come \"dataset_id\". great place start integration. let’s run Seurat integration pipeline. First define model batch set dataset_id. Firs normalize select variable genes seperated batch key dataset_id Now perform integration. Let’s inspect results normalization UMAP visulization. plot UMAP.   Great! can see clustering longer mainly driven assay, albeit still contributing . Great! can see clustering longer mainly driven assay, albeit still contributing .","code":"# split the dataset into a list of two seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x) })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list) seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\") DefaultAssay(seurat_obj.combined) <- \"integrated\"  # Run the standard workflow for visualization and clustering seurat_obj.combined <- ScaleData(seurat_obj.combined, verbose = FALSE) seurat_obj.combined <- RunPCA(seurat_obj.combined, npcs = 30, verbose = FALSE) seurat_obj.combined <- RunUMAP(seurat_obj.combined, reduction = \"pca\", dims = 1:30) # By assay p1 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id-and-controlling-for-batch-using-donor_id","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id and controlling for batch using donor_id","title":"Integrating multi-dataset slices of data with Seurat","text":"Similar dataset_id, cells Census annotated donor_id. definition donor_id depends dataset left discretion data curators. However still rich information can used batch variable integration. donor_id guaranteed unique across cells Census, strongly recommend concatenating dataset_id donor_id use batch separator Seurat Now perform integration. inspect new results UMAP. Plot UMAP.   can see using dataset_id donor_id batch cells now mostly cluster cell type.","code":"# split the dataset into a list of two seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently controlling for batch seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x, vars.to.regress = \"donor_id\") })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list) seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") #> Finding all pairwise anchors #> Running CCA #> Merging objects #> Finding neighborhoods #> Finding anchors #>  Found 7026 anchors #> Filtering anchors #>  Retained 4880 anchors seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\") #> Merging dataset 1 into 2 #> Extracting anchors for merged samples #> Finding integration vectors #> Finding integration vector weights #> Integrating data DefaultAssay(seurat_obj.combined) <- \"integrated\"  # Run the standard workflow for visualization and clustering seurat_obj.combined <- RunPCA(seurat_obj.combined, npcs = 30, verbose = FALSE) seurat_obj.combined <- RunUMAP(seurat_obj.combined, reduction = \"pca\", dims = 1:30) #> 18:25:53 UMAP embedding parameters a = 0.9922 b = 1.112 #> 18:25:53 Read 10153 rows and found 30 numeric columns #> 18:25:53 Using Annoy for neighbor search, n_neighbors = 30 #> 18:25:53 Building Annoy index with metric = cosine, n_trees = 50 #> 0%   10   20   30   40   50   60   70   80   90   100% #> [----|----|----|----|----|----|----|----|----|----| #> **************************************************| #> 18:25:54 Writing NN index file to temp file /var/folders/9q/j_1zpqns7vz_s5n9l6_b943r0000gr/T//RtmpaMpqKs/file9d602f8d4d28 #> 18:25:54 Searching Annoy index using 1 thread, search_k = 3000 #> 18:25:57 Annoy recall = 100% #> 18:25:57 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30 #> 18:25:58 Initializing from normalized Laplacian + noise (using irlba) #> 18:25:58 Commencing optimization for 200 epochs, with 410804 positive edges #> 18:26:03 Optimization finished # By assay p1 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id-and-controlling-for-batch-using-donor_id-assay_ontology_term_id-suspension_type-","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id and controlling for batch using donor_id + assay_ontology_term_id + suspension_type.","title":"Integrating multi-dataset slices of data with Seurat","text":"cases one dataset may contain multiple assay types /multiple suspension types (cell vs nucleus), important consider metadata batches. Therefore, comprehensive definition batch Census can accomplished combining cell metadata dataset_id, donor_id, assay_ontology_term_id suspension_type, latter encode EFO ids assay types. example, two datasets used contain cells one assay , one suspension type . Thus make difference include metadata part batch. implementation look line","code":"# EXAMPLE, DON'T RUN.  # split the dataset into a list of seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently controlling for batch seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x, vars.to.regress = c(\"donor_id\", \"assay_ontology_term_id\", \"suspension_type\")) })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list)  # integrate seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\")"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the census","title":"Normalizing full-length gene sequencing data","text":"First open Census: can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"Seurat\") census <- cellxgene.census::open_soma()"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"fetching-full-length-example-sequencing-data-smart-seq","dir":"Articles","previous_headings":"","what":"Fetching full-length example sequencing data (Smart-Seq)","title":"Normalizing full-length gene sequencing data","text":"Let’s get example data, case ’ll fetch cells relatively small dataset derived Smart-Seq2 technology performs full-length gene sequencing: Collection: Tabula Muris Senis Dataset: Liver - single-cell transcriptomic atlas characterizes ageing tissues mouse - Smart-seq2 Let’s first find dataset’s id using dataset table Census. Now can use id fetch data. Let’s make sure data contains Smart-Seq2 cells. Great! can see small dataset containing 2,859 cells. Now let’s proceed normalize gene lengths.","code":"liver_dataset <- as.data.frame(   census$get(\"census_info\")$get(\"datasets\")         $read(value_filter=\"dataset_title == 'Liver - A single-cell transcriptomic atlas characterizes ageing tissues in the mouse - Smart-seq2'\")         $concat() ) liver_dataset #> # A tibble: 1 × 8 #>   soma_joinid collection_id      collection_name collection_doi dataset_id dataset_title #>         <int> <chr>              <chr>           <chr>          <chr>      <chr>         #> 1         525 0b9d8a04-bb9d-44d… Tabula Muris S… 10.1038/s4158… 4546e757-… Liver - A si… #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int> liver_dataset_id <- liver_dataset[1,\"dataset_id\"] liver_seurat <- cellxgene.census::get_seurat(   census,   organism = \"Mus musculus\",   obs_value_filter = paste0(\"dataset_id == '\", liver_dataset_id, \"'\") ) table(liver_seurat$assay) #>  #> Smart-seq2  #>       2859"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"normalizing-expression-to-account-for-gene-length","dir":"Articles","previous_headings":"","what":"Normalizing expression to account for gene length","title":"Normalizing full-length gene sequencing data","text":"default cellxgene_census::get_seurat() fetches genes Census. let’s first identify genes measured dataset subset Seurat obect include . goal can use “Dataset Presence Matrix” census$get(\"census_data\")$get(\"mus_musculus\")$ms$get(\"RNA\")$get(\"feature_dataset_presence_matrix\"). boolean matrix N x M N number datasets, M number genes Census, 1 entry indicates gene measured dataset. (Note Seurat objects transposed layout M x N.) Let’s get genes measured dataset. can see genes Census 17,992 measured dataset. Now let’s normalize genes gene length. can easily Census gene lengths included gene metadata feature_length. done! can now see real numbers instead integers.","code":"liver_seurat #> An object of class Seurat  #> 52392 features across 2859 samples within 1 assay  #> Active assay: RNA (52392 features, 0 variable features) liver_dataset_joinid <- liver_dataset$soma_joinid[1] presence_matrix <- cellxgene.census::get_presence_matrix(census, \"Mus musculus\", \"RNA\") presence_matrix <- presence_matrix$take(liver_dataset_joinid) gene_presence <- as.vector(presence_matrix$get_one_based_matrix())  liver_seurat <- liver_seurat[gene_presence, ] liver_seurat #> An object of class Seurat  #> 17992 features across 2859 samples within 1 assay  #> Active assay: RNA (17992 features, 0 variable features) GetAssayData(liver_seurat[1:5, 1:5], slot = \"data\") #> 5 x 5 sparse Matrix of class \"dgCMatrix\" #>                    cell3530079 cell3530080 cell3530081 cell3530082 cell3530083 #> ENSMUSG00000025900           .           .           .           .           . #> ENSMUSG00000025902           .           .           .           .        2250 #> ENSMUSG00000033845           .         559        1969           .           . #> ENSMUSG00000025903           .           .           .           .           . #> ENSMUSG00000033813           .           .         828           1          54 gene_lengths <- liver_seurat$RNA@meta.features$feature_length liver_seurat <- SetAssayData(   liver_seurat,    new.data = sweep(GetAssayData(liver_seurat, slot = \"data\"), 1, gene_lengths, \"/\") ) GetAssayData(liver_seurat[1:5, 1:5], slot = \"data\") #> 5 x 5 sparse Matrix of class \"dgCMatrix\" #>                    cell3530079 cell3530080 cell3530081  cell3530082 cell3530083 #> ENSMUSG00000025900           .  .            .         .             .          #> ENSMUSG00000025902           .  .            .         .             0.47150042 #> ENSMUSG00000033845           .  0.06586544   0.2320019 .             .          #> ENSMUSG00000025903           .  .            .         .             .          #> ENSMUSG00000033813           .  .            0.2744448 0.0003314551  0.01789857"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"validation-through-clustering-exploration","dir":"Articles","previous_headings":"","what":"Validation through clustering exploration","title":"Normalizing full-length gene sequencing data","text":"Let’s perform basic clustering analysis see cell types cluster expected using normalized counts. First basic filtering cells genes. normalize account sequencing depth transform data log scale. subset highly variable genes. finally scale values across gene axis. Now can proceed clustering analysis.  exceptions can see cells cell type cluster near serves sanity check gene-length normalization applied. Don’t forget close census.","code":"cells_per_gene <- rowSums(GetAssayData(liver_seurat, slot = \"counts\") > 0) genes_per_cell <- Matrix::colSums(liver_seurat$RNA@counts > 0) liver_seurat <- liver_seurat[cells_per_gene >= 5, genes_per_cell >= 500] liver_seurat <- Seurat::NormalizeData(   liver_seurat,   normalization.method = \"LogNormalize\",   scale.factor = 10000 ) liver_seurat <- Seurat::FindVariableFeatures(   liver_seurat,   selection.method = \"vst\",   nfeatures = 1000 ) all.genes <- rownames(liver_seurat) liver_seurat <- Seurat::ScaleData(liver_seurat, features = all.genes) liver_seurat <- RunPCA(   liver_seurat,   features = VariableFeatures(object = liver_seurat) ) liver_seurat <- FindNeighbors(liver_seurat, dims = 1:40) liver_seurat <- RunUMAP(liver_seurat, dims = 1:40) DimPlot(liver_seurat, reduction = \"umap\", group.by = \"cell_type\") census$close()"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Summarizing cell and gene metadata","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version). open Census, close census$close(). can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma(). can learn cellxgene.census methods accessing corresponding documentation. example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"summarizing-cell-metadata","dir":"Articles","previous_headings":"","what":"Summarizing cell metadata","title":"Summarizing cell and gene metadata","text":"Census open can use TileDB-SOMA methods SOMACollection. can thus access metadata SOMADataFrame objects encoding cell gene metadata. Tips: can read entire SOMADataFrame R using .data.frame(soma_df$read()$concat()). Queries much faster request DataFrame columns required analysis (e.g. column_names = c(\"soma_joinid\", \"cell_type_ontology_term_id\")). can also refine query results using value_filter, filter census matching records.","code":""},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"example-summarize-all-cell-types","dir":"Articles","previous_headings":"Summarizing cell metadata","what":"Example: Summarize all cell types","title":"Summarizing cell and gene metadata","text":"example reads cell metadata (obs) R data frame summarize variety ways.","code":"human <- census$get(\"census_data\")$get(\"homo_sapiens\")  # Read obs into an R data frame (tibble). obs_df <- human$obs$read(column_names = c(\"cell_type\")) obs_df <- as.data.frame(obs_df$concat())  # Find all unique values in the cell_type column. unique_cell_type <- unique(obs_df$cell_type)  cat(   \"There are\",   length(unique_cell_type),   \"cell types in the Census! The first few are: \",   paste(head(unique_cell_type), collapse = \", \") ) #> There are 613 cell types in the Census! The first few are:  syncytiotrophoblast cell, placental villous trophoblast, extravillous trophoblast, trophoblast giant cell, decidual natural killer cell, human, T cell"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"example-summarize-a-subset-of-cell-types-selected-with-a-value_filter","dir":"Articles","previous_headings":"Summarizing cell metadata","what":"Example: Summarize a subset of cell types, selected with a value_filter","title":"Summarizing cell and gene metadata","text":"example utilizes SOMA “value filter” read subset cells tissue_ontology_term_id equal UBERON:0002048 (lung tissue), summarizes query result. can also define much complex value filters. example: combine terms & | use %% operator query multiple values","code":"# Read cell_type terms for cells which have a specific tissue term LUNG_TISSUE <- \"UBERON:0002048\"  obs_df <- human$obs$read(column_names = c(\"cell_type\"), value_filter = paste0(\"tissue_ontology_term_id == '\", LUNG_TISSUE, \"'\")) obs_df <- as.data.frame(obs_df$concat())  # Find all unique values in the cell_type column as an R data frame. unique_cell_type <- unique(obs_df$cell_type) cat(   \"There are \",   length(unique_cell_type),   \" cell types in the Census where tissue_ontology_term_id == \",   LUNG_TISSUE,   \"!\\nThe first few are:\",   paste(head(unique_cell_type), collapse = \", \"),   \"\\n\" ) #> There are  185  cell types in the Census where tissue_ontology_term_id ==  UBERON:0002048 ! #> The first few are: type II pneumocyte, neutrophil, effector CD4-positive, alpha-beta T cell, effector CD8-positive, alpha-beta T cell, mature NK T cell, blood vessel endothelial cell  # Report the 10 most common top_10 <- sort(table(obs_df$cell_type), decreasing = TRUE)[1:10] cat(   \"The top 10 cell types where tissue_ontology_term_id ==\",    LUNG_TISSUE,   \"are: \",   paste(names(top_10), collapse = \", \") ) #> The top 10 cell types where tissue_ontology_term_id == UBERON:0002048 are:  native cell, alveolar macrophage, CD8-positive, alpha-beta T cell, CD4-positive, alpha-beta T cell, macrophage, type II pneumocyte, classical monocyte, natural killer cell, malignant cell, epithelial cell of lower respiratory tract # You can also do more complex queries, such as testing for inclusion in a list of values obs_df <- human$obs$read(   column_names = c(\"cell_type_ontology_term_id\"),   value_filter = \"tissue_ontology_term_id %in% c('UBERON:0002082', 'UBERON:OOO2084', 'UBERON:0002080')\" )  obs_df <- as.data.frame(obs_df$concat())  # Summarize top_10 <- sort(table(obs_df$cell_type_ontology_term_id), decreasing = TRUE)[1:10] print(top_10) #>  #> CL:0000746 CL:0008034 CL:0002548 CL:0000115 CL:0002131 CL:0000763 CL:0000669 CL:0000003  #>     159096      84750      79618      64190      61830      32088      27515      22707  #> CL:0000057 CL:0002144  #>      20117      18593"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"full-census-metadata-stats","dir":"Articles","previous_headings":"","what":"Full Census metadata stats","title":"Summarizing cell and gene metadata","text":"example queries organisms Census, summarizes diversity various metadata labels.","code":"cols_to_query <- c(   \"cell_type_ontology_term_id\",   \"assay_ontology_term_id\",   \"tissue_ontology_term_id\" )  total_cells <- 0 for (organism in census$get(\"census_data\")$names()) {   print(organism)      obs_df <- census$get(\"census_data\")$get(organism)$obs$read(column_names = cols_to_query)   obs_df <- as.data.frame(obs_df$concat())      total_cells <- total_cells + nrow(obs_df)   for (col in cols_to_query) {     cat(\"  Unique \", col, \" values: \", length(unique(obs_df[[col]])), \"\\n\")   } } #> [1] \"mus_musculus\" #>   Unique  cell_type_ontology_term_id  values:  248  #>   Unique  assay_ontology_term_id  values:  9  #>   Unique  tissue_ontology_term_id  values:  66  #> [1] \"homo_sapiens\" #>   Unique  cell_type_ontology_term_id  values:  613  #>   Unique  assay_ontology_term_id  values:  19  #>   Unique  tissue_ontology_term_id  values:  220 cat(\"Complete Census contains \", total_cells, \" cells.\") #> Complete Census contains  61656118  cells."},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"close-the-census","dir":"Articles","previous_headings":"Full Census metadata stats","what":"Close the census","title":"Summarizing cell and gene metadata","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Chan Zuckerberg Initiative. Author, maintainer, copyright holder, funder.","code":""},{"path":"/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Chan Zuckerberg Initiative (2023). cellxgene.census: CZ CELLxGENE Discover Cell Census. R package version 1.5.2, https://github.com/chanzuckerberg/cellxgene-census.","code":"@Manual{,   title = {cellxgene.census: CZ CELLxGENE Discover Cell Census},   author = {{Chan Zuckerberg Initiative}},   year = {2023},   note = {R package version 1.5.2},   url = {https://github.com/chanzuckerberg/cellxgene-census}, }"},{"path":"/index.html","id":"r-package-of-cz-cellxgene-discover-census","dir":"","previous_headings":"","what":"CZ CELLxGENE Discover Cell Census","title":"CZ CELLxGENE Discover Cell Census","text":"documentation R package cellxgene.census part CZ CELLxGENE Discover Census. full details Census data capabilities please go main Census site. cellxgene.census provides API efficiently access cloud-hosted Census single-cell data R. just seconds users can access slice Census data using cell gene filters across hundreds single-cell datasets. Census data can fetched iterative fashion bigger--memory slices data, quickly exported basic R structures, well Seurat SingleCellExperiment objects downstream analysis.","code":""},{"path":"/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"CZ CELLxGENE Discover Cell Census","text":"installing Ubuntu, may need install following libraries via apt install, libxml2-dev libssl-dev libcurl4-openssl-dev. addition must cmake v3.21 greater. installing MacOS, need install developer tools Xcode. Windows supported. R session install cellxgene.census R-Universe. able export Census data Seurat SingleCellExperiment also need install respective packages.","code":"install.packages(   \"cellxgene.census\",   repos=c('https://chanzuckerberg.r-universe.dev', 'https://cloud.r-project.org') ) # Seurat install.packages(\"Seurat\")  # SingleCellExperiment if (!require(\"BiocManager\", quietly = TRUE))     install.packages(\"BiocManager\")  BiocManager::install(\"SingleCellExperiment\")"},{"path":"/index.html","id":"usage","dir":"","previous_headings":"","what":"Usage","title":"CZ CELLxGENE Discover Cell Census","text":"Check vignettes “Articles” section navigation bar site. highly recommend following vignettes starting point: Querying fetching single-cell data cell/gene metadata Learning CZ CELLxGENE Discover Census can also check quick start guide main Census site.","code":""},{"path":"/index.html","id":"example-seurat-and-singlecellexperiment-query","dir":"","previous_headings":"Usage","what":"Example Seurat and SingleCellExperiment query","title":"CZ CELLxGENE Discover Cell Census","text":"following creates Seurat object -demand sympathetic neurons Census filtering genes ENSG00000161798, ENSG00000188229. following retrieves data SingleCellExperiment object.","code":"library(\"cellxgene.census\") library(\"Seurat\")  census <- open_soma()  organism <- \"Homo sapiens\" gene_filter <- \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" cell_filter <-  \"cell_type == 'sympathetic neuron'\" cell_columns <- c(\"assay\", \"cell_type\", \"tissue\", \"tissue_general\", \"suspension_type\", \"disease\")  seurat_obj <- get_seurat(    census = census,    organism = organism,    var_value_filter = gene_filter,    obs_value_filter = cell_filter,    obs_column_names = cell_columns ) library(\"SingleCellExperiment\")  sce_obj <- get_single_cell_experiment(    census = census,    organism = organism,    var_value_filter = gene_filter,    obs_value_filter = cell_filter,    obs_column_names = cell_columns )"},{"path":"/index.html","id":"for-more-help","dir":"","previous_headings":"","what":"For More Help","title":"CZ CELLxGENE Discover Cell Census","text":"help, please go visit main Census site. believe found security issue, appreciate notification. Please send email security@chanzuckerberg.com.","code":""},{"path":"/reference/download_source_h5ad.html","id":null,"dir":"Reference","previous_headings":"","what":"Download source H5AD to local file name. — download_source_h5ad","title":"Download source H5AD to local file name. — download_source_h5ad","text":"Download source H5AD local file name.","code":""},{"path":"/reference/download_source_h5ad.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Download source H5AD to local file name. — download_source_h5ad","text":"","code":"download_source_h5ad(   dataset_id,   file,   overwrite = FALSE,   census_version = \"stable\",   census = NULL )"},{"path":"/reference/download_source_h5ad.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Download source H5AD to local file name. — download_source_h5ad","text":"dataset_id dataset_id interest. file Local file name store H5AD file. overwrite TRUE allow overwriting existing file. census_version desired Census version. census open Census handle census_version. provided, opened closed automatically; efficient reuse handle calling download_source_h5ad() multiple times.","code":""},{"path":"/reference/download_source_h5ad.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Download source H5AD to local file name. — download_source_h5ad","text":"","code":"download_source_h5ad(\"0895c838-e550-48a3-a777-dbcd35d30272\", \"/tmp/data.h5ad\", overwrite = TRUE)"},{"path":"/reference/get_census_version_description.html","id":null,"dir":"Reference","previous_headings":"","what":"Get release description for a Census version — get_census_version_description","title":"Get release description for a Census version — get_census_version_description","text":"Get release description Census version","code":""},{"path":"/reference/get_census_version_description.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get release description for a Census version — get_census_version_description","text":"","code":"get_census_version_description(census_version)"},{"path":"/reference/get_census_version_description.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Get release description for a Census version — get_census_version_description","text":"census_version census version name.","code":""},{"path":"/reference/get_census_version_description.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get release description for a Census version — get_census_version_description","text":"List release location metadata","code":""},{"path":"/reference/get_census_version_description.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get release description for a Census version — get_census_version_description","text":"","code":"as.data.frame(get_census_version_description(\"stable\")) #>   release_date release_build #> 1                 2023-07-25 #>                                                  soma.uri #> 1 s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #>               soma.relative_uri soma.s3_region #> 1 /cell-census/2023-07-25/soma/      us-west-2 #>                                                  h5ads.uri #> 1 s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #>               h5ads.relative_uri h5ads.s3_region do_not_delete  alias #> 1 /cell-census/2023-07-25/h5ads/       us-west-2          TRUE stable #>   census_version #> 1         stable"},{"path":"/reference/get_census_version_directory.html","id":null,"dir":"Reference","previous_headings":"","what":"Get the directory of Census releases currently available — get_census_version_directory","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"Get directory Census releases currently available","code":""},{"path":"/reference/get_census_version_directory.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"","code":"get_census_version_directory()"},{"path":"/reference/get_census_version_directory.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"Data frame available cell census releases, including location metadata.","code":""},{"path":"/reference/get_census_version_directory.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"","code":"get_census_version_directory() #>            release_date release_build #> stable                     2023-07-25 #> latest                     2023-08-25 #> 2023-05-15                 2023-05-15 #> 2023-07-17                 2023-07-17 #> 2023-07-24                 2023-07-24 #> 2023-07-25                 2023-07-25 #> 2023-08-01                 2023-08-01 #> 2023-08-08                 2023-08-08 #> 2023-08-14                 2023-08-14 #> 2023-08-22                 2023-08-22 #> 2023-08-25                 2023-08-25 #>                                                           soma.uri #> stable     s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #> latest     s3://cellxgene-data-public/cell-census/2023-08-25/soma/ #> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/soma/ #> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/soma/ #> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/soma/ #> 2023-07-25 s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #> 2023-08-01 s3://cellxgene-data-public/cell-census/2023-08-01/soma/ #> 2023-08-08 s3://cellxgene-data-public/cell-census/2023-08-08/soma/ #> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/soma/ #> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/soma/ #> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/soma/ #>                        soma.relative_uri soma.s3_region #> stable     /cell-census/2023-07-25/soma/      us-west-2 #> latest     /cell-census/2023-08-25/soma/      us-west-2 #> 2023-05-15 /cell-census/2023-05-15/soma/      us-west-2 #> 2023-07-17 /cell-census/2023-07-17/soma/      us-west-2 #> 2023-07-24 /cell-census/2023-07-24/soma/      us-west-2 #> 2023-07-25 /cell-census/2023-07-25/soma/      us-west-2 #> 2023-08-01 /cell-census/2023-08-01/soma/      us-west-2 #> 2023-08-08 /cell-census/2023-08-08/soma/      us-west-2 #> 2023-08-14 /cell-census/2023-08-14/soma/      us-west-2 #> 2023-08-22 /cell-census/2023-08-22/soma/      us-west-2 #> 2023-08-25 /cell-census/2023-08-25/soma/      us-west-2 #>                                                           h5ads.uri #> stable     s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #> latest     s3://cellxgene-data-public/cell-census/2023-08-25/h5ads/ #> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/h5ads/ #> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/h5ads/ #> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/h5ads/ #> 2023-07-25 s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #> 2023-08-01 s3://cellxgene-data-public/cell-census/2023-08-01/h5ads/ #> 2023-08-08 s3://cellxgene-data-public/cell-census/2023-08-08/h5ads/ #> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/h5ads/ #> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/h5ads/ #> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/h5ads/ #>                        h5ads.relative_uri h5ads.s3_region do_not_delete  alias #> stable     /cell-census/2023-07-25/h5ads/       us-west-2          TRUE stable #> latest     /cell-census/2023-08-25/h5ads/       us-west-2         FALSE latest #> 2023-05-15 /cell-census/2023-05-15/h5ads/       us-west-2          TRUE        #> 2023-07-17 /cell-census/2023-07-17/h5ads/       us-west-2            NA        #> 2023-07-24 /cell-census/2023-07-24/h5ads/       us-west-2            NA        #> 2023-07-25 /cell-census/2023-07-25/h5ads/       us-west-2          TRUE        #> 2023-08-01 /cell-census/2023-08-01/h5ads/       us-west-2         FALSE        #> 2023-08-08 /cell-census/2023-08-08/h5ads/       us-west-2         FALSE        #> 2023-08-14 /cell-census/2023-08-14/h5ads/       us-west-2         FALSE        #> 2023-08-22 /cell-census/2023-08-22/h5ads/       us-west-2         FALSE        #> 2023-08-25 /cell-census/2023-08-25/h5ads/       us-west-2         FALSE"},{"path":"/reference/get_presence_matrix.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the feature dataset presence matrix. — get_presence_matrix","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"Read feature dataset presence matrix.","code":""},{"path":"/reference/get_presence_matrix.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"","code":"get_presence_matrix(census, organism, measurement_name = \"RNA\")"},{"path":"/reference/get_presence_matrix.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"census census object cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA.","code":""},{"path":"/reference/get_presence_matrix.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"tiledbsoma::matrixZeroBasedView object dataset join id & feature join id dimensions, filled 1s indicating presence. sparse matrix accessed zero-based indexes since join id's may zero.","code":""},{"path":"/reference/get_presence_matrix.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"","code":"census <- open_soma() #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. on.exit(census$close(), add = TRUE) print(get_presence_matrix(census, \"Homo sapiens\")$dim()) #> Error in private$check_open_for_read_or_write(): Item must be open for read or write. s3://cellxgene-data-public/cell-census/2023-07-25/soma/"},{"path":"/reference/get_seurat.html","id":null,"dir":"Reference","previous_headings":"","what":"Export Census slices to Seurat — get_seurat","title":"Export Census slices to Seurat — get_seurat","text":"Convenience wrapper around SOMAExperimentAxisQuery, build execute query, return Seurat object.","code":""},{"path":"/reference/get_seurat.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Export Census slices to Seurat — get_seurat","text":"","code":"get_seurat(   census,   organism,   measurement_name = \"RNA\",   X_layers = c(counts = \"raw\", data = NULL),   obs_value_filter = NULL,   obs_coords = NULL,   obs_column_names = NULL,   var_value_filter = NULL,   var_coords = NULL,   var_column_names = NULL,   var_index = \"feature_id\" )"},{"path":"/reference/get_seurat.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Export Census slices to Seurat — get_seurat","text":"census census object, usually returned cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA. X_layers named character X layers add Seurat assay, names names Seurat slots (counts data) values names layers within X. obs_value_filter SOMA value_filter across columns obs dataframe, expressed string. obs_coords set coordinates obs dataframe index, expressed type format supported SOMADataFrame's read() method. obs_column_names Columns fetch obs data frame. var_value_filter obs_value_filter var. var_coords obs_coords var. var_column_names Columns fetch var data frame. var_index Name column ‘var’ add feature names.","code":""},{"path":"/reference/get_seurat.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Export Census slices to Seurat — get_seurat","text":"Seurat object containing sensus slice.","code":""},{"path":"/reference/get_seurat.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Export Census slices to Seurat — get_seurat","text":"","code":"if (FALSE) { census <- open_soma() seurat_obj <- get_seurat(   census,   organism = \"Homo sapiens\",   obs_value_filter = \"cell_type == 'leptomeningeal cell'\",   var_value_filter = \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" )  seurat_obj  census$close() }"},{"path":"/reference/get_single_cell_experiment.html","id":null,"dir":"Reference","previous_headings":"","what":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"Convenience wrapper around SOMAExperimentAxisQuery, build execute query, return SingleCellExperiment object.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"","code":"get_single_cell_experiment(   census,   organism,   measurement_name = \"RNA\",   X_layers = c(counts = \"raw\"),   obs_value_filter = NULL,   obs_coords = NULL,   obs_column_names = NULL,   var_value_filter = NULL,   var_coords = NULL,   var_column_names = NULL,   var_index = \"feature_id\" )"},{"path":"/reference/get_single_cell_experiment.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"census census object, usually returned cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA. X_layers character vector X layers add assays main experiment; may optionally named set name resulting assay (eg. ‘X_layers = c(counts = \"raw\")’ load X layer “‘raw’” assay “‘counts’”); default, loads X layers obs_value_filter SOMA value_filter across columns obs dataframe, expressed string. obs_coords set coordinates obs dataframe index, expressed type format supported SOMADataFrame's read() method. obs_column_names Columns fetch obs data frame. var_value_filter obs_value_filter var. var_coords obs_coords var. var_column_names Columns fetch var data frame. var_index Name column ‘var’ add feature names.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"SingleCellExperiment object containing sensus slice.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"","code":"if (FALSE) { census <- open_soma() sce_obj <- get_single_cell_experiment(   census,   organism = \"Homo sapiens\",   obs_value_filter = \"cell_type == 'leptomeningeal cell'\",   var_value_filter = \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" )  sce_obj  census$close() }"},{"path":"/reference/get_source_h5ad_uri.html","id":null,"dir":"Reference","previous_headings":"","what":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"Locate source h5ad file dataset.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"","code":"get_source_h5ad_uri(dataset_id, census_version = \"stable\", census = NULL)"},{"path":"/reference/get_source_h5ad_uri.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"dataset_id dataset_id interest. census_version desired Census version. census open Census handle census_version. provided, opened closed automatically; efficient reuse handle calling get_source_h5ad_uri() multiple times.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"list uri optional s3_region.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"","code":"get_source_h5ad_uri(\"0895c838-e550-48a3-a777-dbcd35d30272\") #> $uri #> [1] \"s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/0895c838-e550-48a3-a777-dbcd35d30272.h5ad\" #>  #> $s3_region #> [1] \"us-west-2\" #>"},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":null,"dir":"Reference","previous_headings":"","what":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"Create SOMATileDBContext suitable using open_soma(). Typically open_soma() creates context automatically, one can created separately order set custom configuration options, share multiple open Census handles.","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"","code":"new_SOMATileDBContext_for_census(census_version_description, ...)"},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"census_version_description result get_census_version_description() desired Census version. ... Custom configuration options.","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"SOMATileDBContext object open_soma().","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"","code":"census_desc <- get_census_version_description(\"stable\") ctx <- new_SOMATileDBContext_for_census(census_desc, \"soma.init_buffer_bytes\" = paste(4 * 1024**3)) census <- open_soma(\"stable\", tiledbsoma_ctx = ctx) #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. census$close()"},{"path":"/reference/open_soma.html","id":null,"dir":"Reference","previous_headings":"","what":"Open the Census — open_soma","title":"Open the Census — open_soma","text":"Open Census","code":""},{"path":"/reference/open_soma.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Open the Census — open_soma","text":"","code":"open_soma(census_version = \"stable\", uri = NULL, tiledbsoma_ctx = NULL)"},{"path":"/reference/open_soma.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Open the Census — open_soma","text":"census_version version Census, e.g., \"stable\". uri URI containing Census SOMA objects open instead released version. (supplied, takes precedence census_version.) tiledbsoma_ctx tiledbsoma::SOMATileDBContext built using new_SOMATileDBContext_for_census(). Optional (created automatically) using census_version context need reused.","code":""},{"path":"/reference/open_soma.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Open the Census — open_soma","text":"Top-level tiledbsoma::SOMACollection object. use, census closed release memory resources, usually .exit(census$close(), add = TRUE). Closing top-level census also close SOMA objects accessed .","code":""},{"path":"/reference/open_soma.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Open the Census — open_soma","text":"","code":"census <- open_soma() #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. as.data.frame(census$get(\"census_info\")$get(\"summary\")$read()$concat()) #> # A tibble: 7 × 3 #>   soma_joinid label                      value      #>         <int> <chr>                      <chr>      #> 1           0 census_schema_version      1.0.0      #> 2           1 census_build_date          2023-07-25 #> 3           2 dataset_schema_version     3.0.0      #> 4           3 total_cell_count           61656118   #> 5           4 unique_cell_count          37447773   #> 6           5 number_donors_homo_sapiens 13035      #> 7           6 number_donors_mus_musculus 1417       census$close()"}]
+[{"path":"/LICENSE.html","id":null,"dir":"","previous_headings":"","what":"MIT License","title":"MIT License","text":"Copyright (c) 2023 Chan Zuckerberg Initiative Permission hereby granted, free charge, person obtaining copy software associated documentation files (“Software”), deal Software without restriction, including without limitation rights use, copy, modify, merge, publish, distribute, sublicense, /sell copies Software, permit persons Software furnished , subject following conditions: copyright notice permission notice shall included copies substantial portions Software. SOFTWARE PROVIDED “”, WITHOUT WARRANTY KIND, EXPRESS IMPLIED, INCLUDING LIMITED WARRANTIES MERCHANTABILITY, FITNESS PARTICULAR PURPOSE NONINFRINGEMENT. EVENT SHALL AUTHORS COPYRIGHT HOLDERS LIABLE CLAIM, DAMAGES LIABILITY, WHETHER ACTION CONTRACT, TORT OTHERWISE, ARISING , CONNECTION SOFTWARE USE DEALINGS SOFTWARE.","code":""},{"path":"/articles/census_compute_over_X.html","id":"incremental-mean-calculation","dir":"Articles","previous_headings":"","what":"Incremental mean calculation","title":"Computing on X using online (incremental) algorithms","text":"Many statistics, marginal means, easy calculate incrementally. Let’s begin query X$raw sparse matrix unnormalized read counts, return results shards incrementally accumulate read count gene, divide cell count get mean reads per cell gene. First define query - case slice obs axis cells specific tissue & sex value, genes var axis. query$X() method returns iterator results, Arrow Table. table contain sparse X data obs/var coordinates, using standard SOMA names: soma_data - X values (float32) soma_dim_0 - obs coordinate (int64) soma_dim_1 - var coordinate (int64) Important: X matrices joined var/obs axis DataFrames integer join “id” (aka soma_joinid). positionally indexed, given cell gene may soma_joinid value (e.g., large integer). words, given X value, soma_dim_0 corresponds soma_joinid obs dataframe, soma_dim_1 coordinate corresponds soma_joinid var dataframe. convenience, query class includes utility simplify operations query slices. query$indexer indexer used wrap output query$X(), converting soma_joinids positional indexing query results. Positions [0, N), N number results query given axis. Key points: expensive query read results - rather make multiple passes data, read perform multiple computations. default, data census indexed soma_joinid positionally.","code":"library(\"tiledbsoma\") library(\"cellxgene.census\") census <- open_soma()  query <- census$get(\"census_data\")$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = SOMAAxisQuery$new(value_filter = \"tissue=='brain' && sex=='male'\") )  genes_df <- query$var(column_names = c(\"feature_id\", \"feature_name\"))$concat() genes_df <- as.data.frame(genes_df) n_genes <- nrow(genes_df)  # accumulator vector (for each gene) for the total count over all cells in X(\"raw\") raw_sum_by_gene <- numeric(n_genes) names(raw_sum_by_gene) <- genes_df$feature_id  # iterate through in-memory shards of query results tables <- query$X(\"raw\")$tables() while (!tables$read_complete()) {   table_part <- tables$read_next()   # table_part is an Arrow table with the columns mentioned above. The result   # order is not guaranteed!    # table_part$soma_dim_1 is the var/gene soma_joinid. But note that these are   # arbitrary int64 id's, and moreover each table_part may exhibit only a subset   # of the values we'll see over all query results. query$indexer helps us map   # any given soma_dim_1 values onto positions in query$var() (genes_df), that is   # the union of all values we'll see.   gene_indexes <- query$indexer$by_var(table_part$soma_dim_1)$as_vector()   stopifnot(sum(gene_indexes >= n_genes) == 0)   # sum(table_part) group by gene, yielding a numeric vector with the gene_index   # in its names   sum_part <- tapply(as.vector(table_part$soma_data), gene_indexes, sum)   # update the accumulator vector   which_genes <- as.integer(names(sum_part)) + 1  # nb: gene_indexes is zero-based   stopifnot(sum(which_genes > n_genes) == 0)   raw_sum_by_gene[which_genes] <- raw_sum_by_gene[which_genes] + sum_part }  # Divide each sum by cell count to get mean reads per cell (for each gene), # implicitly averaging in all zero entries in X even though they weren't included # in the sparse query results. genes_df$raw_mean <- raw_sum_by_gene / query$n_obs genes_df #> # A tibble: 52,392 × 3 #>    feature_id         feature_name   raw_mean #>    <chr>              <chr>             <dbl> #>  1 ENSMUSG00000051951 Xkr4          1.28      #>  2 ENSMUSG00000089699 Gm1992        0         #>  3 ENSMUSG00000102343 Gm37381       0         #>  4 ENSMUSG00000025900 Rp1           0.291     #>  5 ENSMUSG00000025902 Sox17        60.7       #>  6 ENSMUSG00000104328 Gm37323       0.0000570 #>  7 ENSMUSG00000033845 Mrpl15       36.2       #>  8 ENSMUSG00000025903 Lypla1       18.3       #>  9 ENSMUSG00000104217 Gm37988       0         #> 10 ENSMUSG00000033813 Tcea1        39.6       #> # ℹ 52,382 more rows"},{"path":"/articles/census_compute_over_X.html","id":"counting-cells-grouped-by-dataset-and-gene","dir":"Articles","previous_headings":"","what":"Counting cells grouped by dataset and gene","title":"Computing on X using online (incremental) algorithms","text":"goal example count number cells nonzero reads, grouped gene Census dataset_id. result data frame dataset, gene, number cells nonzero reads dataset gene. multi-factor aggregation, ’ll take advantage dplyr routines instead lower-level vector indexer shown . presentation purposes, ’ll limit query four genes, can expanded genes easily. Don’t forget close census.","code":"library(\"dplyr\")  query <- census$get(\"census_data\")$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = SOMAAxisQuery$new(value_filter = \"tissue=='brain'\"),   var_query = SOMAAxisQuery$new(value_filter = \"feature_name %in% c('Malat1', 'Ptprd', 'Dlg2', 'Pcdh9')\") )  obs_tbl <- query$obs(column_names=c(\"soma_joinid\", \"dataset_id\"))$concat() obs_df <- data.frame(   # materialize soma_joinid as character to avoid overflowing R 32-bit integer   cell_id = as.character(obs_tbl$soma_joinid),   dataset_id = obs_tbl$dataset_id$as_vector() ) var_tbl <- query$var(column_names=c(\"soma_joinid\", \"feature_name\"))$concat() var_df <- data.frame(   gene_id = as.character(var_tbl$soma_joinid),   feature_name = var_tbl$feature_name$as_vector() )  # accumulator for # cells by dataset & gene n_cells_grouped <- data.frame(   \"dataset_id\" = character(0),   \"gene_id\" = character(0),   \"n_cells\" = numeric(0) )  # iterate through in-memory shards of query results tables <- query$X(\"raw\")$tables() while (!tables$read_complete()) {   table_part <- tables$read_next()    # prepare a (dataset,gene,1) tuple for each entry in table_part   n_cells_part <- data.frame(     \"cell_id\" = as.character(table_part$soma_dim_0),     \"gene_id\" = as.character(table_part$soma_dim_1),     \"n_cells\" = 1   )   n_cells_part <- left_join(n_cells_part, obs_df, by = \"cell_id\")   stopifnot(sum(is.null(n_cells_part$dataset_id)) == 0)    # fold those into n_cells_grouped   n_cells_grouped <- n_cells_part %>%                      select(-cell_id) %>%                      bind_rows(n_cells_grouped) %>%                       group_by(dataset_id, gene_id) %>%                       summarise(n_cells = sum(n_cells)) %>%                       ungroup() }  # add gene names for display n_cells_grouped <- left_join(n_cells_grouped, var_df, by = \"gene_id\") stopifnot(sum(is.null(n_cells_grouped$feature_name)) == 0) n_cells_grouped[c(\"dataset_id\", \"feature_name\", \"n_cells\")] #> # A tibble: 17 × 3 #>    dataset_id                           feature_name n_cells #>    <chr>                                <chr>          <dbl> #>  1 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Dlg2           79513 #>  2 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Pcdh9          79476 #>  3 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Malat1         79667 #>  4 3bbb6cf9-72b9-41be-b568-656de6eb18b5 Ptprd          79578 #>  5 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Dlg2              81 #>  6 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Pcdh9            125 #>  7 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Malat1         12622 #>  8 58b01044-c5e5-4b0f-8a2d-6ebf951e01ff Ptprd            474 #>  9 66ff82b4-9380-469c-bc4b-cfa08eacd325 Dlg2             856 #> 10 66ff82b4-9380-469c-bc4b-cfa08eacd325 Pcdh9           2910 #> 11 66ff82b4-9380-469c-bc4b-cfa08eacd325 Malat1          7102 #> 12 98e5ea9f-16d6-47ec-a529-686e76515e39 Dlg2             908 #> 13 98e5ea9f-16d6-47ec-a529-686e76515e39 Pcdh9           3027 #> 14 98e5ea9f-16d6-47ec-a529-686e76515e39 Malat1         20094 #> 15 c08f8441-4a10-4748-872a-e70c0bcccdba Dlg2              52 #> 16 c08f8441-4a10-4748-872a-e70c0bcccdba Pcdh9            117 #> 17 c08f8441-4a10-4748-872a-e70c0bcccdba Malat1         12992 census$close()"},{"path":"/articles/census_dataset_presence.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Genes measured in each cell (dataset presence matrix)","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version).","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/census_dataset_presence.html","id":"fetching-the-ids-of-the-census-datasets","dir":"Articles","previous_headings":"","what":"Fetching the IDs of the Census datasets","title":"Genes measured in each cell (dataset presence matrix)","text":"Let’s grab table datasets included Census use table combination presence matrix .","code":"# Grab the experiment containing human data, and the measurement therein with RNA human <- census$get(\"census_data\")$get(\"homo_sapiens\") human_rna <- human$ms$get(\"RNA\")  # The census-wide datasets datasets_df <- as.data.frame(census$get(\"census_info\")$get(\"datasets\")$read()$concat()) print(datasets_df) #> # A tibble: 593 × 8 #>    soma_joinid collection_id     collection_name collection_doi dataset_id dataset_title #>          <int> <chr>             <chr>           <chr>          <chr>      <chr>         #>  1           0 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… f171db61-… donor_p13_tr… #>  2           1 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… ecf2e08e-… All donors t… #>  3           2 e2c257e7-6f79-48… Spatial multio… 10.1038/s4158… 74cff64f-… All donors a… #>  4           3 f7cecffa-00b4-45… Mapping single… 10.1016/j.cce… 5af90777-… Single-cell … #>  5           4 3f50314f-bdc9-40… Single-cell se… 10.1016/j.cce… bd65a70f-… Single-cell … #>  6           5 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… ff45e623-… Tabula Sapie… #>  7           6 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… f01bdd17-… Tabula Sapie… #>  8           7 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e6a11140-… Tabula Sapie… #>  9           8 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e5c63d94-… Tabula Sapie… #> 10           9 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… d8732da6-… Tabula Sapie… #> # ℹ 583 more rows #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int>"},{"path":"/articles/census_dataset_presence.html","id":"fetching-the-dataset-presence-matrix","dir":"Articles","previous_headings":"","what":"Fetching the dataset presence matrix","title":"Genes measured in each cell (dataset presence matrix)","text":"Now let’s fetch dataset presence matrix. convenience, read entire presence matrix (Homo sapiens) sparse matrix. convenience function providing capability: also need var dataframe, read R data frame convenient manipulation:","code":"presence_matrix <- get_presence_matrix(census, \"Homo sapiens\", \"RNA\") print(dim(presence_matrix)) #> NULL var_df <- as.data.frame(human_rna$var$read()$concat()) print(var_df) #> # A tibble: 60,664 × 4 #>    soma_joinid feature_id      feature_name feature_length #>          <int> <chr>           <chr>                 <int> #>  1           0 ENSG00000121410 A1BG                   3999 #>  2           1 ENSG00000268895 A1BG-AS1               3374 #>  3           2 ENSG00000148584 A1CF                   9603 #>  4           3 ENSG00000175899 A2M                    6318 #>  5           4 ENSG00000245105 A2M-AS1                2948 #>  6           5 ENSG00000166535 A2ML1                  7156 #>  7           6 ENSG00000256661 A2ML1-AS1               452 #>  8           7 ENSG00000184389 A3GALT2                1023 #>  9           8 ENSG00000128274 A4GALT                 3358 #> 10           9 ENSG00000118017 A4GNT                  1779 #> # ℹ 60,654 more rows"},{"path":"/articles/census_dataset_presence.html","id":"identifying-genes-measured-in-a-specific-dataset","dir":"Articles","previous_headings":"","what":"Identifying genes measured in a specific dataset","title":"Genes measured in each cell (dataset presence matrix)","text":"Now dataset table, genes metadata table, dataset presence matrix, can check gene set genes measured specific dataset. Important: presence matrix indexed soma_joinid, positionally indexed. words: first dimension presence matrix dataset’s soma_joinid, stored census_datasets dataframe. second dimension presence matrix feature’s soma_joinid, stored var dataframe. presence matrix method $take() lets slice soma_joinids census_datasets var. full presence matrix, slices , can exported regular matrix method $get_one_based_matrix() Let’s find gene \"ENSG00000286096\" measured dataset id \"97a17473-e2b1-4f31-a544-44a60773e2dd\".","code":"# Get soma_joinid for datasets and genes of interest var_joinid <- var_df$soma_joinid[var_df$feature_id == \"ENSG00000286096\"] dataset_joinid <- datasets_df$soma_joinid[datasets_df$dataset_id == \"97a17473-e2b1-4f31-a544-44a60773e2dd\"]  # Slice presence matrix with datasets and genes of interest presence_matrix_slice <- presence_matrix$take(i = dataset_joinid, j = var_joinid)  # Convert presence matrix to regular matrix presence_matrix_slice <- presence_matrix_slice$get_one_based_matrix()  # Find how if the gene is present in this dataset is_present <- presence_matrix_slice[, , drop = TRUE] cat(paste(\"Feature is\", if (is_present) \"present.\" else \"not present.\")) #> Feature is present."},{"path":"/articles/census_dataset_presence.html","id":"identifying-datasets-that-measured-specific-genes","dir":"Articles","previous_headings":"","what":"Identifying datasets that measured specific genes","title":"Genes measured in each cell (dataset presence matrix)","text":"Similarly, can determine datasets measured specific gene set genes.","code":"# Grab the feature's soma_joinid from the var dataframe var_joinid <- var_df$soma_joinid[var_df$feature_id == \"ENSG00000286096\"]  # The presence matrix is indexed by the joinids of the dataset and var dataframes, # so slice out the feature of interest by its joinid. presence_matrix_slice  <- presence_matrix$take(j = var_joinid)$get_one_based_matrix() measured_datasets <- presence_matrix_slice[, , drop = TRUE] != 0 dataset_joinids <- datasets_df$soma_joinid[measured_datasets]  # From the datasets dataframe, slice out the datasets which have a joinid in the list print(datasets_df[dataset_joinids, ]) #> # A tibble: 42 × 8 #>    soma_joinid collection_id     collection_name collection_doi dataset_id dataset_title #>          <int> <chr>             <chr>           <chr>          <chr>      <chr>         #>  1           4 3f50314f-bdc9-40… Single-cell se… 10.1016/j.cce… bd65a70f-… Single-cell … #>  2           5 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… ff45e623-… Tabula Sapie… #>  3           6 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… f01bdd17-… Tabula Sapie… #>  4           7 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e6a11140-… Tabula Sapie… #>  5           8 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… e5c63d94-… Tabula Sapie… #>  6          10 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… d77ec7d6-… Tabula Sapie… #>  7          11 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… cee11228-… Tabula Sapie… #>  8          13 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… a2d4d33e-… Tabula Sapie… #>  9          14 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… a0754256-… Tabula Sapie… #> 10          18 e5f58829-1a66-40… Tabula Sapiens  10.1126/scien… 6d41668c-… Tabula Sapie… #> # ℹ 32 more rows #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int>"},{"path":"/articles/census_dataset_presence.html","id":"identifying-all-genes-measured-in-a-dataset","dir":"Articles","previous_headings":"","what":"Identifying all genes measured in a dataset","title":"Genes measured in each cell (dataset presence matrix)","text":"Finally, can find set genes measured cells given dataset.","code":"# Slice the dataset(s) of interest, and get the joinid(s) dataset_joinids <- datasets_df$soma_joinid[datasets_df$collection_id == \"17481d16-ee44-49e5-bcf0-28c0780d8c4a\"]  # Slice the presence matrix by the first dimension, i.e., by dataset presence_matrix_slice <- presence_matrix$take(i = dataset_joinids)$get_one_based_matrix() genes_measured <- Matrix::colSums(presence_matrix_slice) > 0 var_joinids <- var_df$soma_joinid[genes_measured]  print(var_df[var_joinids, ]) #> # A tibble: 27,210 × 4 #>    soma_joinid feature_id      feature_name feature_length #>          <int> <chr>           <chr>                 <int> #>  1           0 ENSG00000121410 A1BG                   3999 #>  2           1 ENSG00000268895 A1BG-AS1               3374 #>  3           2 ENSG00000148584 A1CF                   9603 #>  4           3 ENSG00000175899 A2M                    6318 #>  5           4 ENSG00000245105 A2M-AS1                2948 #>  6           5 ENSG00000166535 A2ML1                  7156 #>  7           7 ENSG00000184389 A3GALT2                1023 #>  8           8 ENSG00000128274 A4GALT                 3358 #>  9           9 ENSG00000118017 A4GNT                  1779 #> 10          10 ENSG00000094914 AAAS                   4727 #> # ℹ 27,200 more rows"},{"path":"/articles/census_dataset_presence.html","id":"close-the-census","dir":"Articles","previous_headings":"Identifying all genes measured in a dataset","what":"Close the census","title":"Genes measured in each cell (dataset presence matrix)","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/census_datasets.html","id":"fetching-the-datasets-table","dir":"Articles","previous_headings":"","what":"Fetching the datasets table","title":"Census Datasets example","text":"Census contains top-level data frame itemizing datasets contained therein. can read SOMADataFrame Arrow Table: R data frame: sum cell counts across datasets match number cells across SOMA experiments (human, mouse).","code":"library(\"cellxgene.census\") census <- open_soma() census_datasets <- census$get(\"census_info\")$get(\"datasets\")$read()$concat() print(census_datasets) #> Table #> 593 rows x 8 columns #> $soma_joinid <int64 not null> #> $collection_id <large_string not null> #> $collection_name <large_string not null> #> $collection_doi <large_string not null> #> $dataset_id <large_string not null> #> $dataset_title <large_string not null> #> $dataset_h5ad_path <large_string not null> #> $dataset_total_cell_count <int64 not null> census_datasets <- as.data.frame(census_datasets) print(census_datasets[, c(   \"dataset_id\",   \"dataset_title\",   \"dataset_total_cell_count\" )]) #> # A tibble: 593 × 3 #>    dataset_id                           dataset_title             dataset_total_cell_c…¹ #>    <chr>                                <chr>                                      <int> #>  1 f171db61-e57e-4535-a06a-35d8b6ef8f2b donor_p13_trophoblasts                     31497 #>  2 ecf2e08e-2032-4a9e-b466-b65b395f4a02 All donors trophoblasts                    67070 #>  3 74cff64f-9da9-4b2a-9b3b-8a04a1598040 All donors all cell stat…                 286326 #>  4 5af90777-6760-4003-9dba-8f945fec6fdf Single-cell transcriptom…                 270855 #>  5 bd65a70f-b274-4133-b9dd-0d1431b6af34 Single-cell sequencing l…                 167283 #>  6 ff45e623-7f5f-46e3-b47d-56be0341f66b Tabula Sapiens - Pancreas                  13497 #>  7 f01bdd17-4902-40f5-86e3-240d66dd2587 Tabula Sapiens - Salivar…                  27199 #>  8 e6a11140-2545-46bc-929e-da243eed2cae Tabula Sapiens - Heart                     11505 #>  9 e5c63d94-593c-4338-a489-e1048599e751 Tabula Sapiens - Bladder                   24583 #> 10 d8732da6-8d1d-42d9-b625-f2416c30054b Tabula Sapiens - Trachea                    9522 #> # ℹ 583 more rows #> # ℹ abbreviated name: ¹​dataset_total_cell_count census_data <- census$get(\"census_data\") all_experiments <- lapply(census_data$to_list(), function(x) census_data$get(x$name)) print(all_experiments) #> $mus_musculus #> <SOMAExperiment> #>   uri: s3://cellxgene-data-public/cell-census/2023-07-25/soma/census_data/mus_musculus  #>   arrays: obs*  #>   groups: ms*  #>  #> $homo_sapiens #> <SOMAExperiment> #>   uri: s3://cellxgene-data-public/cell-census/2023-07-25/soma/census_data/homo_sapiens  #>   arrays: obs*  #>   groups: ms* experiments_total_cells <- sum(sapply(all_experiments, function(x) {   nrow(x$obs$read(column_names = c(\"soma_joinid\"))$concat()) }))  print(paste(\"Found\", experiments_total_cells, \"cells in all experiments.\")) #> [1] \"Found 61656118 cells in all experiments.\" print(paste(   \"Found\", sum(as.vector(census_datasets$dataset_total_cell_count)),   \"cells in all datasets.\" )) #> [1] \"Found 61656118 cells in all datasets.\""},{"path":"/articles/census_datasets.html","id":"fetching-the-expression-data-from-a-single-dataset","dir":"Articles","previous_headings":"","what":"Fetching the expression data from a single dataset","title":"Census Datasets example","text":"Let’s pick one dataset slice census, turn Seurat -memory object. (requires Seurat package installed beforehand.) Create query mouse experiment, “RNA” measurement, dataset_id.","code":"census_datasets[census_datasets$dataset_id == \"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\", ] #> # A tibble: 1 × 8 #>   soma_joinid collection_id      collection_name collection_doi dataset_id dataset_title #>         <int> <chr>              <chr>           <chr>          <chr>      <chr>         #> 1         522 0b9d8a04-bb9d-44d… Tabula Muris S… 10.1038/s4158… 0bd1a1de-… Bone marrow … #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int> library(\"tiledbsoma\") #> Warning: package 'tiledbsoma' was built under R version 4.3.1 obs_query <- SOMAAxisQuery$new(   value_filter = \"dataset_id == '0bd1a1de-3aee-40e0-b2ec-86c7a30c7149'\" ) expt_query <- census_data$get(\"mus_musculus\")$axis_query(   measurement_name = \"RNA\",   obs_query = obs_query ) dataset_seurat <- expt_query$to_seurat(c(counts = \"raw\")) #> The legacy packages maptools, rgdal, and rgeos, underpinning the sp package, #> which was just loaded, will retire in October 2023. #> Please refer to R-spatial evolution reports for details, especially #> https://r-spatial.org/r/2023/05/15/evolution4.html. #> It may be desirable to make the sf package available; #> package maintainers should consider adding sf to Suggests:. #> The sp package is now running under evolution status 2 #>      (status 2 uses the sf package in place of rgdal) print(dataset_seurat) #> An object of class Seurat  #> 52392 features across 40220 samples within 1 assay  #> Active assay: RNA (52392 features, 0 variable features)"},{"path":"/articles/census_datasets.html","id":"downloading-the-original-source-h5ad-file-of-a-dataset","dir":"Articles","previous_headings":"","what":"Downloading the original source H5AD file of a dataset","title":"Census Datasets example","text":"can use cellxgene.census::get_source_h5ad_uri() API fetch URI pointing H5AD associated dataset_id. H5AD can download CZ CELLxGENE Discover, may contain additional data-submitter provided information included Census. can fetch location cloud directly download system. local H5AD file can used R using SeuratDisk’s anndata converter.","code":"# Option 1: Direct download download_source_h5ad(   dataset_id = \"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\",   file = \"/tmp/Tabula_Muris_Senis-bone_marrow.h5ad\",   overwrite = TRUE ) # Option 2: Get location and download via preferred method get_source_h5ad_uri(\"0bd1a1de-3aee-40e0-b2ec-86c7a30c7149\") #> $uri #> [1] \"s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/0bd1a1de-3aee-40e0-b2ec-86c7a30c7149.h5ad\" #>  #> $s3_region #> [1] \"us-west-2\""},{"path":"/articles/census_datasets.html","id":"close-the-census","dir":"Articles","previous_headings":"Downloading the original source H5AD file of a dataset","what":"Close the census","title":"Census Datasets example","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/census_query_extract.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the census","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version). can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/census_query_extract.html","id":"querying-cell-metadata-obs","dir":"Articles","previous_headings":"","what":"Querying cell metadata (obs)","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"human gene metadata Census, RNA assays, located census$get(\"census_data\")$get(\"homo_sapiens\")$obs. SOMADataFrame can materialized R data frame (tibble) using .data.frame(obs$read()$concat()). mouse cell metadata census$get(\"census_data\")$get(\"mus_musculus\").obs. slicing cell metadata two relevant arguments can passed read(): column_names — character vector indicating metadata columns fetch. Expressions one comparisons Comparisons one <column> <op> <value> <column> <op> <column> Expressions can combine comparisons using && || op one < | > | <= | >= | == | != %% learn metadata columns available fetching filtering can directly look keys cell metadata. soma_joinid special SOMADataFrame column used join operations. definition columns can found Census schema. can used fetch specific columns specific rows matching condition. latter need know values looking priori. example let’s see possible values available sex. can load cell metadata fetching column sex. can see three different values sex, \"male\", \"female\" \"unknown\". information can fetch cell metatadata specific sex value, example \"unknown\". can use column_names value_filter perform specific queries. example let’s fetch disease column cell_type \"B cell\" tissue_general \"lung\".","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$obs$colnames() #>  [1] \"soma_joinid\"                              #>  [2] \"dataset_id\"                               #>  [3] \"assay\"                                    #>  [4] \"assay_ontology_term_id\"                   #>  [5] \"cell_type\"                                #>  [6] \"cell_type_ontology_term_id\"               #>  [7] \"development_stage\"                        #>  [8] \"development_stage_ontology_term_id\"       #>  [9] \"disease\"                                  #> [10] \"disease_ontology_term_id\"                 #> [11] \"donor_id\"                                 #> [12] \"is_primary_data\"                          #> [13] \"self_reported_ethnicity\"                  #> [14] \"self_reported_ethnicity_ontology_term_id\" #> [15] \"sex\"                                      #> [16] \"sex_ontology_term_id\"                     #> [17] \"suspension_type\"                          #> [18] \"tissue\"                                   #> [19] \"tissue_ontology_term_id\"                  #> [20] \"tissue_general\"                           #> [21] \"tissue_general_ontology_term_id\" unique(as.data.frame(census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(column_names = \"sex\")$concat())) #> # A tibble: 3 × 1 #>   sex     #>   <chr>   #> 1 unknown #> 2 female  #> 3 male as.data.frame(census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(value_filter = \"sex == 'unknown'\")$concat()) #> # A tibble: 3,251,334 × 21 #>    soma_joinid dataset_id  assay assay_ontology_term_id cell_type cell_type_ontology_t…¹ #>          <int> <chr>       <chr> <chr>                  <chr>     <chr>                  #>  1           0 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  2           1 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #>  3           2 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  4           3 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  5           4 f171db61-e… 10x … EFO:0009922            extravil… CL:0008036             #>  6           5 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #>  7           6 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #>  8           7 f171db61-e… 10x … EFO:0009922            extravil… CL:0008036             #>  9           8 f171db61-e… 10x … EFO:0009922            placenta… CL:2000060             #> 10           9 f171db61-e… 10x … EFO:0009922            syncytio… CL:0000525             #> # ℹ 3,251,324 more rows #> # ℹ abbreviated name: ¹​cell_type_ontology_term_id #> # ℹ 15 more variables: development_stage <chr>, #> #   development_stage_ontology_term_id <chr>, disease <chr>, #> #   disease_ontology_term_id <chr>, donor_id <chr>, is_primary_data <lgl>, #> #   self_reported_ethnicity <chr>, self_reported_ethnicity_ontology_term_id <chr>, #> #   sex <chr>, sex_ontology_term_id <chr>, suspension_type <chr>, tissue <chr>, … cell_metadata_b_cell <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   value_filter = \"cell_type == 'B cell' & tissue_general == 'lung'\",   column_names = \"disease\" )  cell_metadata_b_cell <- as.data.frame(cell_metadata_b_cell$concat())  table(cell_metadata_b_cell) #> disease #> chronic obstructive pulmonary disease                              COVID-19  #>                                  6369                                  2729  #>          hypersensitivity pneumonitis             interstitial lung disease  #>                                    52                                   376  #>                   lung adenocarcinoma             lung large cell carcinoma  #>                                 62351                                  1534  #>              lymphangioleiomyomatosis         non-small cell lung carcinoma  #>                                   133                                 17484  #>   non-specific interstitial pneumonia                                normal  #>                                   231                                 25461  #>                 pleomorphic carcinoma                             pneumonia  #>                                  1210                                    50  #>                   pulmonary emphysema                    pulmonary fibrosis  #>                                  1512                                  6798  #>                 pulmonary sarcoidosis             small cell lung carcinoma  #>                                     6                                   583  #>          squamous cell lung carcinoma  #>                                 11920"},{"path":"/articles/census_query_extract.html","id":"querying-gene-metadata-var","dir":"Articles","previous_headings":"","what":"Querying gene metadata (var)","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"human gene metadata Census located census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var. Similarly cell metadata, SOMADataFrame thus can also use method read(). mouse gene metadata census$get(\"census_data\")$get(\"mus_musculus\")$ms$get(\"RNA\")$var. Let’s take look metadata available column selection row filtering. exception soma_joinid columns defined Census schema. Similarly cell metadata, can use operations learn fetch gene metadata. example, get feature_name feature_length genes \"ENSG00000161798\" \"ENSG00000188229\" can following.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$colnames() #> [1] \"soma_joinid\"    \"feature_id\"     \"feature_name\"   \"feature_length\" var_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$read(   value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   column_names = c(\"feature_name\", \"feature_length\") )  as.data.frame(var_df$concat()) #> # A tibble: 2 × 2 #>   feature_name feature_length #>   <chr>                 <int> #> 1 AQP5                   1884 #> 2 TUBB4B                 2037"},{"path":"/articles/census_query_extract.html","id":"querying-expression-data-as-seurat","dir":"Articles","previous_headings":"","what":"Querying expression data as Seurat","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"convenient way query fetch expression data use get_seurat method cellxgene.census API. method combines column selection value filtering described obtain slices expression data based metadata queries. method return Seurat object, takes input census object, string organism, cell gene metadata can specify filters column selection described following arguments: obs_column_names — character vector indicating columns select cell metadata. obs_value_filter — expression selection conditions fetch cells meeting criteria. var_column_names — character vector indicating columns select gene metadata. var_value_filter — expression selection conditions fetch genes meeting criteria. example want fetch expression data : Genes \"ENSG00000161798\" \"ENSG00000188229\". \"B cells\" \"lung\" \"COVID-19\". gene metadata adding sex cell metadata. full description refer ?cellxgene.census::get_seurat.","code":"library(\"Seurat\")  seurat_obj <- get_seurat(   census, \"Homo sapiens\",   obs_column_names = c(\"cell_type\", \"tissue_general\", \"disease\", \"sex\"),   var_value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   obs_value_filter = \"cell_type == 'B cell' & tissue_general == 'lung' & disease == 'COVID-19'\" ) seurat_obj #> An object of class Seurat  #> 2 features across 2729 samples within 1 assay  #> Active assay: RNA (2 features, 0 variable features) head(seurat_obj[[]]) #>                orig.ident nCount_RNA nFeature_RNA cell_type tissue_general  disease #> cell5946018 SeuratProject          0            0    B cell           lung COVID-19 #> cell5948526 SeuratProject          1            1    B cell           lung COVID-19 #> cell5949180 SeuratProject          0            0    B cell           lung COVID-19 #> cell5949686 SeuratProject          0            0    B cell           lung COVID-19 #> cell5950730 SeuratProject          0            0    B cell           lung COVID-19 #> cell5952197 SeuratProject          0            0    B cell           lung COVID-19 #>                 sex #> cell5946018    male #> cell5948526 unknown #> cell5949180    male #> cell5949686 unknown #> cell5950730    male #> cell5952197 unknown head(seurat_obj$RNA[[]]) #>                 feature_name feature_length #> ENSG00000161798         AQP5           1884 #> ENSG00000188229       TUBB4B           2037"},{"path":"/articles/census_query_extract.html","id":"querying-expression-data-as-singlecellexperiment","dir":"Articles","previous_headings":"","what":"Querying expression data as SingleCellExperiment","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"Similarly previous section, get_single_cell_experiment method cellxgene.census API. behaves exactly get_seurat returns SingleCellExperiment object. example, repeat query can simply following. full description refer ?cellxgene.census::get_single_cell_experiment.","code":"library(\"SingleCellExperiment\")  sce_obj <- get_single_cell_experiment(   census, \"Homo sapiens\",   obs_column_names = c(\"cell_type\", \"tissue_general\", \"disease\", \"sex\"),   var_value_filter = \"feature_id %in% c('ENSG00000161798', 'ENSG00000188229')\",   obs_value_filter = \"cell_type == 'B cell' & tissue_general == 'lung' & disease == 'COVID-19'\" ) sce_obj #> class: SingleCellExperiment  #> dim: 2 2729  #> metadata(0): #> assays(1): counts #> rownames(2): ENSG00000161798 ENSG00000188229 #> rowData names(2): feature_name feature_length #> colnames(2729): obs5946018 obs5948526 ... obs48038140 obs48038164 #> colData names(4): cell_type tissue_general disease sex #> reducedDimNames(0): #> mainExpName: RNA #> altExpNames(0): head(colData(sce_obj)) #> DataFrame with 6 rows and 4 columns #>              cell_type tissue_general     disease         sex #>            <character>    <character> <character> <character> #> obs5946018      B cell           lung    COVID-19        male #> obs5948526      B cell           lung    COVID-19     unknown #> obs5949180      B cell           lung    COVID-19        male #> obs5949686      B cell           lung    COVID-19     unknown #> obs5950730      B cell           lung    COVID-19        male #> obs5952197      B cell           lung    COVID-19     unknown head(rowData(sce_obj)) #> DataFrame with 2 rows and 2 columns #>                 feature_name feature_length #>                  <character>      <integer> #> ENSG00000161798         AQP5           1884 #> ENSG00000188229       TUBB4B           2037"},{"path":"/articles/census_query_extract.html","id":"close-the-census","dir":"Articles","previous_headings":"Querying expression data as SingleCellExperiment","what":"Close the census","title":"Querying and fetching the single-cell data and cell/gene metadata","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/articles/comp_bio_census_info.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Learning about the CZ CELLxGENE Census","text":"cellxgene.census R package contains convenient open_soma() API open version Census (stable default). can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/comp_bio_census_info.html","id":"census-organization","dir":"Articles","previous_headings":"","what":"Census organization","title":"Learning about the CZ CELLxGENE Census","text":"Census schema defines structure Census. short, can think Census structured collection items stores different pieces information. items parent collection SOMA objects various types can accessed TileDB-SOMA API (documentation). cellxgene.census package contains convenient wrappers TileDB-SOMA API. example function used open Census: cellxgene_census.open_soma().","code":""},{"path":"/articles/comp_bio_census_info.html","id":"main-census-components","dir":"Articles","previous_headings":"Census organization","what":"Main Census components","title":"Learning about the CZ CELLxGENE Census","text":"command created census, SOMACollection, R6 class providing key-value associative map. get() method can access two top-level collection members, census_info census_data, instances SOMACollection.","code":""},{"path":"/articles/comp_bio_census_info.html","id":"census-summary-info","dir":"Articles","previous_headings":"Census organization","what":"Census summary info","title":"Learning about the CZ CELLxGENE Census","text":"census$get(\"census_info\")$get(\"summary\"): data frame high-level information Census, e.g. build date, total cell count, etc. census$get(\"census_info\")$get(\"datasets\"): data frame datasets CELLxGENE Discover used create Census. census$get(\"census_info\")$get(\"summary_cell_counts\"): data frame cell counts stratified relevant cell metadata Census data Data organism stored independent SOMAExperiment objects specialized form SOMACollection. store data matrix (cell genes), cell metadata, gene metadata, useful components covered notebook. data organized one organism – Homo sapiens: census$get(\"census_data\")$get(\"homo_sapiens\")$obs: Cell metadata census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\"): Data matrices, currently … census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$X$get(\"raw\"): matrix raw counts SOMASparseNDArray census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var: Gene Metadata","code":""},{"path":"/articles/comp_bio_census_info.html","id":"cell-metadata","dir":"Articles","previous_headings":"","what":"Cell metadata","title":"Learning about the CZ CELLxGENE Census","text":"can obtain cell metadata variables directly querying columns corresponding SOMADataFrame. variables can used querying Census case want work specific cells. variables defined CELLxGENE dataset schema except following: soma_joinid: SOMA-defined value use join operations. dataset_id: dataset id encoded census$get(\"census_info\")$get(\"datasets\"). tissue_general tissue_general_ontology_term_id: high-level tissue mapping.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$obs$colnames() #>  [1] \"soma_joinid\"                              #>  [2] \"dataset_id\"                               #>  [3] \"assay\"                                    #>  [4] \"assay_ontology_term_id\"                   #>  [5] \"cell_type\"                                #>  [6] \"cell_type_ontology_term_id\"               #>  [7] \"development_stage\"                        #>  [8] \"development_stage_ontology_term_id\"       #>  [9] \"disease\"                                  #> [10] \"disease_ontology_term_id\"                 #> [11] \"donor_id\"                                 #> [12] \"is_primary_data\"                          #> [13] \"self_reported_ethnicity\"                  #> [14] \"self_reported_ethnicity_ontology_term_id\" #> [15] \"sex\"                                      #> [16] \"sex_ontology_term_id\"                     #> [17] \"suspension_type\"                          #> [18] \"tissue\"                                   #> [19] \"tissue_ontology_term_id\"                  #> [20] \"tissue_general\"                           #> [21] \"tissue_general_ontology_term_id\""},{"path":"/articles/comp_bio_census_info.html","id":"gene-metadata","dir":"Articles","previous_headings":"","what":"Gene metadata","title":"Learning about the CZ CELLxGENE Census","text":"Similarly, can obtain gene metadata variables directly querying columns corresponding SOMADataFrame. variables can use querying Census case specific genes interested . variables defined CELLxGENE dataset schema except following: soma_joinid: SOMA-defined value use join operations. feature_length: length base pairs gene.","code":"census$get(\"census_data\")$get(\"homo_sapiens\")$ms$get(\"RNA\")$var$colnames() #> [1] \"soma_joinid\"    \"feature_id\"     \"feature_name\"   \"feature_length\""},{"path":"/articles/comp_bio_census_info.html","id":"census-summary-content-tables","dir":"Articles","previous_headings":"","what":"Census summary content tables","title":"Learning about the CZ CELLxGENE Census","text":"can take quick look high-level Census information looking census$get(\"census_info\")$get(\"summary\"): special interest label-value combinations : total_cell_count total number cells Census. unique_cell_count number unique cells, cells may present twice due meta-analysis consortia-like data. number_donors_homo_sapiens number_donors_mus_musculus number individuals human mouse. guaranteed unique one individual ID may present identical different datasets.","code":"as.data.frame(census$get(\"census_info\")$get(\"summary\")$read()$concat()) #> # A tibble: 7 × 3 #>   soma_joinid label                      value      #>         <int> <chr>                      <chr>      #> 1           0 census_schema_version      1.0.0      #> 2           1 census_build_date          2023-07-25 #> 3           2 dataset_schema_version     3.0.0      #> 4           3 total_cell_count           61656118   #> 5           4 unique_cell_count          37447773   #> 6           5 number_donors_homo_sapiens 13035      #> 7           6 number_donors_mus_musculus 1417"},{"path":"/articles/comp_bio_census_info.html","id":"cell-counts-by-cell-metadata","dir":"Articles","previous_headings":"Census summary content tables","what":"Cell counts by cell metadata","title":"Learning about the CZ CELLxGENE Census","text":"looking census$get(\"census_info)$get(\"summary_cell_counts\") can get general idea cell counts stratified relevant cell metadata. cell metadata included table, can take look cell gene metadata available sections “Cell metadata” “Gene metadata”. line retrieves table casts R data frame: combination organism values category cell metadata can take look total_cell_count unique_cell_count cell counts combination. values category specified ontology_term_id label, value’s IDs labels, respectively.","code":"census_counts <- as.data.frame(census$get(\"census_info\")$get(\"summary_cell_counts\")$read()$concat()) head(census_counts) #> # A tibble: 6 × 7 #>   soma_joinid organism     category ontology_term_id unique_cell_count total_cell_count #>         <int> <chr>        <chr>    <chr>                        <int>            <int> #> 1           0 Homo sapiens all      na                        33364242         56400873 #> 2           1 Homo sapiens assay    EFO:0008722                 264166           279635 #> 3           2 Homo sapiens assay    EFO:0008780                  25652            51304 #> 4           3 Homo sapiens assay    EFO:0008919                  89477           206754 #> 5           4 Homo sapiens assay    EFO:0008931                  78750           188248 #> 6           5 Homo sapiens assay    EFO:0008953                   4693             9386 #> # ℹ 1 more variable: label <chr>"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-metadata-included-in-the-summary-counts-table","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: cell metadata included in the summary counts table","title":"Learning about the CZ CELLxGENE Census","text":"get available cell metadata summary counts table can following. Remember cell metadata available, variables omitted creation table.","code":"t(table(census_counts$organism, census_counts$category)) #>                           #>                           Homo sapiens Mus musculus #>   all                                1            1 #>   assay                             19            9 #>   cell_type                        613          248 #>   disease                           64            5 #>   self_reported_ethnicity           26            1 #>   sex                                3            3 #>   suspension_type                    1            1 #>   tissue                           220           66 #>   tissue_general                    54           27"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-counts-for-each-sequencing-assay-in-human-data","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: cell counts for each sequencing assay in human data","title":"Learning about the CZ CELLxGENE Census","text":"get cell counts sequencing assay type human data, can perform following operations:","code":"human_assay_counts <- census_counts[census_counts$organism == \"Homo sapiens\" & census_counts$category == \"assay\", ] human_assay_counts <- human_assay_counts[order(human_assay_counts$total_cell_count, decreasing = TRUE), ]"},{"path":"/articles/comp_bio_census_info.html","id":"example-number-of-microglial-cells-in-the-census","dir":"Articles","previous_headings":"Census summary content tables > Cell counts by cell metadata","what":"Example: number of microglial cells in the Census","title":"Learning about the CZ CELLxGENE Census","text":"specific term categories shown can directly find number cells term.","code":"census_counts[census_counts$label == \"microglial cell\", ] #> # A tibble: 2 × 7 #>   soma_joinid organism     category  ontology_term_id unique_cell_count total_cell_count #>         <int> <chr>        <chr>     <chr>                        <int>            <int> #> 1          69 Homo sapiens cell_type CL:0000129                  268114           370771 #> 2        1038 Mus musculus cell_type CL:0000129                   48998            62617 #> # ℹ 1 more variable: label <chr>"},{"path":"/articles/comp_bio_census_info.html","id":"understanding-census-contents-beyond-the-summary-tables","dir":"Articles","previous_headings":"","what":"Understanding Census contents beyond the summary tables","title":"Learning about the CZ CELLxGENE Census","text":"using pre-computed tables census$get(\"census_info\") easy quick way understand contents Census, falls short want learn certain slices Census. example, may want learn : cell types available human liver? total number cells lung datasets stratified sequencing technology? sex distribution cells brain mouse? diseases available T cells? questions can answered directly querying cell metadata shown examples .","code":""},{"path":"/articles/comp_bio_census_info.html","id":"example-all-cell-types-available-in-human","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: all cell types available in human","title":"Learning about the CZ CELLxGENE Census","text":"exemplify process accessing slicing cell metadata summary stats, let’s start trivial example take look human cell types available Census: number rows total number cells humans. Now, wish get cell counts per cell type can work data frame. addition, focus cells marked is_primary_data=TRUE ensures de-duplicate cells appear CELLxGENE Discover. number unique cells. Now let’s look counts per cell type: shows abundant cell types “glutamatergic neuron”, “CD8-positive, alpha-beta T cell”, “CD4-positive, alpha-beta T cell”. Now let’s take look number unique cell types: total number different cell types human. information example can quickly obtained summary table census$get(\"census-info\")$get(\"summary_cell_counts\"). examples complex can achieved accessing cell metadata.","code":"obs_df <-   census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(column_names = c(\"cell_type\", \"is_primary_data\")) as.data.frame(obs_df$concat()) #> # A tibble: 56,400,873 × 2 #>    cell_type                     is_primary_data #>    <chr>                         <lgl>           #>  1 syncytiotrophoblast cell      FALSE           #>  2 placental villous trophoblast FALSE           #>  3 syncytiotrophoblast cell      FALSE           #>  4 syncytiotrophoblast cell      FALSE           #>  5 extravillous trophoblast      FALSE           #>  6 placental villous trophoblast FALSE           #>  7 syncytiotrophoblast cell      FALSE           #>  8 extravillous trophoblast      FALSE           #>  9 placental villous trophoblast FALSE           #> 10 syncytiotrophoblast cell      FALSE           #> # ℹ 56,400,863 more rows obs_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = \"cell_type\",   value_filter = \"is_primary_data == TRUE\" )  obs_df <- as.data.frame(obs_df$concat()) nrow(obs_df) #> [1] 33364242 human_cell_type_counts <- table(obs_df$cell_type) sort(human_cell_type_counts, decreasing = TRUE)[1:10] #>  #>                          neuron            glutamatergic neuron  #>                         2673669                         1541605  #> CD4-positive, alpha-beta T cell CD8-positive, alpha-beta T cell  #>                         1258976                         1235987  #>              classical monocyte                          B cell  #>                         1030996                          908651  #>                     native cell             natural killer cell  #>                          889262                          768755  #>                      macrophage                 oligodendrocyte  #>                          721687                          710242 length(human_cell_type_counts) #> [1] 599"},{"path":"/articles/comp_bio_census_info.html","id":"example-cell-types-available-in-human-liver","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: cell types available in human liver","title":"Learning about the CZ CELLxGENE Census","text":"Similar example , can learn cell types available specific tissue, e.g. liver. achieve goal just need limit cell metadata tissue. use information cell metadata variable tissue_general. variable contains high-level tissue label cells Census: cell types cell counts human liver.","code":"obs_liver_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = \"cell_type\",   value_filter = \"is_primary_data == TRUE & tissue_general == 'liver'\" )  obs_liver_df <- as.data.frame(obs_liver_df$concat())  sort(table(obs_liver_df$cell_type), decreasing = TRUE)[1:10] #>  #>                          T cell                     hepatoblast  #>                           85739                           58447  #>                 neoplastic cell                    erythroblast  #>                           52431                           45605  #>                        monocyte                      hepatocyte  #>                           31388                           28309  #>             natural killer cell    periportal region hepatocyte  #>                           26871                           23509  #>                      macrophage centrilobular region hepatocyte  #>                           16707                           15819"},{"path":"/articles/comp_bio_census_info.html","id":"example-diseased-t-cells-in-human-tissues","dir":"Articles","previous_headings":"Understanding Census contents beyond the summary tables","what":"Example: diseased T cells in human tissues","title":"Learning about the CZ CELLxGENE Census","text":"example going get counts diseased cells annotated T cells. sake example focus “CD8-positive, alpha-beta T cell” “CD4-positive, alpha-beta T cell”: cell counts annotated indicated disease across human tissues “CD8-positive, alpha-beta T cell” “CD4-positive, alpha-beta T cell”.","code":"obs_t_cells_df <- census$get(\"census_data\")$get(\"homo_sapiens\")$obs$read(   column_names = c(\"disease\", \"tissue_general\"),   value_filter = \"is_primary_data == TRUE & disease != 'normal' & cell_type %in% c('CD8-positive, alpha-beta T cell', 'CD4-positive, alpha-beta T cell')\" )  obs_t_cells_df <- as.data.frame(obs_t_cells_df$concat())  print(table(obs_t_cells_df)) #>                                        tissue_general #> disease                                 adipose tissue adrenal gland  blood blood clot #>   B-cell non-Hodgkin lymphoma                        0             0  62499          0 #>   breast cancer                                      0             0      0          0 #>   chronic obstructive pulmonary disease              0             0      0          0 #>   chronic rhinitis                                   0             0      0          0 #>   clear cell renal carcinoma                         0             0   6548          0 #>   COVID-19                                           0             0 819428          0 #>   Crohn disease                                      0             0      0          0 #>   cystic fibrosis                                    0             0      0          0 #>   Down syndrome                                      0             0      0          0 #>   follicular lymphoma                                0             0      0          0 #>   influenza                                          0             0   8871          0 #>   interstitial lung disease                          0             0      0          0 #>   kidney benign neoplasm                             0             0     20          0 #>   kidney oncocytoma                                  0             0     16          0 #>   lung adenocarcinoma                                0           205      0          0 #>                                        tissue_general #> disease                                 bone marrow  brain breast  colon kidney  liver #>   B-cell non-Hodgkin lymphoma                     0      0      0      0      0      0 #>   breast cancer                                   0      0   1850      0      0      0 #>   chronic obstructive pulmonary disease           0      0      0      0      0      0 #>   chronic rhinitis                                0      0      0      0      0      0 #>   clear cell renal carcinoma                      0      0      0      0  20540      0 #>   COVID-19                                        0      0      0      0      0      0 #>   Crohn disease                                   0      0      0  17490      0      0 #>   cystic fibrosis                                 0      0      0      0      0      0 #>   Down syndrome                                 181      0      0      0      0      0 #>   follicular lymphoma                             0      0      0      0      0      0 #>   influenza                                       0      0      0      0      0      0 #>   interstitial lung disease                       0      0      0      0      0      0 #>   kidney benign neoplasm                          0      0      0      0     10      0 #>   kidney oncocytoma                               0      0      0      0   2408      0 #>   lung adenocarcinoma                             0   3274      0      0      0    507 #>                                        tissue_general #> disease                                   lung lymph node   nose pleural fluid #>   B-cell non-Hodgkin lymphoma                0          0      0             0 #>   breast cancer                              0          0      0             0 #>   chronic obstructive pulmonary disease   9382          0      0             0 #>   chronic rhinitis                           0          0    909             0 #>   clear cell renal carcinoma                 0         36      0             0 #>   COVID-19                               30578          0     13             0 #>   Crohn disease                              0          0      0             0 #>   cystic fibrosis                            7          0      0             0 #>   Down syndrome                              0          0      0             0 #>   follicular lymphoma                        0       1089      0             0 #>   influenza                                  0          0      0             0 #>   interstitial lung disease               1803          0      0             0 #>   kidney benign neoplasm                     0          0      0             0 #>   kidney oncocytoma                          0          0      0             0 #>   lung adenocarcinoma                   215013      24969      0         11558 #>                                        tissue_general #> disease                                 respiratory system saliva small intestine #>   B-cell non-Hodgkin lymphoma                            0      0               0 #>   breast cancer                                          0      0               0 #>   chronic obstructive pulmonary disease                  0      0               0 #>   chronic rhinitis                                       0      0               0 #>   clear cell renal carcinoma                             0      0               0 #>   COVID-19                                               4     41               0 #>   Crohn disease                                          0      0           52029 #>   cystic fibrosis                                        0      0               0 #>   Down syndrome                                          0      0               0 #>   follicular lymphoma                                    0      0               0 #>   influenza                                              0      0               0 #>   interstitial lung disease                              0      0               0 #>   kidney benign neoplasm                                 0      0               0 #>   kidney oncocytoma                                      0      0               0 #>   lung adenocarcinoma                                    0      0               0 #>  [ reached getOption(\"max.print\") -- omitted 10 rows ]"},{"path":"/articles/comp_bio_data_integration.html","id":"finding-and-fetching-data-from-mouse-liver-10x-genomics-and-smart-seq2","dir":"Articles","previous_headings":"","what":"Finding and fetching data from mouse liver (10X Genomics and Smart-Seq2)","title":"Integrating multi-dataset slices of data with Seurat","text":"Let’s load packages needed notebook. Now can open Census. notebook use Tabula Muris Senis data liver contains cells 10X Genomics Smart-Seq2 technologies. Let’s query datasets table Census filtering collection_name “Tabula Muris Senis” dataset_title “liver”. Now can use values dataset_id query load Seurat object cells datasets. can check cell counts 10X Genomics Smart-Seq2 data looking assay metadata.","code":"library(\"cellxgene.census\") library(\"Seurat\") census <- open_soma() census_datasets <- census$get(\"census_info\")$get(\"datasets\") census_datasets <- census_datasets$read(value_filter = \"collection_name == 'Tabula Muris Senis'\") census_datasets <- as.data.frame(census_datasets$concat())  # Print rows with liver data census_datasets[grep(\"Liver\", census_datasets$dataset_title), ] #> # A tibble: 2 × 8 #>   soma_joinid collection_id            collection_name collection_doi dataset_id #>         <int> <chr>                    <chr>           <chr>          <chr>      #> 1         525 0b9d8a04-bb9d-44da-aa27… Tabula Muris S… 10.1038/s4158… 4546e757-… #> 2         547 0b9d8a04-bb9d-44da-aa27… Tabula Muris S… 10.1038/s4158… 6202a243-… #> # ℹ 3 more variables: dataset_title <chr>, dataset_h5ad_path <chr>, #> #   dataset_total_cell_count <int> tabula_muris_liver_ids <- c(\"4546e757-34d0-4d17-be06-538318925fcd\", \"6202a243-b713-4e12-9ced-c387f8483dea\")  seurat_obj <- get_seurat(   census,   organism = \"Mus musculus\",   obs_value_filter = \"dataset_id %in% tabula_muris_liver_ids\" ) table(seurat_obj$assay) #>  #>  10x 3' v2 Smart-seq2  #>       7294       2859"},{"path":"/articles/comp_bio_data_integration.html","id":"gene-length-normalization-of-smart-seq2-data-","dir":"Articles","previous_headings":"","what":"Gene-length normalization of Smart-Seq2 data.","title":"Integrating multi-dataset slices of data with Seurat","text":"Smart-seq2 read counts normalized gene length. Lets first get gene lengths var.feature_length. Now can use normalize Smart-seq data. let’s split object assay. normalize Smart-seq slice using gene lengths merge back single object.","code":"smart_seq_gene_lengths <- seurat_obj$RNA[[]]$feature_length seurat_obj.list <- SplitObject(seurat_obj, split.by = \"assay\") seurat_obj.list[[\"Smart-seq2\"]][[\"RNA\"]]@counts <- seurat_obj.list[[\"Smart-seq2\"]][[\"RNA\"]]@counts / smart_seq_gene_lengths seurat_obj <- merge(seurat_obj.list[[1]], seurat_obj.list[[2]])"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-with-seurat","dir":"Articles","previous_headings":"","what":"Integration with Seurat","title":"Integrating multi-dataset slices of data with Seurat","text":"use native integration capabilities Seurat. comprehensive usage best practices Seurat intergation please refer doc site Seurat.","code":""},{"path":"/articles/comp_bio_data_integration.html","id":"inspecting-data-prior-to-integration","dir":"Articles","previous_headings":"Integration with Seurat","what":"Inspecting data prior to integration","title":"Integrating multi-dataset slices of data with Seurat","text":"Let’s take look strength batch effects data. perform embedding visualization via UMAP. Let’s basic data normalization variable gene selection now perform PCA UMAP   can see batch effects strong cells cluster primarily assay cell_type. Properly integrated embedding principle cluster primarily cell_type, assay best randomly distributed.","code":"seurat_obj <- SCTransform(seurat_obj) seurat_obj <- FindVariableFeatures(seurat_obj, selection.method = \"vst\", nfeatures = 2000) seurat_obj <- RunPCA(seurat_obj, features = VariableFeatures(object = seurat_obj)) seurat_obj <- RunUMAP(seurat_obj, dims = 1:30) # By assay p1 <- DimPlot(seurat_obj, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"data-integration-with-seurat","dir":"Articles","previous_headings":"Integration with Seurat","what":"Data integration with Seurat","title":"Integrating multi-dataset slices of data with Seurat","text":"Whenever query fetch Census data multiple datasets integration needs performed evidenced batch effects observed. paramaters Seurat used notebook selected model run quickly. best practices integration single-cell data using Seurat please refer documentation page. seurat_d reading article integrated cell atlas human lung health disease Sikkema et al. perfomed integration 43 datasets Lung. focus metadata Census can batch information integration.","code":""},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id","title":"Integrating multi-dataset slices of data with Seurat","text":"cells Census annotated dataset come \"dataset_id\". great place start integration. let’s run Seurat integration pipeline. First define model batch set dataset_id. Firs normalize select variable genes seperated batch key dataset_id Now perform integration. Let’s inspect results normalization UMAP visulization. plot UMAP.   Great! can see clustering longer mainly driven assay, albeit still contributing . Great! can see clustering longer mainly driven assay, albeit still contributing .","code":"# split the dataset into a list of two seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x) })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list) seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\") DefaultAssay(seurat_obj.combined) <- \"integrated\"  # Run the standard workflow for visualization and clustering seurat_obj.combined <- ScaleData(seurat_obj.combined, verbose = FALSE) seurat_obj.combined <- RunPCA(seurat_obj.combined, npcs = 30, verbose = FALSE) seurat_obj.combined <- RunUMAP(seurat_obj.combined, reduction = \"pca\", dims = 1:30) # By assay p1 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id-and-controlling-for-batch-using-donor_id","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id and controlling for batch using donor_id","title":"Integrating multi-dataset slices of data with Seurat","text":"Similar dataset_id, cells Census annotated donor_id. definition donor_id depends dataset left discretion data curators. However still rich information can used batch variable integration. donor_id guaranteed unique across cells Census, strongly recommend concatenating dataset_id donor_id use batch separator Seurat Now perform integration. inspect new results UMAP. Plot UMAP.   can see using dataset_id donor_id batch cells now mostly cluster cell type.","code":"# split the dataset into a list of two seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently controlling for batch seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x, vars.to.regress = \"donor_id\") })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list) seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") #> Finding all pairwise anchors #> Running CCA #> Merging objects #> Finding neighborhoods #> Finding anchors #>  Found 7026 anchors #> Filtering anchors #>  Retained 4880 anchors seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\") #> Merging dataset 1 into 2 #> Extracting anchors for merged samples #> Finding integration vectors #> Finding integration vector weights #> Integrating data DefaultAssay(seurat_obj.combined) <- \"integrated\"  # Run the standard workflow for visualization and clustering seurat_obj.combined <- RunPCA(seurat_obj.combined, npcs = 30, verbose = FALSE) seurat_obj.combined <- RunUMAP(seurat_obj.combined, reduction = \"pca\", dims = 1:30) #> 13:30:46 UMAP embedding parameters a = 0.9922 b = 1.112 #> 13:30:46 Read 10153 rows and found 30 numeric columns #> 13:30:46 Using Annoy for neighbor search, n_neighbors = 30 #> 13:30:46 Building Annoy index with metric = cosine, n_trees = 50 #> 0%   10   20   30   40   50   60   70   80   90   100% #> [----|----|----|----|----|----|----|----|----|----| #> **************************************************| #> 13:30:47 Writing NN index file to temp file /var/folders/9q/j_1zpqns7vz_s5n9l6_b943r0000gr/T//RtmpwHKO6w/file16d2113ba6e8 #> 13:30:47 Searching Annoy index using 1 thread, search_k = 3000 #> 13:30:51 Annoy recall = 100% #> 13:30:51 Commencing smooth kNN distance calibration using 1 thread with target n_neighbors = 30 #> 13:30:52 Initializing from normalized Laplacian + noise (using irlba) #> 13:30:53 Commencing optimization for 200 epochs, with 410804 positive edges #> 13:30:59 Optimization finished # By assay p1 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"assay\") p1 # By cell type p2 <- DimPlot(seurat_obj.combined, reduction = \"umap\", group.by = \"cell_type\") p2"},{"path":"/articles/comp_bio_data_integration.html","id":"integration-across-datasets-using-dataset_id-and-controlling-for-batch-using-donor_id-assay_ontology_term_id-suspension_type-","dir":"Articles","previous_headings":"Integration with Seurat > Data integration with Seurat","what":"Integration across datasets using dataset_id and controlling for batch using donor_id + assay_ontology_term_id + suspension_type.","title":"Integrating multi-dataset slices of data with Seurat","text":"cases one dataset may contain multiple assay types /multiple suspension types (cell vs nucleus), important consider metadata batches. Therefore, comprehensive definition batch Census can accomplished combining cell metadata dataset_id, donor_id, assay_ontology_term_id suspension_type, latter encode EFO ids assay types. example, two datasets used contain cells one assay , one suspension type . Thus make difference include metadata part batch. implementation look line","code":"# EXAMPLE, DON'T RUN.  # split the dataset into a list of seurat objects for each dataset seurat_obj.list <- SplitObject(seurat_obj, split.by = \"dataset_id\")  # normalize each dataset independently controlling for batch seurat_obj.list <- lapply(X = seurat_obj.list, FUN = function(x) {   x <- SCTransform(x, vars.to.regress = c(\"donor_id\", \"assay_ontology_term_id\", \"suspension_type\")) })  # select features for integration features <- SelectIntegrationFeatures(object.list = seurat_obj.list)  # integrate seurat_obj.list <- PrepSCTIntegration(seurat_obj.list, anchor.features = features) seurat_obj.anchors <- FindIntegrationAnchors(object.list = seurat_obj.list, anchor.features = features, normalization.method = \"SCT\") seurat_obj.combined <- IntegrateData(anchorset = seurat_obj.anchors, normalization.method = \"SCT\")"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the census","title":"Normalizing full-length gene sequencing data","text":"First open Census: can learn cellxgene.census methods accessing corresponding documentation, example ?cellxgene.census::open_soma.","code":"library(\"Seurat\") census <- cellxgene.census::open_soma()"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"fetching-full-length-example-sequencing-data-smart-seq","dir":"Articles","previous_headings":"","what":"Fetching full-length example sequencing data (Smart-Seq)","title":"Normalizing full-length gene sequencing data","text":"Let’s get example data, case ’ll fetch cells relatively small dataset derived Smart-Seq2 technology performs full-length gene sequencing: Collection: Tabula Muris Senis Dataset: Liver - single-cell transcriptomic atlas characterizes ageing tissues mouse - Smart-seq2 Let’s first find dataset’s id using dataset table Census. Now can use id fetch data. Let’s make sure data contains Smart-Seq2 cells. Great! can see small dataset containing 2,859 cells. Now let’s proceed normalize gene lengths.","code":"liver_dataset <- as.data.frame(   census$get(\"census_info\")$get(\"datasets\")         $read(value_filter=\"dataset_title == 'Liver - A single-cell transcriptomic atlas characterizes ageing tissues in the mouse - Smart-seq2'\")         $concat() ) liver_dataset #> # A tibble: 1 × 8 #>   soma_joinid collection_id      collection_name collection_doi dataset_id dataset_title #>         <int> <chr>              <chr>           <chr>          <chr>      <chr>         #> 1         525 0b9d8a04-bb9d-44d… Tabula Muris S… 10.1038/s4158… 4546e757-… Liver - A si… #> # ℹ 2 more variables: dataset_h5ad_path <chr>, dataset_total_cell_count <int> liver_dataset_id <- liver_dataset[1,\"dataset_id\"] liver_seurat <- cellxgene.census::get_seurat(   census,   organism = \"Mus musculus\",   obs_value_filter = paste0(\"dataset_id == '\", liver_dataset_id, \"'\") ) table(liver_seurat$assay) #>  #> Smart-seq2  #>       2859"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"normalizing-expression-to-account-for-gene-length","dir":"Articles","previous_headings":"","what":"Normalizing expression to account for gene length","title":"Normalizing full-length gene sequencing data","text":"default cellxgene_census::get_seurat() fetches genes Census. let’s first identify genes measured dataset subset Seurat obect include . goal can use “Dataset Presence Matrix” census$get(\"census_data\")$get(\"mus_musculus\")$ms$get(\"RNA\")$get(\"feature_dataset_presence_matrix\"). boolean matrix N x M N number datasets, M number genes Census, 1 entry indicates gene measured dataset. (Note Seurat objects transposed layout M x N.) Let’s get genes measured dataset. can see genes Census 17,992 measured dataset. Now let’s normalize genes gene length. can easily Census gene lengths included gene metadata feature_length. done! can now see real numbers instead integers.","code":"liver_seurat #> An object of class Seurat  #> 52392 features across 2859 samples within 1 assay  #> Active assay: RNA (52392 features, 0 variable features) liver_dataset_joinid <- liver_dataset$soma_joinid[1] presence_matrix <- cellxgene.census::get_presence_matrix(census, \"Mus musculus\", \"RNA\") presence_matrix <- presence_matrix$take(liver_dataset_joinid) gene_presence <- as.vector(presence_matrix$get_one_based_matrix())  liver_seurat <- liver_seurat[gene_presence, ] liver_seurat #> An object of class Seurat  #> 17992 features across 2859 samples within 1 assay  #> Active assay: RNA (17992 features, 0 variable features) GetAssayData(liver_seurat[1:5, 1:5], slot = \"data\") #> 5 x 5 sparse Matrix of class \"dgCMatrix\" #>                    cell3530079 cell3530080 cell3530081 cell3530082 cell3530083 #> ENSMUSG00000025900           .           .           .           .           . #> ENSMUSG00000025902           .           .           .           .        2250 #> ENSMUSG00000033845           .         559        1969           .           . #> ENSMUSG00000025903           .           .           .           .           . #> ENSMUSG00000033813           .           .         828           1          54 gene_lengths <- liver_seurat$RNA@meta.features$feature_length liver_seurat <- SetAssayData(   liver_seurat,    new.data = sweep(GetAssayData(liver_seurat, slot = \"data\"), 1, gene_lengths, \"/\") ) GetAssayData(liver_seurat[1:5, 1:5], slot = \"data\") #> 5 x 5 sparse Matrix of class \"dgCMatrix\" #>                    cell3530079 cell3530080 cell3530081  cell3530082 cell3530083 #> ENSMUSG00000025900           .  .            .         .             .          #> ENSMUSG00000025902           .  .            .         .             0.47150042 #> ENSMUSG00000033845           .  0.06586544   0.2320019 .             .          #> ENSMUSG00000025903           .  .            .         .             .          #> ENSMUSG00000033813           .  .            0.2744448 0.0003314551  0.01789857"},{"path":"/articles/comp_bio_normalizing_full_gene_sequencing.html","id":"validation-through-clustering-exploration","dir":"Articles","previous_headings":"","what":"Validation through clustering exploration","title":"Normalizing full-length gene sequencing data","text":"Let’s perform basic clustering analysis see cell types cluster expected using normalized counts. First basic filtering cells genes. normalize account sequencing depth transform data log scale. subset highly variable genes. finally scale values across gene axis. Now can proceed clustering analysis.  exceptions can see cells cell type cluster near serves sanity check gene-length normalization applied. Don’t forget close census.","code":"cells_per_gene <- rowSums(GetAssayData(liver_seurat, slot = \"counts\") > 0) genes_per_cell <- Matrix::colSums(liver_seurat$RNA@counts > 0) liver_seurat <- liver_seurat[cells_per_gene >= 5, genes_per_cell >= 500] liver_seurat <- Seurat::NormalizeData(   liver_seurat,   normalization.method = \"LogNormalize\",   scale.factor = 10000 ) liver_seurat <- Seurat::FindVariableFeatures(   liver_seurat,   selection.method = \"vst\",   nfeatures = 1000 ) all.genes <- rownames(liver_seurat) liver_seurat <- Seurat::ScaleData(liver_seurat, features = all.genes) liver_seurat <- RunPCA(   liver_seurat,   features = VariableFeatures(object = liver_seurat) ) liver_seurat <- FindNeighbors(liver_seurat, dims = 1:40) liver_seurat <- RunUMAP(liver_seurat, dims = 1:40) DimPlot(liver_seurat, reduction = \"umap\", group.by = \"cell_type\") census$close()"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"opening-the-census","dir":"Articles","previous_headings":"","what":"Opening the Census","title":"Summarizing cell and gene metadata","text":"cellxgene.census R package contains convenient API open version Census (default, newest stable version). open Census, close census$close(). can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma(). can learn cellxgene.census methods accessing corresponding documentation. example ?cellxgene.census::open_soma.","code":"library(\"cellxgene.census\") census <- open_soma()"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"summarizing-cell-metadata","dir":"Articles","previous_headings":"","what":"Summarizing cell metadata","title":"Summarizing cell and gene metadata","text":"Census open can use TileDB-SOMA methods SOMACollection. can thus access metadata SOMADataFrame objects encoding cell gene metadata. Tips: can read entire SOMADataFrame R using .data.frame(soma_df$read()$concat()). Queries much faster request DataFrame columns required analysis (e.g. column_names = c(\"soma_joinid\", \"cell_type_ontology_term_id\")). can also refine query results using value_filter, filter census matching records.","code":""},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"example-summarize-all-cell-types","dir":"Articles","previous_headings":"Summarizing cell metadata","what":"Example: Summarize all cell types","title":"Summarizing cell and gene metadata","text":"example reads cell metadata (obs) R data frame summarize variety ways.","code":"human <- census$get(\"census_data\")$get(\"homo_sapiens\")  # Read obs into an R data frame (tibble). obs_df <- human$obs$read(column_names = c(\"cell_type\")) obs_df <- as.data.frame(obs_df$concat())  # Find all unique values in the cell_type column. unique_cell_type <- unique(obs_df$cell_type)  cat(   \"There are\",   length(unique_cell_type),   \"cell types in the Census! The first few are: \",   paste(head(unique_cell_type), collapse = \", \") ) #> There are 613 cell types in the Census! The first few are:  syncytiotrophoblast cell, placental villous trophoblast, extravillous trophoblast, trophoblast giant cell, decidual natural killer cell, human, T cell"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"example-summarize-a-subset-of-cell-types-selected-with-a-value_filter","dir":"Articles","previous_headings":"Summarizing cell metadata","what":"Example: Summarize a subset of cell types, selected with a value_filter","title":"Summarizing cell and gene metadata","text":"example utilizes SOMA “value filter” read subset cells tissue_ontology_term_id equal UBERON:0002048 (lung tissue), summarizes query result. can also define much complex value filters. example: combine terms & | use %% operator query multiple values","code":"# Read cell_type terms for cells which have a specific tissue term LUNG_TISSUE <- \"UBERON:0002048\"  obs_df <- human$obs$read(column_names = c(\"cell_type\"), value_filter = paste0(\"tissue_ontology_term_id == '\", LUNG_TISSUE, \"'\")) obs_df <- as.data.frame(obs_df$concat())  # Find all unique values in the cell_type column as an R data frame. unique_cell_type <- unique(obs_df$cell_type) cat(   \"There are \",   length(unique_cell_type),   \" cell types in the Census where tissue_ontology_term_id == \",   LUNG_TISSUE,   \"!\\nThe first few are:\",   paste(head(unique_cell_type), collapse = \", \"),   \"\\n\" ) #> There are  185  cell types in the Census where tissue_ontology_term_id ==  UBERON:0002048 ! #> The first few are: type II pneumocyte, neutrophil, effector CD4-positive, alpha-beta T cell, effector CD8-positive, alpha-beta T cell, mature NK T cell, blood vessel endothelial cell  # Report the 10 most common top_10 <- sort(table(obs_df$cell_type), decreasing = TRUE)[1:10] cat(   \"The top 10 cell types where tissue_ontology_term_id ==\",    LUNG_TISSUE,   \"are: \",   paste(names(top_10), collapse = \", \") ) #> The top 10 cell types where tissue_ontology_term_id == UBERON:0002048 are:  native cell, alveolar macrophage, CD8-positive, alpha-beta T cell, CD4-positive, alpha-beta T cell, macrophage, type II pneumocyte, classical monocyte, natural killer cell, malignant cell, epithelial cell of lower respiratory tract # You can also do more complex queries, such as testing for inclusion in a list of values obs_df <- human$obs$read(   column_names = c(\"cell_type_ontology_term_id\"),   value_filter = \"tissue_ontology_term_id %in% c('UBERON:0002082', 'UBERON:OOO2084', 'UBERON:0002080')\" )  obs_df <- as.data.frame(obs_df$concat())  # Summarize top_10 <- sort(table(obs_df$cell_type_ontology_term_id), decreasing = TRUE)[1:10] print(top_10) #>  #> CL:0000746 CL:0008034 CL:0002548 CL:0000115 CL:0002131 CL:0000763 CL:0000669 CL:0000003  #>     159096      84750      79618      64190      61830      32088      27515      22707  #> CL:0000057 CL:0002144  #>      20117      18593"},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"full-census-metadata-stats","dir":"Articles","previous_headings":"","what":"Full Census metadata stats","title":"Summarizing cell and gene metadata","text":"example queries organisms Census, summarizes diversity various metadata labels.","code":"cols_to_query <- c(   \"cell_type_ontology_term_id\",   \"assay_ontology_term_id\",   \"tissue_ontology_term_id\" )  total_cells <- 0 for (organism in census$get(\"census_data\")$names()) {   print(organism)      obs_df <- census$get(\"census_data\")$get(organism)$obs$read(column_names = cols_to_query)   obs_df <- as.data.frame(obs_df$concat())      total_cells <- total_cells + nrow(obs_df)   for (col in cols_to_query) {     cat(\"  Unique \", col, \" values: \", length(unique(obs_df[[col]])), \"\\n\")   } } #> [1] \"mus_musculus\" #>   Unique  cell_type_ontology_term_id  values:  248  #>   Unique  assay_ontology_term_id  values:  9  #>   Unique  tissue_ontology_term_id  values:  66  #> [1] \"homo_sapiens\" #>   Unique  cell_type_ontology_term_id  values:  613  #>   Unique  assay_ontology_term_id  values:  19  #>   Unique  tissue_ontology_term_id  values:  220 cat(\"Complete Census contains \", total_cells, \" cells.\") #> Complete Census contains  61656118  cells."},{"path":"/articles/comp_bio_summarize_axis_query.html","id":"close-the-census","dir":"Articles","previous_headings":"Full Census metadata stats","what":"Close the census","title":"Summarizing cell and gene metadata","text":"use, census object closed release memory resources. also closes SOMA objects accessed via top-level census. Closing can automated using .exit(census$close(), add = TRUE) immediately census <- open_soma().","code":"census$close()"},{"path":"/authors.html","id":null,"dir":"","previous_headings":"","what":"Authors","title":"Authors and Citation","text":"Chan Zuckerberg Initiative. Author, maintainer, copyright holder, funder.","code":""},{"path":"/authors.html","id":"citation","dir":"","previous_headings":"","what":"Citation","title":"Authors and Citation","text":"Chan Zuckerberg Initiative (2023). cellxgene.census: CZ CELLxGENE Discover Cell Census. R package version 1.6.0, https://github.com/chanzuckerberg/cellxgene-census.","code":"@Manual{,   title = {cellxgene.census: CZ CELLxGENE Discover Cell Census},   author = {{Chan Zuckerberg Initiative}},   year = {2023},   note = {R package version 1.6.0},   url = {https://github.com/chanzuckerberg/cellxgene-census}, }"},{"path":"/index.html","id":"r-package-of-cz-cellxgene-discover-census","dir":"","previous_headings":"","what":"CZ CELLxGENE Discover Cell Census","title":"CZ CELLxGENE Discover Cell Census","text":"documentation R package cellxgene.census part CZ CELLxGENE Discover Census. full details Census data capabilities please go main Census site. cellxgene.census provides API efficiently access cloud-hosted Census single-cell data R. just seconds users can access slice Census data using cell gene filters across hundreds single-cell datasets. Census data can fetched iterative fashion bigger--memory slices data, quickly exported basic R structures, well Seurat SingleCellExperiment objects downstream analysis.","code":""},{"path":"/index.html","id":"installation","dir":"","previous_headings":"","what":"Installation","title":"CZ CELLxGENE Discover Cell Census","text":"installing Ubuntu, may need install following libraries via apt install, libxml2-dev libssl-dev libcurl4-openssl-dev. addition must cmake v3.21 greater. installing MacOS, need install developer tools Xcode. Windows supported. R session install cellxgene.census R-Universe. able export Census data Seurat SingleCellExperiment also need install respective packages.","code":"install.packages(   \"cellxgene.census\",   repos=c('https://chanzuckerberg.r-universe.dev', 'https://cloud.r-project.org') ) # Seurat install.packages(\"Seurat\")  # SingleCellExperiment if (!require(\"BiocManager\", quietly = TRUE))     install.packages(\"BiocManager\")  BiocManager::install(\"SingleCellExperiment\")"},{"path":"/index.html","id":"usage","dir":"","previous_headings":"","what":"Usage","title":"CZ CELLxGENE Discover Cell Census","text":"Check vignettes “Articles” section navigation bar site. highly recommend following vignettes starting point: Querying fetching single-cell data cell/gene metadata Learning CZ CELLxGENE Discover Census can also check quick start guide main Census site.","code":""},{"path":"/index.html","id":"example-seurat-and-singlecellexperiment-query","dir":"","previous_headings":"Usage","what":"Example Seurat and SingleCellExperiment query","title":"CZ CELLxGENE Discover Cell Census","text":"following creates Seurat object -demand sympathetic neurons Census filtering genes ENSG00000161798, ENSG00000188229. following retrieves data SingleCellExperiment object.","code":"library(\"cellxgene.census\") library(\"Seurat\")  census <- open_soma()  organism <- \"Homo sapiens\" gene_filter <- \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" cell_filter <-  \"cell_type == 'sympathetic neuron'\" cell_columns <- c(\"assay\", \"cell_type\", \"tissue\", \"tissue_general\", \"suspension_type\", \"disease\")  seurat_obj <- get_seurat(    census = census,    organism = organism,    var_value_filter = gene_filter,    obs_value_filter = cell_filter,    obs_column_names = cell_columns ) library(\"SingleCellExperiment\")  sce_obj <- get_single_cell_experiment(    census = census,    organism = organism,    var_value_filter = gene_filter,    obs_value_filter = cell_filter,    obs_column_names = cell_columns )"},{"path":"/index.html","id":"for-more-help","dir":"","previous_headings":"","what":"For More Help","title":"CZ CELLxGENE Discover Cell Census","text":"help, please go visit main Census site. believe found security issue, appreciate notification. Please send email security@chanzuckerberg.com.","code":""},{"path":"/reference/download_source_h5ad.html","id":null,"dir":"Reference","previous_headings":"","what":"Download source H5AD to local file name. — download_source_h5ad","title":"Download source H5AD to local file name. — download_source_h5ad","text":"Download source H5AD local file name.","code":""},{"path":"/reference/download_source_h5ad.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Download source H5AD to local file name. — download_source_h5ad","text":"","code":"download_source_h5ad(   dataset_id,   file,   overwrite = FALSE,   census_version = \"stable\",   census = NULL )"},{"path":"/reference/download_source_h5ad.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Download source H5AD to local file name. — download_source_h5ad","text":"dataset_id dataset_id interest. file Local file name store H5AD file. overwrite TRUE allow overwriting existing file. census_version desired Census version. census open Census handle census_version. provided, opened closed automatically; efficient reuse handle calling download_source_h5ad() multiple times.","code":""},{"path":"/reference/download_source_h5ad.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Download source H5AD to local file name. — download_source_h5ad","text":"","code":"download_source_h5ad(\"0895c838-e550-48a3-a777-dbcd35d30272\", \"/tmp/data.h5ad\", overwrite = TRUE)"},{"path":"/reference/get_census_version_description.html","id":null,"dir":"Reference","previous_headings":"","what":"Get release description for a Census version — get_census_version_description","title":"Get release description for a Census version — get_census_version_description","text":"Get release description Census version","code":""},{"path":"/reference/get_census_version_description.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get release description for a Census version — get_census_version_description","text":"","code":"get_census_version_description(census_version)"},{"path":"/reference/get_census_version_description.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Get release description for a Census version — get_census_version_description","text":"census_version census version name.","code":""},{"path":"/reference/get_census_version_description.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get release description for a Census version — get_census_version_description","text":"List release location metadata","code":""},{"path":"/reference/get_census_version_description.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get release description for a Census version — get_census_version_description","text":"","code":"as.data.frame(get_census_version_description(\"stable\")) #>   release_date release_build #> 1                 2023-07-25 #>                                                  soma.uri #> 1 s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #>               soma.relative_uri soma.s3_region #> 1 /cell-census/2023-07-25/soma/      us-west-2 #>                                                  h5ads.uri #> 1 s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #>               h5ads.relative_uri h5ads.s3_region do_not_delete  alias #> 1 /cell-census/2023-07-25/h5ads/       us-west-2          TRUE stable #>   census_version #> 1         stable"},{"path":"/reference/get_census_version_directory.html","id":null,"dir":"Reference","previous_headings":"","what":"Get the directory of Census releases currently available — get_census_version_directory","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"Get directory Census releases currently available","code":""},{"path":"/reference/get_census_version_directory.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"","code":"get_census_version_directory()"},{"path":"/reference/get_census_version_directory.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"Data frame available cell census releases, including location metadata.","code":""},{"path":"/reference/get_census_version_directory.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Get the directory of Census releases currently available — get_census_version_directory","text":"","code":"get_census_version_directory() #>            release_date release_build #> stable                     2023-07-25 #> latest                     2023-09-04 #> 2023-05-15                 2023-05-15 #> 2023-07-17                 2023-07-17 #> 2023-07-24                 2023-07-24 #> 2023-07-25                 2023-07-25 #> 2023-08-01                 2023-08-01 #> 2023-08-08                 2023-08-08 #> 2023-08-14                 2023-08-14 #> 2023-08-22                 2023-08-22 #> 2023-08-25                 2023-08-25 #> 2023-09-04                 2023-09-04 #>                                                           soma.uri #> stable     s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #> latest     s3://cellxgene-data-public/cell-census/2023-09-04/soma/ #> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/soma/ #> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/soma/ #> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/soma/ #> 2023-07-25 s3://cellxgene-data-public/cell-census/2023-07-25/soma/ #> 2023-08-01 s3://cellxgene-data-public/cell-census/2023-08-01/soma/ #> 2023-08-08 s3://cellxgene-data-public/cell-census/2023-08-08/soma/ #> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/soma/ #> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/soma/ #> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/soma/ #> 2023-09-04 s3://cellxgene-data-public/cell-census/2023-09-04/soma/ #>                        soma.relative_uri soma.s3_region #> stable     /cell-census/2023-07-25/soma/      us-west-2 #> latest     /cell-census/2023-09-04/soma/      us-west-2 #> 2023-05-15 /cell-census/2023-05-15/soma/      us-west-2 #> 2023-07-17 /cell-census/2023-07-17/soma/      us-west-2 #> 2023-07-24 /cell-census/2023-07-24/soma/      us-west-2 #> 2023-07-25 /cell-census/2023-07-25/soma/      us-west-2 #> 2023-08-01 /cell-census/2023-08-01/soma/      us-west-2 #> 2023-08-08 /cell-census/2023-08-08/soma/      us-west-2 #> 2023-08-14 /cell-census/2023-08-14/soma/      us-west-2 #> 2023-08-22 /cell-census/2023-08-22/soma/      us-west-2 #> 2023-08-25 /cell-census/2023-08-25/soma/      us-west-2 #> 2023-09-04 /cell-census/2023-09-04/soma/      us-west-2 #>                                                           h5ads.uri #> stable     s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #> latest     s3://cellxgene-data-public/cell-census/2023-09-04/h5ads/ #> 2023-05-15 s3://cellxgene-data-public/cell-census/2023-05-15/h5ads/ #> 2023-07-17 s3://cellxgene-data-public/cell-census/2023-07-17/h5ads/ #> 2023-07-24 s3://cellxgene-data-public/cell-census/2023-07-24/h5ads/ #> 2023-07-25 s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/ #> 2023-08-01 s3://cellxgene-data-public/cell-census/2023-08-01/h5ads/ #> 2023-08-08 s3://cellxgene-data-public/cell-census/2023-08-08/h5ads/ #> 2023-08-14 s3://cellxgene-data-public/cell-census/2023-08-14/h5ads/ #> 2023-08-22 s3://cellxgene-data-public/cell-census/2023-08-22/h5ads/ #> 2023-08-25 s3://cellxgene-data-public/cell-census/2023-08-25/h5ads/ #> 2023-09-04 s3://cellxgene-data-public/cell-census/2023-09-04/h5ads/ #>                        h5ads.relative_uri h5ads.s3_region do_not_delete  alias #> stable     /cell-census/2023-07-25/h5ads/       us-west-2          TRUE stable #> latest     /cell-census/2023-09-04/h5ads/       us-west-2         FALSE latest #> 2023-05-15 /cell-census/2023-05-15/h5ads/       us-west-2          TRUE        #> 2023-07-17 /cell-census/2023-07-17/h5ads/       us-west-2            NA        #> 2023-07-24 /cell-census/2023-07-24/h5ads/       us-west-2            NA        #> 2023-07-25 /cell-census/2023-07-25/h5ads/       us-west-2          TRUE        #> 2023-08-01 /cell-census/2023-08-01/h5ads/       us-west-2         FALSE        #> 2023-08-08 /cell-census/2023-08-08/h5ads/       us-west-2         FALSE        #> 2023-08-14 /cell-census/2023-08-14/h5ads/       us-west-2         FALSE        #> 2023-08-22 /cell-census/2023-08-22/h5ads/       us-west-2         FALSE        #> 2023-08-25 /cell-census/2023-08-25/h5ads/       us-west-2         FALSE        #> 2023-09-04 /cell-census/2023-09-04/h5ads/       us-west-2         FALSE"},{"path":"/reference/get_presence_matrix.html","id":null,"dir":"Reference","previous_headings":"","what":"Read the feature dataset presence matrix. — get_presence_matrix","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"Read feature dataset presence matrix.","code":""},{"path":"/reference/get_presence_matrix.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"","code":"get_presence_matrix(census, organism, measurement_name = \"RNA\")"},{"path":"/reference/get_presence_matrix.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"census census object cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA.","code":""},{"path":"/reference/get_presence_matrix.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"tiledbsoma::matrixZeroBasedView object dataset join id & feature join id dimensions, filled 1s indicating presence. sparse matrix accessed zero-based indexes since join id's may zero.","code":""},{"path":"/reference/get_presence_matrix.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Read the feature dataset presence matrix. — get_presence_matrix","text":"","code":"census <- open_soma() #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. on.exit(census$close(), add = TRUE) print(get_presence_matrix(census, \"Homo sapiens\")$dim()) #> Error in private$check_open_for_read_or_write(): Item must be open for read or write. s3://cellxgene-data-public/cell-census/2023-07-25/soma/"},{"path":"/reference/get_seurat.html","id":null,"dir":"Reference","previous_headings":"","what":"Export Census slices to Seurat — get_seurat","title":"Export Census slices to Seurat — get_seurat","text":"Convenience wrapper around SOMAExperimentAxisQuery, build execute query, return Seurat object.","code":""},{"path":"/reference/get_seurat.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Export Census slices to Seurat — get_seurat","text":"","code":"get_seurat(   census,   organism,   measurement_name = \"RNA\",   X_layers = c(counts = \"raw\", data = NULL),   obs_value_filter = NULL,   obs_coords = NULL,   obs_column_names = NULL,   var_value_filter = NULL,   var_coords = NULL,   var_column_names = NULL,   var_index = \"feature_id\" )"},{"path":"/reference/get_seurat.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Export Census slices to Seurat — get_seurat","text":"census census object, usually returned cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA. X_layers named character X layers add Seurat assay, names names Seurat slots (counts data) values names layers within X. obs_value_filter SOMA value_filter across columns obs dataframe, expressed string. obs_coords set coordinates obs dataframe index, expressed type format supported SOMADataFrame's read() method. obs_column_names Columns fetch obs data frame. var_value_filter obs_value_filter var. var_coords obs_coords var. var_column_names Columns fetch var data frame. var_index Name column ‘var’ add feature names.","code":""},{"path":"/reference/get_seurat.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Export Census slices to Seurat — get_seurat","text":"Seurat object containing sensus slice.","code":""},{"path":"/reference/get_seurat.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Export Census slices to Seurat — get_seurat","text":"","code":"if (FALSE) { census <- open_soma() seurat_obj <- get_seurat(   census,   organism = \"Homo sapiens\",   obs_value_filter = \"cell_type == 'leptomeningeal cell'\",   var_value_filter = \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" )  seurat_obj  census$close() }"},{"path":"/reference/get_single_cell_experiment.html","id":null,"dir":"Reference","previous_headings":"","what":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"Convenience wrapper around SOMAExperimentAxisQuery, build execute query, return SingleCellExperiment object.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"","code":"get_single_cell_experiment(   census,   organism,   measurement_name = \"RNA\",   X_layers = c(counts = \"raw\"),   obs_value_filter = NULL,   obs_coords = NULL,   obs_column_names = NULL,   var_value_filter = NULL,   var_coords = NULL,   var_column_names = NULL,   var_index = \"feature_id\" )"},{"path":"/reference/get_single_cell_experiment.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"census census object, usually returned cellxgene.census::open_soma(). organism organism query, usually one Homo sapiens Mus musculus measurement_name measurement object query. Defaults RNA. X_layers character vector X layers add assays main experiment; may optionally named set name resulting assay (eg. ‘X_layers = c(counts = \"raw\")’ load X layer “‘raw’” assay “‘counts’”); default, loads X layers obs_value_filter SOMA value_filter across columns obs dataframe, expressed string. obs_coords set coordinates obs dataframe index, expressed type format supported SOMADataFrame's read() method. obs_column_names Columns fetch obs data frame. var_value_filter obs_value_filter var. var_coords obs_coords var. var_column_names Columns fetch var data frame. var_index Name column ‘var’ add feature names.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"SingleCellExperiment object containing sensus slice.","code":""},{"path":"/reference/get_single_cell_experiment.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Export Census slices to SingleCellExperiment — get_single_cell_experiment","text":"","code":"if (FALSE) { census <- open_soma() sce_obj <- get_single_cell_experiment(   census,   organism = \"Homo sapiens\",   obs_value_filter = \"cell_type == 'leptomeningeal cell'\",   var_value_filter = \"feature_id %in% c('ENSG00000107317', 'ENSG00000106034')\" )  sce_obj  census$close() }"},{"path":"/reference/get_source_h5ad_uri.html","id":null,"dir":"Reference","previous_headings":"","what":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"Locate source h5ad file dataset.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"","code":"get_source_h5ad_uri(dataset_id, census_version = \"stable\", census = NULL)"},{"path":"/reference/get_source_h5ad_uri.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"dataset_id dataset_id interest. census_version desired Census version. census open Census handle census_version. provided, opened closed automatically; efficient reuse handle calling get_source_h5ad_uri() multiple times.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"list uri optional s3_region.","code":""},{"path":"/reference/get_source_h5ad_uri.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Locate source h5ad file for a dataset. — get_source_h5ad_uri","text":"","code":"get_source_h5ad_uri(\"0895c838-e550-48a3-a777-dbcd35d30272\") #> $uri #> [1] \"s3://cellxgene-data-public/cell-census/2023-07-25/h5ads/0895c838-e550-48a3-a777-dbcd35d30272.h5ad\" #>  #> $s3_region #> [1] \"us-west-2\" #>"},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":null,"dir":"Reference","previous_headings":"","what":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"Create SOMATileDBContext suitable using open_soma(). Typically open_soma() creates context automatically, one can created separately order set custom configuration options, share multiple open Census handles.","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"","code":"new_SOMATileDBContext_for_census(census_version_description, ...)"},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"census_version_description result get_census_version_description() desired Census version. ... Custom configuration options.","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"SOMATileDBContext object open_soma().","code":""},{"path":"/reference/new_SOMATileDBContext_for_census.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Create SOMATileDBContext for Census — new_SOMATileDBContext_for_census","text":"","code":"census_desc <- get_census_version_description(\"stable\") ctx <- new_SOMATileDBContext_for_census(census_desc, \"soma.init_buffer_bytes\" = paste(4 * 1024**3)) census <- open_soma(\"stable\", tiledbsoma_ctx = ctx) #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. census$close()"},{"path":"/reference/open_soma.html","id":null,"dir":"Reference","previous_headings":"","what":"Open the Census — open_soma","title":"Open the Census — open_soma","text":"Open Census","code":""},{"path":"/reference/open_soma.html","id":"ref-usage","dir":"Reference","previous_headings":"","what":"Usage","title":"Open the Census — open_soma","text":"","code":"open_soma(census_version = \"stable\", uri = NULL, tiledbsoma_ctx = NULL)"},{"path":"/reference/open_soma.html","id":"arguments","dir":"Reference","previous_headings":"","what":"Arguments","title":"Open the Census — open_soma","text":"census_version version Census, e.g., \"stable\". uri URI containing Census SOMA objects open instead released version. (supplied, takes precedence census_version.) tiledbsoma_ctx tiledbsoma::SOMATileDBContext built using new_SOMATileDBContext_for_census(). Optional (created automatically) using census_version context need reused.","code":""},{"path":"/reference/open_soma.html","id":"value","dir":"Reference","previous_headings":"","what":"Value","title":"Open the Census — open_soma","text":"Top-level tiledbsoma::SOMACollection object. use, census closed release memory resources, usually .exit(census$close(), add = TRUE). Closing top-level census also close SOMA objects accessed .","code":""},{"path":"/reference/open_soma.html","id":"ref-examples","dir":"Reference","previous_headings":"","what":"Examples","title":"Open the Census — open_soma","text":"","code":"census <- open_soma() #> The stable Census release is currently 2023-07-25. Specify census_version = \"2023-07-25\" in future calls to open_soma() to ensure data consistency. as.data.frame(census$get(\"census_info\")$get(\"summary\")$read()$concat()) #> # A tibble: 7 × 3 #>   soma_joinid label                      value      #>         <int> <chr>                      <chr>      #> 1           0 census_schema_version      1.0.0      #> 2           1 census_build_date          2023-07-25 #> 3           2 dataset_schema_version     3.0.0      #> 4           3 total_cell_count           61656118   #> 5           4 unique_cell_count          37447773   #> 6           5 number_donors_homo_sapiens 13035      #> 7           6 number_donors_mus_musculus 1417       census$close()"}]