Merge pull request #9 from chanzuckerberg/uermel/method_type

Add method type to 10000 - 10010 and fix various metadata errors found along the way. Also added is_curator_recommended and is_visualization_default to 10000 - 10010. Reimports required: 10000: Dataset metadata, Annotation metadata 10001: Annotation metadata 10002: Annotation metadata 10003: Annotation metadata 10004: Annotation metadata 10005: Annotation metadata 10006: Annotation metadata 10007: Annotation metadata 10008: Annotation metadata 10009: Dataset metadata, Annotation metadata 10010: Annotation metadata
chanzuckerberg · Feb 9, 2024 · b4e39dd · b4e39dd
2 parents fcb8d19 + 166ec26
commit b4e39dd
Show file tree

Hide file tree

Showing 11 changed files with 181 additions and 31 deletions.
diff --git a/ingestion_tools/dataset_configs/10000.yaml b/ingestion_tools/dataset_configs/10000.yaml
@@ -16,8 +16,8 @@ dataset:
       ORCID: 0000-0003-4388-1349
     - name: Mauricio Toro-Nahuelpan
       ORCID: 0000-0001-5333-3640
-    - name: Cheng DWC
-    - name: Tollervey F
+    - name: Dorothy W. C. Cheng
+    - name: Fergus Tollervey
     - name: Constantin Pape
       ORCID: 0000-0001-6562-7187
     - name: Martin Beck
@@ -64,6 +64,7 @@ annotations:
         name: 'fatty acid synthase complex'
       dates: *repo-dates
       annotation_method: Cumulative template-matching trained 2D CNN predictions + visual filtering + distance constraints + manual addition
+      method_type: hybrid
       annotation_publications: &annotation_publication "EMPIAR-10988, EMD-14412, EMD-14413, EMD-14415, EMD-14417, EMD-14418, EMD-14419, EMD-14420, 10.1101/2022.04.12.488077"
       ground_truth_status: true
       authors: &annotation_authors
@@ -98,27 +99,32 @@ annotations:
           corresponding_author_status: true
       annotation_software: pyTOM + Keras
       version: "1.0"
+      is_curator_recommended: true
     sources:
       - columns: xyz
         file_format: csv
         glob_string: particle_lists/{run_name}_fas.csv
         shape: Point
+        is_visualization_default: false
   - metadata:
       annotation_object:
         id: GO:0022626
         name: 'cytosolic ribosome'
       dates: *repo-dates
       annotation_method: Cumulative template-matching trained 2D CNN predictions + visual filtering + distance constraints + manual addition
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
       annotation_software: pyTOM + Keras
       version: "1.0"
+      is_curator_recommended: true
     sources:
       - shape: Point
         columns: xyz
         file_format: csv
         glob_string: particle_lists/{run_name}_cyto_ribosomes.csv
+        is_visualization_default: true
   # Label 1 - cytoplasm
   - metadata:
       annotation_object:
@@ -128,6 +134,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: &organelle_segmask_annotation_method spectrum equalization filter + 2D CNN prediction + manual correction
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -137,11 +144,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: &segmask1_glob 'labels/180426_{mapped_segmask_name}.labels.mrc'
         mask_label: 1
+        is_visualization_default: false
   # Label 2 - Mitochondria
   - metadata:
       annotation_object:
@@ -151,6 +160,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -160,11 +170,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 2
+        is_visualization_default: true
   # Label 3 - Vesicle
   - metadata:
       annotation_object:
@@ -174,6 +186,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -183,11 +196,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 3
+        is_visualization_default: false
   # Label 4 - Microtubule
   - metadata:
       annotation_object:
@@ -197,6 +212,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -206,11 +222,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 4
+        is_visualization_default: true
   # Label 5 - ER
   - metadata:
       annotation_object:
@@ -220,6 +238,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -229,11 +248,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 5
+        is_visualization_default: true
   # Label 6 - Nuclear envelope
   - metadata:
       annotation_object:
@@ -243,6 +264,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -252,11 +274,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 6
+        is_visualization_default: true
   # Label 7 - Nucleus
   - metadata:
       annotation_object:
@@ -266,6 +290,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -275,11 +300,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 7
+        is_visualization_default: false
   # Label 8 - Vacuole
   - metadata:
       annotation_object:
@@ -289,6 +316,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -298,11 +326,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 8
+        is_visualization_default: false
   # Label 9 - Lipid droplet
   - metadata:
       annotation_object:
@@ -312,6 +342,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -321,11 +352,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 9
+        is_visualization_default: false
   # Label 10 - Golgi apparatus
   - metadata:
       annotation_object:
@@ -335,6 +368,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -344,11 +378,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 10
+        is_visualization_default: true
   # Label 11 - Vesicular body
   - metadata:
       annotation_object:
@@ -358,6 +394,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -367,11 +404,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 11
+        is_visualization_default: false
   # Label 13 - Non-specified compartment
   - metadata:
       annotation_object:
@@ -381,6 +420,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: *organelle_segmask_annotation_method
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -390,11 +430,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: false
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: *segmask1_glob
         mask_label: 13
+        is_visualization_default: false
   # Membranes
   - metadata:
       annotation_object:
@@ -404,6 +446,7 @@ annotations:
         state: ~
       dates: *repo-dates
       annotation_method: 3D CNN prediction + manual correction
+      method_type: hybrid
       annotation_publications: *annotation_publication
       ground_truth_status: true
       authors: *annotation_authors
@@ -413,11 +456,13 @@ annotations:
         precision: ~
         recall: ~
         ground_truth_used: ~
+      is_curator_recommended: true
     sources:
       - shape: SemanticSegmentationMask
         file_format: mrc
         glob_string: 'labels/{run_name}_membranes.mrc'
         mask_label: 1
+        is_visualization_default: false
 runs: {}
 tiltseries:
   scales: []