Skip to content

Commit

Permalink
auto update
Browse files Browse the repository at this point in the history
  • Loading branch information
@elkoz @github-actions
elkoz authored and github-actions[bot] committed Feb 8, 2024
1 parent 5e33dd8 commit 19b5c10
Show file tree
Hide file tree
Showing 15 changed files with 208 additions and 45 deletions.
1 change: 0 additions & 1 deletion dev/update_init_docs.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
"""Update the docstring in __init__.py with the README.md file."""


with open("README.md") as f:
readme = list(f.readlines())

Expand Down
117 changes: 107 additions & 10 deletions docs/data/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,8 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
proteinflow pickle file or a PDB file.

&#34;&#34;&#34;

import itertools
import os
import pickle
import string
Expand All @@ -60,6 +62,7 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
import pandas as pd
from Bio import pairwise2
from biopandas.pdb import PandasPdb
from editdistance import eval as edit_distance
from torch import Tensor, from_numpy

try:
Expand Down Expand Up @@ -611,6 +614,9 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
A dictionary mapping old chain IDs to new chain IDs

&#34;&#34;&#34;
for chain in self.get_chains():
if chain not in chain_dict:
chain_dict[chain] = chain
self._rename_chains({k: k * 5 for k in self.get_chains()})
self._rename_chains({k * 5: v for k, v in chain_dict.items()})

Expand Down Expand Up @@ -1024,6 +1030,10 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
Title of the PDB file (by default either the protein id or &#34;Untitled&#34;)

&#34;&#34;&#34;
if any([x[0].upper() != x for x in self.get_chains()]):
raise ValueError(
&#34;Chain IDs must be single uppercase letters, please rename with `rename_chains` before saving.&#34;
)
pdb_builder = PDBBuilder(
self,
only_ca=only_ca,
Expand Down Expand Up @@ -1809,9 +1819,9 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
esm_entry.align_structure(
reference_pdb_path=temp_file,
save_pdb_path=path.rsplit(&#34;.&#34;, 1)[0] + &#34;_aligned.pdb&#34;,
chain_ids=entry.get_predicted_chains()
if entry.has_predict_mask()
else chains,
chain_ids=(
entry.get_predicted_chains() if entry.has_predict_mask() else chains
),
)
rmsds.append(
entry.ca_rmsd(
Expand Down Expand Up @@ -2118,6 +2128,25 @@ <h1 class="title">Module <code>proteinflow.data</code></h1>
out_dict[&#34;protein_id&#34;] = self.id
return ProteinEntry.from_dict(out_dict)

def get_protein_class(self):
&#34;&#34;&#34;Get the protein class.

Returns
-------
protein_class : str
The protein class (&#34;single_chain&#34;, &#34;heteromer&#34;, &#34;homomer&#34;)

&#34;&#34;&#34;
if len(self.get_chains()) == 1:
return &#34;single_chain&#34;
else:
for chain1, chain2 in itertools.combinations(self.get_chains(), 2):
if len(chain1) &gt; 0.9 * len(chain2) or len(chain2) &gt; 0.9 * len(chain1):
return &#34;heteromer&#34;
if edit_distance(chain1, chain2) / max(len(chain1), len(chain2)) &gt; 0.1:
return &#34;heteromer&#34;
return &#34;homomer&#34;


class PDBEntry:
&#34;&#34;&#34;A class for parsing PDB entries.&#34;&#34;&#34;
Expand Down Expand Up @@ -4715,6 +4744,9 @@ <h2 id="parameters">Parameters</h2>
A dictionary mapping old chain IDs to new chain IDs

&#34;&#34;&#34;
for chain in self.get_chains():
if chain not in chain_dict:
chain_dict[chain] = chain
self._rename_chains({k: k * 5 for k in self.get_chains()})
self._rename_chains({k * 5: v for k, v in chain_dict.items()})

Expand Down Expand Up @@ -5128,6 +5160,10 @@ <h2 id="parameters">Parameters</h2>
Title of the PDB file (by default either the protein id or &#34;Untitled&#34;)

&#34;&#34;&#34;
if any([x[0].upper() != x for x in self.get_chains()]):
raise ValueError(
&#34;Chain IDs must be single uppercase letters, please rename with `rename_chains` before saving.&#34;
)
pdb_builder = PDBBuilder(
self,
only_ca=only_ca,
Expand Down Expand Up @@ -5913,9 +5949,9 @@ <h2 id="parameters">Parameters</h2>
esm_entry.align_structure(
reference_pdb_path=temp_file,
save_pdb_path=path.rsplit(&#34;.&#34;, 1)[0] + &#34;_aligned.pdb&#34;,
chain_ids=entry.get_predicted_chains()
if entry.has_predict_mask()
else chains,
chain_ids=(
entry.get_predicted_chains() if entry.has_predict_mask() else chains
),
)
rmsds.append(
entry.ca_rmsd(
Expand Down Expand Up @@ -6220,7 +6256,26 @@ <h2 id="parameters">Parameters</h2>
out_dict[chain][&#34;predict_msk&#34;] = self.predict_mask[chain][chain_mask]
if self.id is not None:
out_dict[&#34;protein_id&#34;] = self.id
return ProteinEntry.from_dict(out_dict)</code></pre>
return ProteinEntry.from_dict(out_dict)

def get_protein_class(self):
&#34;&#34;&#34;Get the protein class.

Returns
-------
protein_class : str
The protein class (&#34;single_chain&#34;, &#34;heteromer&#34;, &#34;homomer&#34;)

&#34;&#34;&#34;
if len(self.get_chains()) == 1:
return &#34;single_chain&#34;
else:
for chain1, chain2 in itertools.combinations(self.get_chains(), 2):
if len(chain1) &gt; 0.9 * len(chain2) or len(chain2) &gt; 0.9 * len(chain1):
return &#34;heteromer&#34;
if edit_distance(chain1, chain2) / max(len(chain1), len(chain2)) &gt; 0.1:
return &#34;heteromer&#34;
return &#34;homomer&#34;</code></pre>
</details>
<h3>Class variables</h3>
<dl>
Expand Down Expand Up @@ -6455,9 +6510,9 @@ <h2 id="returns">Returns</h2>
esm_entry.align_structure(
reference_pdb_path=temp_file,
save_pdb_path=path.rsplit(&#34;.&#34;, 1)[0] + &#34;_aligned.pdb&#34;,
chain_ids=entry.get_predicted_chains()
if entry.has_predict_mask()
else chains,
chain_ids=(
entry.get_predicted_chains() if entry.has_predict_mask() else chains
),
)
rmsds.append(
entry.ca_rmsd(
Expand Down Expand Up @@ -8486,6 +8541,40 @@ <h2 id="returns">Returns</h2>
return ProteinEntry.from_dict(entry_dict)</code></pre>
</details>
</dd>
<dt id="proteinflow.data.ProteinEntry.get_protein_class"><code class="name flex">
<span>def <span class="ident">get_protein_class</span></span>(<span>self)</span>
</code></dt>
<dd>
<div class="desc"><p>Get the protein class.</p>
<h2 id="returns">Returns</h2>
<dl>
<dt><strong><code>protein_class</code></strong> :&ensp;<code>str</code></dt>
<dd>The protein class ("single_chain", "heteromer", "homomer")</dd>
</dl></div>
<details class="source">
<summary>
<span>Expand source code</span>
</summary>
<pre><code class="python">def get_protein_class(self):
&#34;&#34;&#34;Get the protein class.

Returns
-------
protein_class : str
The protein class (&#34;single_chain&#34;, &#34;heteromer&#34;, &#34;homomer&#34;)

&#34;&#34;&#34;
if len(self.get_chains()) == 1:
return &#34;single_chain&#34;
else:
for chain1, chain2 in itertools.combinations(self.get_chains(), 2):
if len(chain1) &gt; 0.9 * len(chain2) or len(chain2) &gt; 0.9 * len(chain1):
return &#34;heteromer&#34;
if edit_distance(chain1, chain2) / max(len(chain1), len(chain2)) &gt; 0.1:
return &#34;heteromer&#34;
return &#34;homomer&#34;</code></pre>
</details>
</dd>
<dt id="proteinflow.data.ProteinEntry.get_sequence"><code class="name flex">
<span>def <span class="ident">get_sequence</span></span>(<span>self, chains=None, encode=False, cdr=None, only_known=False)</span>
</code></dt>
Expand Down Expand Up @@ -8847,6 +8936,9 @@ <h2 id="parameters">Parameters</h2>
A dictionary mapping old chain IDs to new chain IDs

&#34;&#34;&#34;
for chain in self.get_chains():
if chain not in chain_dict:
chain_dict[chain] = chain
self._rename_chains({k: k * 5 for k in self.get_chains()})
self._rename_chains({k * 5: v for k, v in chain_dict.items()})</code></pre>
</details>
Expand Down Expand Up @@ -9201,6 +9293,10 @@ <h2 id="parameters">Parameters</h2>
Title of the PDB file (by default either the protein id or &#34;Untitled&#34;)

&#34;&#34;&#34;
if any([x[0].upper() != x for x in self.get_chains()]):
raise ValueError(
&#34;Chain IDs must be single uppercase letters, please rename with `rename_chains` before saving.&#34;
)
pdb_builder = PDBBuilder(
self,
only_ca=only_ca,
Expand Down Expand Up @@ -9949,6 +10045,7 @@ <h4><code><a title="proteinflow.data.ProteinEntry" href="#proteinflow.data.Prote
<li><code><a title="proteinflow.data.ProteinEntry.get_predict_mask" href="#proteinflow.data.ProteinEntry.get_predict_mask">get_predict_mask</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.get_predicted_chains" href="#proteinflow.data.ProteinEntry.get_predicted_chains">get_predicted_chains</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.get_predicted_entry" href="#proteinflow.data.ProteinEntry.get_predicted_entry">get_predicted_entry</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.get_protein_class" href="#proteinflow.data.ProteinEntry.get_protein_class">get_protein_class</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.get_sequence" href="#proteinflow.data.ProteinEntry.get_sequence">get_sequence</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.has_cdr" href="#proteinflow.data.ProteinEntry.has_cdr">has_cdr</a></code></li>
<li><code><a title="proteinflow.data.ProteinEntry.has_predict_mask" href="#proteinflow.data.ProteinEntry.has_predict_mask">has_predict_mask</a></code></li>
Expand Down

0 comments on commit 19b5c10

Please sign in to comment.