Return ptm from batch colabfold

.github/workflows/release-to-pypi.yml

@@ -71,6 +71,11 @@ jobs:
         with:
           name: python-package-distributions
           path: dist/
+      - name: Extract version from setup.py
+        id: get_version
+        run: |
+          VERSION=$(python setup.py --version)
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
       - name: Sign the dists with Sigstore
         uses: sigstore/gh-action-sigstore-python@v3.0.0
         with:
@@ -82,15 +87,15 @@ jobs:
           GITHUB_TOKEN: ${{ github.token }}
         run: >-
           gh release create
-          '${{ github.ref_name }}'
+          "$VERSION"
           --repo '${{ github.repository }}'
           --notes ""
       - name: Upload artifact signatures to GitHub Release
         env:
           GITHUB_TOKEN: ${{ github.token }}
         run: >-
           gh release upload
-          '${{ github.ref_name }}' dist/**
+          "$VERSION" dist/**
           --repo '${{ github.repository }}'
 
   publish-to-testpypi:

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name="plcg",
-    version="1.0.1",
+    version="1.0.2",
     author="Spencer Perkins",
     author_email="spencer.perkins44sp@gmail.com",
     description="Computational biology and machine learning utilities for the Pardee Lab Computation Group",

src/plcg/structure_prediction/colabfold/colabfold.py

@@ -2,6 +2,7 @@
 import os
 import shutil
 import subprocess
+import json
 
 from plcg.structure_prediction.fasta.fasta import save_fasta_file
 
@@ -48,7 +49,7 @@ def run_colabfold_and_get_filepath(seq: str, working_dir: str):
     if len(json_filepath) > 0:
         json_filepath = json_filepath[0]
         with open(working_dir + json_filepath, "r", encoding="utf-8") as f:
-            data = f.read()
+            data = json.load(f)
             ptm_value = data.get("ptm")
 
     return pdb_filepath, ptm_value
@@ -76,11 +77,15 @@ def run_colabfold_batch_and_return_filepaths(sequences: list[str], working_dir:
     save_fasta_file(sequences, working_dir + fasta_file_path)
     colabfold_batch(working_dir + fasta_file_path, working_dir)
     sequences_to_pdb_filepaths = {}
+    sequences_to_json_filepaths = {}
     files = os.listdir(working_dir)
     for i, sequence in enumerate(sequences):
         results = [result for result in files if "Sequence_" + str(i) in result]
         result = [result for result in results if "unrelaxed_rank_001" in result]
+        json_filepath = [result for result in results if "scores_rank_001" in result]
         if len(result) > 0:
             result = result[0]
+            json_filepath = json_filepath[0]
             sequences_to_pdb_filepaths[i] = working_dir + result
-    return sequences_to_pdb_filepaths
+            sequences_to_json_filepaths[i] = working_dir + json_filepath
+    return sequences_to_pdb_filepaths, sequences_to_json_filepaths