updates Bio.PDBData call and environment.yml

environment.yml

@@ -10,11 +10,10 @@ dependencies:
   - pip
   - openmm=7.7
   - pdbfixer
-  - cudatoolkit==11.3.*
-  - pytorch-lightning==2.0.9
-  - biopython==1.79
-  - numpy==1.21
-  - pandas==2.0
+  - pytorch-lightning
+  - biopython
+  - numpy
+  - pandas
   - PyYAML==5.4.1
   - requests
   - scipy==1.7

openfold/data/mmcif_parsing.py

@@ -24,7 +24,7 @@ import os
 from typing import Any, Mapping, Optional, Sequence, Tuple
 
 from Bio import PDB
-from Bio.Data import SCOPData
+from Bio.Data import PDBData
 import numpy as np
 
 from openfold.data.errors import MultipleChainsError
@@ -283,7 +283,7 @@ def parse(
             author_chain = mmcif_to_author_chain_id[chain_id]
             seq = []
             for monomer in seq_info:
-                code = SCOPData.protein_letters_3to1.get(monomer.id, "X")
+                code = PDBData.protein_letters_3to1.get(monomer.id, "X")
                 seq.append(code if len(code) == 1 else "X")
             seq = "".join(seq)
             author_chain_to_sequence[author_chain] = seq