updates Bio.PDBData call and environment.yml

environment.yml

@@ -12,7 +12,7 @@ dependencies:
   - openmm=7.7
   - pdbfixer
   - pytorch-lightning
-  - biopython==1.79
+  - biopython
   - numpy
   - pandas
   - PyYAML==5.4.1
@@ -24,13 +24,13 @@ dependencies:
   - modelcif==0.7
   - awscli
   - ml-collections
-  - mkl=2024.0
+  - mkl=2022.1
   - aria2
   - git
   - bioconda::hmmer==3.3.2
   - bioconda::hhsuite==3.3.0
   - bioconda::kalign2==2.04
-  - pytorch::pytorch=2.2
+  - pytorch::pytorch=2.1
   - pytorch::pytorch-cuda=12.1
   - pip:
       - deepspeed==0.12.4

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