boltz-vsynthes 0.1.3__tar.gz → 0.1.5__tar.gz

{boltz_vsynthes-0.1.3 → boltz_vsynthes-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 0.1.3
+Version: 0.1.5
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown

{boltz_vsynthes-0.1.3 → boltz_vsynthes-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "boltz-vsynthes"
-version = "0.1.3"
+version = "0.1.5"
 requires-python = ">=3.10,<3.13"
 description = "Boltz for VSYNTHES"
 readme = "README.md"

{boltz_vsynthes-0.1.3 → boltz_vsynthes-0.1.5}/src/boltz/data/parse/pdb.py

@@ -8,6 +8,9 @@ from Bio.PDB.Polypeptide import PPBuilder
 from Bio.Data.IUPACData import protein_letters_3to1
 from rdkit import Chem
 from rdkit.Chem.rdchem import Mol
+from Bio.SeqUtils import seq1
+from collections import defaultdict
+
 
 from boltz.data.types import Target
 from boltz.data.parse.schema import parse_boltz_schema
@@ -38,27 +41,35 @@ def parse_pdb(
         Dictionary containing sequences and bonds.
     """
     # Read PDB file
-    parser = PDBParser(QUIET=True)
-    structure = parser.get_structure("protein", str(pdb_path))
-    ppb = PPBuilder()
-
-    # Convert to yaml format
     sequences = []
-    for model in structure:
-        for chain in model:
-            for pp in ppb.build_peptides(chain):
-                seq = str(pp.get_sequence())
-                if seq:  # Only add if sequence is not empty
-                    sequences.append({
-                        "protein": {
-                            "id": chain.id,
-                            "sequence": seq,
-                            "modifications": [],
-                        }
-                    })
+    sequence_by_chain = defaultdict(list)
+
+    # Parse SEQRES records directly
+    with open(pdb_path) as f:
+        for line in f:
+            if line.startswith("SEQRES"):
+                parts = line.split()
+                chain_id = parts[2]
+                residues = parts[4:]
+                for res in residues:
+                    try:
+                        aa = seq1(res)
+                    except KeyError:
+                        aa = 'X'
+                    sequence_by_chain[chain_id].append(aa)
+
+    # Convert to yaml-style list
+    for chain_id, aa_list in sequence_by_chain.items():
+        sequences.append({
+            "protein": {
+                "id": chain_id,
+                "sequence": ''.join(aa_list),
+                "modifications": [],
+            }
+        })
 
     return {
         "sequences": sequences,
         "bonds": [],
         "version": 1,
-    } 
+    }

{boltz_vsynthes-0.1.3 → boltz_vsynthes-0.1.5}/src/boltz/data/parse/pdb_download.py

@@ -8,6 +8,8 @@ from Bio.PDB.PDBParser import PDBParser
 from Bio.PDB.Polypeptide import PPBuilder
 from rdkit import Chem
 from rdkit.Chem.rdchem import Mol
+from Bio.SeqUtils import seq1
+from collections import defaultdict
 
 from boltz.data.types import Target
 from boltz.data.parse.schema import parse_boltz_schema
@@ -79,28 +81,35 @@ def parse_pdb_id(
     # Download PDB file
     pdb_path = download_pdb(pdb_id, cache_dir)
 
-    # Read PDB file
-    parser = PDBParser(QUIET=True)
-    structure = parser.get_structure("protein", str(pdb_path))
-    ppb = PPBuilder()
-
-    # Convert to yaml format
     sequences = []
-    for model in structure:
-        for chain in model:
-            for pp in ppb.build_peptides(chain):
-                seq = str(pp.get_sequence())
-                if seq:  # Only add if sequence is not empty
-                    sequences.append({
-                        "protein": {
-                            "id": chain.id,
-                            "sequence": seq,
-                            "modifications": [],
-                        }
-                    })
+    sequence_by_chain = defaultdict(list)
+
+    # Parse SEQRES records directly
+    with open(pdb_path) as f:
+        for line in f:
+            if line.startswith("SEQRES"):
+                parts = line.split()
+                chain_id = parts[2]
+                residues = parts[4:]
+                for res in residues:
+                    try:
+                        aa = seq1(res)
+                    except KeyError:
+                        aa = 'X'
+                    sequence_by_chain[chain_id].append(aa)
+
+    # Convert to yaml-style list
+    for chain_id, aa_list in sequence_by_chain.items():
+        sequences.append({
+            "protein": {
+                "id": chain_id,
+                "sequence": ''.join(aa_list),
+                "modifications": [],
+            }
+        })
 
     return {
         "sequences": sequences,
         "bonds": [],
         "version": 1,
-    } 
+    } 

{boltz_vsynthes-0.1.3 → boltz_vsynthes-0.1.5}/src/boltz_vsynthes.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: boltz-vsynthes
-Version: 0.1.3
+Version: 0.1.5
 Summary: Boltz for VSYNTHES
 Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown