boltz-vsynthes 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

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/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.dist-info → boltz_vsynthes-0.1.5.dist-info}/METADATA

@@ -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.dist-info → boltz_vsynthes-0.1.5.dist-info}/RECORD

@@ -38,8 +38,8 @@ boltz/data/parse/csv.py,sha256=Hcq8rJW2njczahEr8jfd_o-zxLaNSgJ3YIoC9srIqpw,2518
 boltz/data/parse/fasta.py,sha256=taI4s_CqPtyF0XaLJAsVAJHCL0GXm2g1g8Qeccdxikk,3906
 boltz/data/parse/mmcif.py,sha256=25kEXCkx-OuaawAs7cdz0fxdRu5_CCO0AV00u84PrjQ,36822
 boltz/data/parse/mmcif_with_constraints.py,sha256=WHYZckSqUwu-Nb9vmVmxHmC7uxwVrF7AVUeVKsc5wGQ,51473
-boltz/data/parse/pdb.py,sha256=iybk4p2UgUy_ABGprDq_xxyPSdm1HAZsGTM0lhxVEwM,1654
-boltz/data/parse/pdb_download.py,sha256=wge-scX-lOatX0q83W1wOsaql99rYp-6uGWSHEc995M,2718
+boltz/data/parse/pdb.py,sha256=jHTZKGmq4fNZrol1qhHvelpuFjbItqbJJuBA2mdr2ao,1893
+boltz/data/parse/pdb_download.py,sha256=F-ySQzG7Upu8_qAUpkbihVszLjZdGmKnKzxoFdvC1I4,2937
 boltz/data/parse/schema.py,sha256=kNu28U2_MGiecwWNlcxgaDH3WOcO0P-q2LdoSPSb66w,63826
 boltz/data/parse/sdf.py,sha256=fs3MQVClDcCzxJaeVYiDuoh-fUrYc8Tcd5Bz8ws3FKI,2052
 boltz/data/parse/yaml.py,sha256=GRFRMtDD4PQ4PIpA_S1jj0vRaEu2LlZd_g4rN1zUrNo,1505
@@ -110,9 +110,9 @@ boltz/model/potentials/schedules.py,sha256=m7XJjfuF9uTX3bR9VisXv1rvzJjxiD8PobXRp
 boltz/utils/sdf_splitter.py,sha256=ZHn_syOcmm-fDnJ3YEGyGv_vYz2IRzUW7vbbMSU2JBY,2108
 boltz/utils/sdf_to_pre_affinity_npz.py,sha256=ro0KGe24JexbJm47J8S8w8Lmr_KaQbzOAb_dKZO2G9I,40384
 boltz/utils/yaml_generator.py,sha256=ermWIG-BE6nNWHFvpEwpk92N9J-YATpGXZGLvD1I2oQ,4012
-boltz_vsynthes-0.1.3.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
-boltz_vsynthes-0.1.3.dist-info/METADATA,sha256=HBpb17_3dujv6tXG1SdhhsMBMckGUhJ8ZDT6ou_G06Y,7234
-boltz_vsynthes-0.1.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-boltz_vsynthes-0.1.3.dist-info/entry_points.txt,sha256=nZNYPKKrmAr-MVA0K-ClNRT2p90FV1_14d7HpsESZFQ,211
-boltz_vsynthes-0.1.3.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
-boltz_vsynthes-0.1.3.dist-info/RECORD,,
+boltz_vsynthes-0.1.5.dist-info/licenses/LICENSE,sha256=8GZ_1eZsUeG6jdqgJJxtciWzADfgLEV4LY8sKUOsJhc,1102
+boltz_vsynthes-0.1.5.dist-info/METADATA,sha256=TeZDNsVLslOB7cazrlq-FRaDOHB8rLNCj7hlo73a9GU,7234
+boltz_vsynthes-0.1.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+boltz_vsynthes-0.1.5.dist-info/entry_points.txt,sha256=nZNYPKKrmAr-MVA0K-ClNRT2p90FV1_14d7HpsESZFQ,211
+boltz_vsynthes-0.1.5.dist-info/top_level.txt,sha256=MgU3Jfb-ctWm07YGMts68PMjSh9v26D0gfG3dFRmVFA,6
+boltz_vsynthes-0.1.5.dist-info/RECORD,,