rcsb-embedding-model 0.0.32__tar.gz → 0.0.34__tar.gz

{rcsb_embedding_model-0.0.32 → rcsb_embedding_model-0.0.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rcsb-embedding-model
-Version: 0.0.32
+Version: 0.0.34
 Summary: Protein Embedding Model for Structure Search
 Project-URL: Homepage, https://github.com/rcsb/rcsb-embedding-model
 Project-URL: Issues, https://github.com/rcsb/rcsb-embedding-model/issues

{rcsb_embedding_model-0.0.32 → rcsb_embedding_model-0.0.34}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "rcsb-embedding-model"
-version = "0.0.32"
+version = "0.0.34"
 authors = [
     { name="Joan Segura", email="joan.segura@rcsb.org" },
 ]

{rcsb_embedding_model-0.0.32 → rcsb_embedding_model-0.0.34}/src/rcsb_embedding_model/dataset/esm_prot_from_chain.py

@@ -11,7 +11,7 @@ import pandas as pd
 
 from rcsb_embedding_model.types.api_types import StructureFormat, StructureLocation, SrcLocation
 from rcsb_embedding_model.utils.data import stringio_from_url
-from rcsb_embedding_model.utils.structure_parser import rename_atom_ch, check_all_hetero, remove_hetero
+from rcsb_embedding_model.utils.structure_parser import rename_atom_attr,filter_residues
 from rcsb_embedding_model.utils.structure_provider import StructureProvider
 
 
@@ -72,13 +72,17 @@ class EsmProtFromChain(Dataset):
         for atom_ch in chain_iter(structure):
             if len(atom_ch) == 0:
                 raise IOError(f"No atoms were found in structure chain {src_name}.{chain_id}")
-            if check_all_hetero(atom_ch):
-                atom_ch = remove_hetero(atom_ch)
-            atom_ch = rename_atom_ch(atom_ch)
-            protein_chain = ProteinChain.from_atomarray(atom_ch)
-            protein_chain = ESMProtein.from_protein_chain(protein_chain)
+            atom_ch = filter_residues(atom_ch)
+            atom_ch = rename_atom_attr(atom_ch)
+            try:
+                protein_chain = ProteinChain.from_atomarray(atom_ch)
+                protein_chain = ESMProtein.from_protein_chain(protein_chain)
+            except Exception as e:
+                raise IOError(f"Error while creating ESMProtein from structure chain {src_name}.{chain_id}: {e}")
+
             if len(protein_chain) == 0:
                 raise IOError(f"No atoms were found in structure chain {src_name}.{chain_id}")
+
             return protein_chain, item_name
         raise IOError(f"No atoms were found in structure chain {src_name}.{chain_id}")
 

{rcsb_embedding_model-0.0.32 → rcsb_embedding_model-0.0.34}/src/rcsb_embedding_model/utils/data.py

@@ -4,6 +4,7 @@ import gzip
 from io import StringIO, BytesIO
 
 import torch
+from requests import RequestException
 
 
 def collate_seq_embeddings(batch_list):
@@ -52,13 +53,10 @@ def stringio_from_url(url):
                 return StringIO(f.read())
         else:
             return StringIO(response.text)
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching URL: {e}")
-        return None
+    except RequestException as e:
+        raise RuntimeError(f"Error fetching URL: {e}")
     except (OSError, gzip.BadGzipFile) as e:
-        print(f"Error decompressing gzip file: {e}")
-        return None
-
+        raise RuntimeError(f"Error decompressing gzip file: {e}")
 
 
 def concatenate_tensors(file_list, max_residues, dim=0):

rcsb_embedding_model-0.0.34/src/rcsb_embedding_model/utils/structure_parser.py

@@ -0,0 +1,100 @@
+import numpy as np
+from biotite.structure import filter_amino_acids, filter_polymer, chain_iter, get_chains, get_residues, \
+    filter_peptide_backbone, residue_iter, array
+from biotite.structure.io.pdb import PDBFile, get_structure as get_pdb_structure, get_assembly as get_pdb_assembly, list_assemblies as list_pdb_assemblies
+from biotite.structure.io.pdbx import CIFFile, get_structure, get_assembly, BinaryCIFFile, list_assemblies
+
+
+def get_structure_from_src(
+        src_structure,
+        structure_format="mmcif",
+        chain_id=None,
+        assembly_id=None
+):
+    try:
+        if structure_format == "pdb":
+            pdb_file = PDBFile.read(src_structure)
+            structure = __get_pdb_structure(pdb_file, assembly_id)
+        elif structure_format == "mmcif":
+            cif_file = CIFFile.read(src_structure)
+            structure = __get_structure(cif_file, assembly_id)
+        elif structure_format == "binarycif":
+            cif_file = BinaryCIFFile.read(src_structure)
+            structure = __get_structure(cif_file, assembly_id)
+        else:
+            raise RuntimeError(f"Unknown file format {structure_format}")
+    except Exception as e:
+        raise RuntimeError(f"Error reading structure from {src_structure}: {e}")
+
+    if chain_id is not None:
+        return structure[structure.chain_id == chain_id]
+
+    return structure
+
+
+def get_protein_chains(structure, min_res_n=0):
+    chain_ids = []
+    for atom_ch in chain_iter(structure):
+        atom_res = atom_ch[filter_polymer(atom_ch)]
+        atom_res = atom_res[filter_amino_acids(atom_res)]
+        if len(atom_res) > 0 and len(get_residues(atom_res)[0]) > min_res_n:
+            chain_ids.append(str(get_chains(atom_res)[0]))
+    return tuple(chain_ids)
+
+
+def get_assemblies(structure, structure_format="mmcif"):
+    try:
+        if structure_format == "pdb":
+            return tuple(list_pdb_assemblies(PDBFile.read(structure)))
+        elif structure_format == "mmcif":
+            return tuple(list_assemblies(CIFFile.read(structure)).keys())
+        elif structure_format == "binarycif":
+            return tuple(list_assemblies(BinaryCIFFile.read(structure)))
+        else:
+            raise RuntimeError(f"Unknown file format {structure_format}")
+    except Exception as e:
+        raise RuntimeError(f"Error reading assemblies from {structure}: {e}")
+
+
+def rename_atom_attr(atom_ch):
+    return array([__rename_atom(a) for a in atom_ch])
+
+
+def filter_residues(atom_ch):
+    return atom_ch[filter_amino_acids(atom_ch)]
+
+
+def get_backbone_atoms(atom_ch):
+    return np.array([(lambda x: [a.coord for a in x])(r) for r in  residue_iter(atom_ch[filter_peptide_backbone(atom_ch)])])
+
+
+def __get_pdb_structure(pdb_file, assembly_id=None):
+    return get_pdb_structure(
+        pdb_file,
+        model=1
+    ) if assembly_id is None else get_pdb_assembly(
+        pdb_file,
+        assembly_id=assembly_id,
+        model=1
+    )
+
+
+def __rename_atom(atom):
+    atom.chain_id = "A"
+    atom.hetero = False
+    if len(atom.res_name) > 3:
+        atom.res_name = 'UNK'
+    return atom
+
+
+def __get_structure(cif_file, assembly_id=None):
+    return get_structure(
+        cif_file,
+        model=1,
+        use_author_fields=False
+    ) if assembly_id is None else get_assembly(
+        cif_file,
+        assembly_id=assembly_id,
+        model=1,
+        use_author_fields=False
+    )

rcsb_embedding_model-0.0.32/src/rcsb_embedding_model/utils/structure_parser.py

@@ -1,92 +0,0 @@
-from biotite.structure import filter_amino_acids, filter_polymer, chain_iter, get_chains, get_residues, AtomArray
-from biotite.structure.io.pdb import PDBFile, get_structure as get_pdb_structure, get_assembly as get_pdb_assembly, list_assemblies as list_pdb_assemblies
-from biotite.structure.io.pdbx import CIFFile, get_structure, get_assembly, BinaryCIFFile, list_assemblies
-
-
-def get_structure_from_src(
-        src_structure,
-        structure_format="mmcif",
-        chain_id=None,
-        assembly_id=None
-):
-    if structure_format == "pdb":
-        pdb_file = PDBFile.read(src_structure)
-        structure = __get_pdb_structure(pdb_file, assembly_id)
-    elif structure_format == "mmcif":
-        cif_file = CIFFile.read(src_structure)
-        structure = __get_structure(cif_file, assembly_id)
-    elif structure_format == "binarycif":
-        cif_file = BinaryCIFFile.read(src_structure)
-        structure = __get_structure(cif_file, assembly_id)
-    else:
-        raise RuntimeError(f"Unknown file format {structure_format}")
-
-    if chain_id is not None:
-        return structure[structure.chain_id == chain_id]
-
-    return structure
-
-
-def get_protein_chains(structure, min_res_n=0):
-    chain_ids = []
-    for atom_ch in chain_iter(structure):
-        atom_res = atom_ch[filter_polymer(atom_ch)]
-        atom_res = atom_res[filter_amino_acids(atom_res)]
-        if len(atom_res) > 0 and len(get_residues(atom_res)[0]) > min_res_n:
-            chain_ids.append(str(get_chains(atom_res)[0]))
-    return tuple(chain_ids)
-
-
-def get_assemblies(structure, structure_format="mmcif"):
-    if structure_format == "pdb":
-        return tuple(list_pdb_assemblies(PDBFile.read(structure)))
-    elif structure_format == "mmcif":
-        return tuple(list_assemblies(CIFFile.read(structure)).keys())
-    elif structure_format == "binarycif":
-        return tuple(list_assemblies(BinaryCIFFile.read(structure)))
-    else:
-        raise RuntimeError(f"Unknown file format {structure_format}")
-
-
-def rename_atom_ch(atom_ch, ch="A"):
-    renamed_atom_ch = AtomArray(len(atom_ch))
-    for idx, atom in enumerate(atom_ch):
-        atom.chain_id = ch
-        renamed_atom_ch[idx] = atom
-    return renamed_atom_ch
-
-
-def remove_hetero(atom_ch):
-    renamed_atom_ch = AtomArray(len(atom_ch))
-    for idx, atom in enumerate(atom_ch):
-        atom.hetero = False
-        renamed_atom_ch[idx] = atom
-    return renamed_atom_ch
-
-
-def check_all_hetero(atom_ch):
-    return sum(atom_ch.hetero) == len(atom_ch)
-
-
-def __get_pdb_structure(pdb_file, assembly_id=None):
-    return get_pdb_structure(
-        pdb_file,
-        model=1
-    ) if assembly_id is None else get_pdb_assembly(
-        pdb_file,
-        assembly_id=assembly_id,
-        model=1
-    )
-
-
-def __get_structure(cif_file, assembly_id=None):
-    return get_structure(
-        cif_file,
-        model=1,
-        use_author_fields=False
-    ) if assembly_id is None else get_assembly(
-        cif_file,
-        assembly_id=assembly_id,
-        model=1,
-        use_author_fields=False
-    )