rcsb-embedding-model 0.0.35__py3-none-any.whl → 0.0.36__py3-none-any.whl

rcsb_embedding_model/cli/inference.py

@@ -6,7 +6,7 @@ import typer
 from rcsb_embedding_model import __version__
 from rcsb_embedding_model.cli.args_utils import arg_devices
 from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, SrcLocation, SrcProteinFrom, \
-    StructureLocation, SrcAssemblyFrom, SrcTensorFrom, OutFormat
+    SrcAssemblyFrom, SrcTensorFrom, OutFormat
 from rcsb_embedding_model.utils.data import adapt_csv_to_embedding_chain_stream
 
 import os
@@ -42,9 +42,6 @@ def residue_embedding(
         output_name: Annotated[str, typer.Option(
             help='File name for storing embeddings as a single JSON file. Used when output-format=grouped.'
         )] = 'inference',
-        structure_location: Annotated[StructureLocation, typer.Option(
-            help='Structure file location.'
-        )] = StructureLocation.local,
         structure_format: Annotated[StructureFormat, typer.Option(
             help='Structure file format.'
         )] = StructureFormat.mmcif,
@@ -72,7 +69,6 @@ def residue_embedding(
         src_stream=src_file,
         src_location=SrcLocation.file,
         src_from=SrcProteinFrom.chain,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size,
@@ -108,9 +104,6 @@ def structure_embedding(
         output_name: Annotated[str, typer.Option(
             help='File name for storing embeddings as a single JSON file.'
         )] = 'inference',
-        structure_location: Annotated[StructureLocation, typer.Option(
-            help='Structure file location.'
-        )] = StructureLocation.local,
         structure_format: Annotated[StructureFormat, typer.Option(
             help='Structure file format.'
         )] = StructureFormat.mmcif,
@@ -138,7 +131,6 @@ def structure_embedding(
         src_stream=src_file,
         src_location=SrcLocation.file,
         src_from=SrcProteinFrom.chain,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size,
@@ -183,9 +175,6 @@ def chain_embedding(
         output_name: Annotated[str, typer.Option(
             help='File name for storing embeddings as a single JSON file. Used when output-format=grouped.'
         )] = 'inference',
-        structure_location: Annotated[StructureLocation, typer.Option(
-            help='Structure file location.'
-        )] = StructureLocation.local,
         structure_format: Annotated[StructureFormat, typer.Option(
             help='Structure file format.'
         )] = StructureFormat.mmcif,
@@ -214,7 +203,6 @@ def chain_embedding(
         res_embedding_location=res_embedding_location,
         src_location=SrcLocation.stream,
         src_from=SrcTensorFrom.file,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size,
@@ -259,9 +247,6 @@ def assembly_embedding(
         output_name: Annotated[str, typer.Option(
             help='File name for storing embeddings as a single JSON file. Used when output-format=grouped.'
         )] = 'inference',
-        structure_location: Annotated[StructureLocation, typer.Option(
-            help='Structure file location.'
-        )] = StructureLocation.local,
         structure_format: Annotated[StructureFormat, typer.Option(
             help='Structure file format.'
         )] = StructureFormat.mmcif,
@@ -293,7 +278,6 @@ def assembly_embedding(
         res_embedding_location=res_embedding_location,
         src_location=SrcLocation.file,
         src_from=SrcAssemblyFrom.assembly,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         max_res_n=max_res_n,
@@ -356,9 +340,6 @@ def complete_embedding(
         output_assembly_name: Annotated[str, typer.Option(
             help='File name for storing chain embeddings as a single JSON file. Used when output-format=grouped.'
         )] = 'chain-inference',
-        structure_location: Annotated[StructureLocation, typer.Option(
-            help='Structure file location.'
-        )] = StructureLocation.local,
         structure_format: Annotated[StructureFormat, typer.Option(
             help='Structure file format.'
         )] = StructureFormat.mmcif,
@@ -397,7 +378,6 @@ def complete_embedding(
         src_file=src_chain_file,
         output_path=output_res_path,
         output_format=OutFormat.separated,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size_res,
@@ -412,7 +392,6 @@ def complete_embedding(
         output_format=output_format,
         output_name=output_chain_name,
         res_embedding_location=output_res_path,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size_chain,
@@ -427,7 +406,6 @@ def complete_embedding(
         output_format=output_format,
         output_name=output_assembly_name,
         res_embedding_location=output_res_path,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         batch_size=batch_size_assembly,

rcsb_embedding_model/dataset/esm_prot_from_chain.py

@@ -9,6 +9,7 @@ from esm.utils.structure.protein_chain import ProteinChain
 from torch.utils.data import Dataset, DataLoader
 import pandas as pd
 
+from rcsb_embedding_model.dataset.untils import get_structure_location
 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_attr,filter_residues
@@ -28,14 +29,12 @@ class EsmProtFromChain(Dataset):
         self,
         src_stream,
         src_location=SrcLocation.file,
-        structure_location=StructureLocation.local,
         structure_format=StructureFormat.mmcif,
         structure_provider=StructureProvider()
     ):
         super().__init__()
         self.__structure_provider = structure_provider
         self.src_location = src_location
-        self.structure_location = structure_location
         self.structure_format = structure_format
         self.data = pd.DataFrame()
         self.__load_stream(src_stream)
@@ -65,7 +64,7 @@ class EsmProtFromChain(Dataset):
         item_name = self.data.iloc[idx][EsmProtFromChain.ITEM_NAME_ATTR]
         structure = self.__structure_provider.get_structure(
             src_name=src_name,
-            src_structure=stringio_from_url(src_structure) if self.structure_location == StructureLocation.remote else src_structure,
+            src_structure=stringio_from_url(src_structure) if get_structure_location(src_structure) == StructureLocation.remote else src_structure,
             structure_format=self.structure_format,
             chain_id=chain_id
         )
@@ -96,7 +95,6 @@ if __name__ == '__main__':
     dataset = EsmProtFromChain(
         src_stream=args.file_list,
         src_location=SrcLocation.file,
-        structure_location=StructureLocation.remote,
         structure_format=StructureFormat.bciff,
     )
 

rcsb_embedding_model/dataset/esm_prot_from_structure.py

@@ -2,6 +2,7 @@
 import pandas as pd
 
 from rcsb_embedding_model.dataset.esm_prot_from_chain import EsmProtFromChain
+from rcsb_embedding_model.dataset.untils import get_structure_location
 from rcsb_embedding_model.types.api_types import StructureLocation, StructureFormat, SrcLocation
 from rcsb_embedding_model.utils.data import stringio_from_url
 from rcsb_embedding_model.utils.structure_parser import get_protein_chains
@@ -20,20 +21,17 @@ class EsmProtFromStructure(EsmProtFromChain):
             self,
             src_stream,
             src_location=SrcLocation.file,
-            structure_location=StructureLocation.local,
             structure_format=StructureFormat.mmcif,
             min_res_n=0,
             structure_provider=StructureProvider()
     ):
         self.min_res_n = min_res_n
         self.src_location = src_location
-        self.structure_location = structure_location
         self.structure_format = structure_format
         self.__structure_provider = structure_provider
         super().__init__(
             src_stream=self.__get_chains(src_stream),
             src_location=SrcLocation.stream,
-            structure_location=structure_location,
             structure_format=structure_format,
             structure_provider=structure_provider
         )
@@ -58,7 +56,7 @@ class EsmProtFromStructure(EsmProtFromChain):
             item_name = row[EsmProtFromStructure.ITEM_NAME_ATTR]
             structure = self.__structure_provider.get_structure(
                 src_name=src_name,
-                src_structure=stringio_from_url(src_structure) if self.structure_location == StructureLocation.remote else src_structure,
+                src_structure=stringio_from_url(src_structure) if get_structure_location(src_structure) == StructureLocation.remote else src_structure,
                 structure_format=self.structure_format
             )
             for ch in get_protein_chains(structure, self.min_res_n):

rcsb_embedding_model/dataset/resdiue_assembly_embedding_from_structure.py

@@ -3,6 +3,7 @@ import sys
 import pandas as pd
 
 from rcsb_embedding_model.dataset.residue_assembly_embedding_from_tensor_file import ResidueAssemblyEmbeddingFromTensorFile
+from rcsb_embedding_model.dataset.untils import get_structure_location
 from rcsb_embedding_model.types.api_types import SrcLocation, StructureLocation, StructureFormat
 from rcsb_embedding_model.utils.data import stringio_from_url
 from rcsb_embedding_model.utils.structure_parser import get_assemblies
@@ -22,14 +23,12 @@ class ResidueAssemblyDatasetFromStructure(ResidueAssemblyEmbeddingFromTensorFile
             src_stream,
             res_embedding_location,
             src_location=SrcLocation.file,
-            structure_location=StructureLocation.local,
             structure_format=StructureFormat.mmcif,
             min_res_n=0,
             max_res_n=sys.maxsize,
             structure_provider=StructureProvider()
     ):
         self.src_location = src_location
-        self.structure_location = structure_location
         self.structure_format = structure_format
         self.min_res_n = min_res_n
         self.max_res_n = max_res_n
@@ -37,7 +36,6 @@ class ResidueAssemblyDatasetFromStructure(ResidueAssemblyEmbeddingFromTensorFile
             src_stream=self.__get_assemblies(src_stream),
             res_embedding_location=res_embedding_location,
             src_location=SrcLocation.stream,
-            structure_location=structure_location,
             structure_format=structure_format,
             min_res_n=min_res_n,
             max_res_n=max_res_n,
@@ -61,7 +59,7 @@ class ResidueAssemblyDatasetFromStructure(ResidueAssemblyEmbeddingFromTensorFile
         for idx, row in data.iterrows():
             src_name = row[ResidueAssemblyDatasetFromStructure.STREAM_NAME_ATTR]
             src_structure = row[ResidueAssemblyDatasetFromStructure.STREAM_ATTR]
-            structure = stringio_from_url(src_structure) if self.structure_location == StructureLocation.remote else src_structure
+            structure = stringio_from_url(src_structure) if get_structure_location(src_structure) == StructureLocation.remote else src_structure
             item_name = row[ResidueAssemblyDatasetFromStructure.ITEM_NAME_ATTR]
             for assembly_id in get_assemblies(structure=structure, structure_format=self.structure_format):
                 assemblies.append((src_name, src_structure, str(assembly_id), f"{item_name}-{assembly_id}"))

rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py

@@ -4,6 +4,7 @@ import sys
 import pandas as pd
 from torch.utils.data import Dataset, DataLoader
 
+from rcsb_embedding_model.dataset.untils import get_structure_location
 from rcsb_embedding_model.types.api_types import StructureLocation, StructureFormat, SrcLocation
 from rcsb_embedding_model.utils.data import stringio_from_url, concatenate_tensors
 from rcsb_embedding_model.utils.structure_parser import get_protein_chains
@@ -24,7 +25,6 @@ class ResidueAssemblyEmbeddingFromTensorFile(Dataset):
             src_stream,
             res_embedding_location,
             src_location=SrcLocation.file,
-            structure_location=StructureLocation.local,
             structure_format=StructureFormat.mmcif,
             min_res_n=0,
             max_res_n=sys.maxsize,
@@ -33,7 +33,6 @@ class ResidueAssemblyEmbeddingFromTensorFile(Dataset):
         super().__init__()
         self.res_embedding_location = res_embedding_location
         self.src_location = src_location
-        self.structure_location = structure_location
         self.structure_format = structure_format
         self.min_res_n = min_res_n
         self.max_res_n = max_res_n
@@ -65,7 +64,7 @@ class ResidueAssemblyEmbeddingFromTensorFile(Dataset):
         item_name = self.data.iloc[idx][ResidueAssemblyEmbeddingFromTensorFile.ITEM_NAME_ATTR]
         structure = self.__structure_provider.get_structure(
             src_name=src_name,
-            src_structure=stringio_from_url(src_structure) if self.structure_location == StructureLocation.remote else src_structure,
+            src_structure=stringio_from_url(src_structure) if get_structure_location(src_structure) == StructureLocation.remote else src_structure,
             structure_format=self.structure_format,
             assembly_id=assembly_id
         )
@@ -86,7 +85,6 @@ if __name__ == "__main__":
         src_stream=args.file_list,
         res_embedding_location=args.res_embeddings_path,
         src_location=SrcLocation.file,
-        structure_location=StructureLocation.remote,
         structure_format=StructureFormat.bciff
     )
 

rcsb_embedding_model/dataset/residue_embedding_from_structure.py

@@ -3,6 +3,7 @@ import os
 import pandas as pd
 
 from rcsb_embedding_model.dataset.residue_embedding_from_tensor_file import ResidueEmbeddingFromTensorFile
+from rcsb_embedding_model.dataset.untils import get_structure_location
 from rcsb_embedding_model.types.api_types import SrcLocation, StructureLocation, StructureFormat
 from rcsb_embedding_model.utils.data import stringio_from_url
 from rcsb_embedding_model.utils.structure_parser import get_protein_chains
@@ -22,7 +23,6 @@ class ResidueEmbeddingFromStructure(ResidueEmbeddingFromTensorFile):
             src_stream,
             res_embedding_location,
             src_location=SrcLocation.file,
-            structure_location=StructureLocation.local,
             structure_format=StructureFormat.mmcif,
             min_res_n=0,
             structure_provider=StructureProvider()
@@ -31,7 +31,6 @@ class ResidueEmbeddingFromStructure(ResidueEmbeddingFromTensorFile):
             raise FileNotFoundError(f"Folder {res_embedding_location} does not exist")
         self.res_embedding_location = res_embedding_location
         self.src_location = src_location
-        self.structure_location = structure_location
         self.structure_format = structure_format
         self.min_res_n = min_res_n
         self.__structure_provider = structure_provider
@@ -60,7 +59,7 @@ class ResidueEmbeddingFromStructure(ResidueEmbeddingFromTensorFile):
             item_name = row[ResidueEmbeddingFromStructure.ITEM_NAME_ATTR]
             structure = self.__structure_provider.get_structure(
                 src_name=src_name,
-                src_structure=stringio_from_url(src_structure) if self.structure_location == StructureLocation.remote else src_structure,
+                src_structure=stringio_from_url(src_structure) if get_structure_location(src_structure) == StructureLocation.remote else src_structure,
                 structure_format=self.structure_format
             )
             for ch in get_protein_chains(structure, self.min_res_n):

rcsb_embedding_model/dataset/untils/__init__.py

@@ -0,0 +1,4 @@
+
+from rcsb_embedding_model.dataset.untils.utils import get_structure_location
+
+__all__ = ["get_structure_location"]

rcsb_embedding_model/dataset/untils/utils.py

@@ -0,0 +1,17 @@
+import os
+from urllib.parse import urlparse
+from rcsb_embedding_model.types.api_types import StructureLocation
+
+
+def get_structure_location(s: str) -> str:
+    # First, attempt to parse as URL
+    parsed = urlparse(s)
+    if parsed.scheme.lower() in {'http', 'https', 'ftp'} and parsed.netloc:
+        return StructureLocation.remote
+
+    # Next, test for an existing file or directory
+    if os.path.exists(s):
+        return StructureLocation.local
+
+    # Neither URL nor existing file
+    raise ValueError(f"Structure file source is neither a recognized URL nor file: {s!r}")

rcsb_embedding_model/inference/assembly_inferece.py

@@ -3,7 +3,7 @@ import sys
 from rcsb_embedding_model.dataset.resdiue_assembly_embedding_from_structure import ResidueAssemblyDatasetFromStructure
 from rcsb_embedding_model.dataset.residue_assembly_embedding_from_tensor_file import ResidueAssemblyEmbeddingFromTensorFile
 from rcsb_embedding_model.types.api_types import FileOrStreamTuple, SrcLocation, Accelerator, Devices, OptionalPath, \
-    EmbeddingPath, StructureLocation, StructureFormat, SrcAssemblyFrom, OutFormat
+    EmbeddingPath, StructureFormat, SrcAssemblyFrom, OutFormat
 from rcsb_embedding_model.inference.chain_inference import predict as chain_predict
 
 
@@ -12,7 +12,6 @@ def predict(
         res_embedding_location: EmbeddingPath,
         src_location: SrcLocation = SrcLocation.file,
         src_from: SrcAssemblyFrom = SrcAssemblyFrom.assembly,
-        structure_location: StructureLocation = StructureLocation.local,
         structure_format: StructureFormat = StructureFormat.mmcif,
         min_res_n: int = 0,
         max_res_n: int = sys.maxsize,
@@ -29,7 +28,6 @@ def predict(
         src_stream=src_stream,
         res_embedding_location=res_embedding_location,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         max_res_n=max_res_n
@@ -37,7 +35,6 @@ def predict(
         src_stream=src_stream,
         res_embedding_location=res_embedding_location,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n,
         max_res_n=max_res_n

rcsb_embedding_model/inference/chain_inference.py

@@ -6,7 +6,7 @@ from rcsb_embedding_model.dataset.residue_embedding_from_structure import Residu
 from rcsb_embedding_model.dataset.residue_embedding_from_tensor_file import ResidueEmbeddingFromTensorFile
 from rcsb_embedding_model.modules.chain_module import ChainModule
 from rcsb_embedding_model.types.api_types import Accelerator, Devices, OptionalPath, FileOrStreamTuple, SrcLocation, \
-    SrcTensorFrom, StructureLocation, StructureFormat, OutFormat
+    SrcTensorFrom, StructureFormat, OutFormat
 from rcsb_embedding_model.utils.data import collate_seq_embeddings
 from rcsb_embedding_model.utils.model import get_aggregator_model
 from rcsb_embedding_model.writer.batch_writer import CsvBatchWriter, JsonStorage
@@ -17,7 +17,6 @@ def predict(
         res_embedding_location: OptionalPath = None,
         src_location: SrcLocation = SrcLocation.file,
         src_from: SrcTensorFrom = SrcTensorFrom.file,
-        structure_location: StructureLocation = StructureLocation.local,
         structure_format: StructureFormat = StructureFormat.mmcif,
         min_res_n: int = 0,
         batch_size: int = 1,
@@ -39,7 +38,6 @@ def predict(
             src_stream=src_stream,
             res_embedding_location=res_embedding_location,
             src_location=src_location,
-            structure_location=structure_location,
             structure_format=structure_format,
             min_res_n=min_res_n
         )

rcsb_embedding_model/inference/esm_inference.py

@@ -5,7 +5,7 @@ from lightning import Trainer
 from rcsb_embedding_model.dataset.esm_prot_from_structure import EsmProtFromStructure
 from rcsb_embedding_model.dataset.esm_prot_from_chain import EsmProtFromChain
 from rcsb_embedding_model.modules.esm_module import EsmModule
-from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, Devices, OptionalPath, StructureLocation, \
+from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, Devices, OptionalPath, \
     SrcProteinFrom, FileOrStreamTuple, SrcLocation, OutFormat
 from rcsb_embedding_model.utils.model import get_residue_model
 from rcsb_embedding_model.writer.batch_writer import TensorBatchWriter, JsonStorage
@@ -15,7 +15,6 @@ def predict(
         src_stream: FileOrStreamTuple,
         src_location: SrcLocation = SrcLocation.file,
         src_from: SrcProteinFrom = SrcProteinFrom.chain,
-        structure_location: StructureLocation = StructureLocation.local,
         structure_format: StructureFormat = StructureFormat.mmcif,
         min_res_n: int = 0,
         batch_size: int = 1,
@@ -31,12 +30,10 @@ def predict(
     inference_set = EsmProtFromChain(
         src_stream=src_stream,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format
     ) if src_from == SrcProteinFrom.chain else EsmProtFromStructure(
         src_stream=src_stream,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n
     )

rcsb_embedding_model/inference/structure_inference.py

@@ -5,7 +5,7 @@ from lightning import Trainer
 from rcsb_embedding_model.dataset.esm_prot_from_structure import EsmProtFromStructure
 from rcsb_embedding_model.dataset.esm_prot_from_chain import EsmProtFromChain
 from rcsb_embedding_model.modules.structure_module import StructureModule
-from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, Devices, OptionalPath, StructureLocation, \
+from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, Devices, OptionalPath, \
     SrcProteinFrom, FileOrStreamTuple, SrcLocation
 from rcsb_embedding_model.utils.model import get_residue_model, get_aggregator_model
 from rcsb_embedding_model.writer.batch_writer import JsonStorage
@@ -15,7 +15,6 @@ def predict(
         src_stream: FileOrStreamTuple,
         src_location: SrcLocation = SrcLocation.file,
         src_from: SrcProteinFrom = SrcProteinFrom.chain,
-        structure_location: StructureLocation = StructureLocation.local,
         structure_format: StructureFormat = StructureFormat.mmcif,
         min_res_n: int = 0,
         batch_size: int = 1,
@@ -30,12 +29,10 @@ def predict(
     inference_set = EsmProtFromChain(
         src_stream=src_stream,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format
     ) if src_from == SrcProteinFrom.chain else EsmProtFromStructure(
         src_stream=src_stream,
         src_location=src_location,
-        structure_location=structure_location,
         structure_format=structure_format,
         min_res_n=min_res_n
     )

{rcsb_embedding_model-0.0.35.dist-info → rcsb_embedding_model-0.0.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rcsb-embedding-model
-Version: 0.0.35
+Version: 0.0.36
 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-0.0.35.dist-info → rcsb_embedding_model-0.0.36.dist-info}/RECORD

@@ -1,17 +1,19 @@
 rcsb_embedding_model/__init__.py,sha256=7YfYO-V-u__19eAZfQ3t5Gf2qrhd_gwQB8rHO0J0puw,306
 rcsb_embedding_model/rcsb_structure_embedding.py,sha256=dKp9hXQO0JAnO4SEfjJ_mG_jHu3UxAPguv6jkOjp-BI,4487
 rcsb_embedding_model/cli/args_utils.py,sha256=7nP2q8pL5dWK_U7opxtWmoFcYVwasky6elHk-dASFaI,165
-rcsb_embedding_model/cli/inference.py,sha256=67_Tr3LWeA3T4KS5mkjq6tw77Ypy0R8IwMxEG2FwVqQ,19901
-rcsb_embedding_model/dataset/esm_prot_from_chain.py,sha256=sLbBapgchxciq4RgwHkw9yoNokGlOv2Z5PSaiWV5G64,4418
-rcsb_embedding_model/dataset/esm_prot_from_structure.py,sha256=3HzXCCc-UqmZNbJaeXHyUsSIZZxMc2erbxAPGIxSmfE,2621
-rcsb_embedding_model/dataset/resdiue_assembly_embedding_from_structure.py,sha256=69h1VkrIXesHZi1cG3BOMMytSDeRzcBBP0_Z3Xz3dM8,2869
-rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py,sha256=Hd9oH-IVgY6d7Dxy5VfiwHvSaK-Wwhk6ccUBgOwl0TU,3740
-rcsb_embedding_model/dataset/residue_embedding_from_structure.py,sha256=1jmeEcCK41cAi2ZnqQkd667NWCAIGS3k6jGDF-WxtTk,2854
+rcsb_embedding_model/cli/inference.py,sha256=cXYaais4A3rVAkiucMdJxrYVxezKti8hL3DogBU0_2c,18788
+rcsb_embedding_model/dataset/esm_prot_from_chain.py,sha256=_DYWLDEc492nhUdFRAQjwh0romF9iMwydFNi43-r0TY,4345
+rcsb_embedding_model/dataset/esm_prot_from_structure.py,sha256=VU9BxNUApZ-pus_vmFGEU4eplcCH0fO7KBdic6X_NOM,2546
+rcsb_embedding_model/dataset/resdiue_assembly_embedding_from_structure.py,sha256=9iO7ZUcxl0TIBiwNieqjZFfnM7-7V3pl5abYiLzIY0I,2794
+rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py,sha256=6bMjb0hfNbrTOqstnUVHbegw0xeUo7s6INnRsvP7V3I,3663
+rcsb_embedding_model/dataset/residue_embedding_from_structure.py,sha256=tFHiXqGceZjAoYfVkeXG3sa2mz0gd5XBfm9EpJswcWI,2830
 rcsb_embedding_model/dataset/residue_embedding_from_tensor_file.py,sha256=4OPaw55yGKHjY2iPpCnemcfwfmTZ4j5VrGQ2oIMQw6A,1343
-rcsb_embedding_model/inference/assembly_inferece.py,sha256=8fPJjEXy1WsM5XB5U7KfdO5-Du6nEsawsaAjmWoXA9I,2329
-rcsb_embedding_model/inference/chain_inference.py,sha256=6f5wVzjtRtHU3BPMTe5k3nH_Nl440Am8BL8h1vmK1jI,2925
-rcsb_embedding_model/inference/esm_inference.py,sha256=rn6H43D8BYzMZbMu7UPsLYg2dgERmmpci5weNItrG5Q,2546
-rcsb_embedding_model/inference/structure_inference.py,sha256=0wqCW5wee_UQ8WJo9KG6SBHmosdNRzoJYEm7rMn4veA,2591
+rcsb_embedding_model/dataset/untils/__init__.py,sha256=O3WOukwvaKJvHUTALD3eYNHRacJo8o5BW7-ZulLZ65g,116
+rcsb_embedding_model/dataset/untils/utils.py,sha256=SPiQ9aO2WLictO4R2JiNlo2ChhlANNMeIhbN0kq11kQ,578
+rcsb_embedding_model/inference/assembly_inferece.py,sha256=b-mAfOJOO-s6gilOedZpaM90OTbhm_RQVqh2zKFG4dQ,2143
+rcsb_embedding_model/inference/chain_inference.py,sha256=0HkV4EnLwg4ttQhf-xwOuSksZwEYDEChnHU4_A0xUXM,2782
+rcsb_embedding_model/inference/esm_inference.py,sha256=nmHJYfSGjEqRPgb3l9s5fqtlyzdbAsiPz-OxHXBTgcI,2360
+rcsb_embedding_model/inference/structure_inference.py,sha256=b44mY7VcCbjbtB35Mi9EhZoM18yyMaF579MKmzwB564,2405
 rcsb_embedding_model/model/layers.py,sha256=lhKaWC4gTS_T5lHOP0mgnnP8nKTPEOm4MrjhESA4hE8,743
 rcsb_embedding_model/model/residue_embedding_aggregator.py,sha256=k3UW63Ax8DtjCMdD3O5xNxtyAu28l2n3-Ab6nS0atm0,1967
 rcsb_embedding_model/modules/chain_module.py,sha256=KsZw2uagO4rpAKWv6ivqEMxIEzgtfQFliHV_vX8kqtc,435
@@ -23,8 +25,8 @@ rcsb_embedding_model/utils/model.py,sha256=xr3p02ohOgJ5UInwdIupN68Oq4yvNFhxobZRa
 rcsb_embedding_model/utils/structure_parser.py,sha256=fSIbq_a_aEigCWY_1dUcW9d9Law0ZDOcZAxJlZL0Rt8,3377
 rcsb_embedding_model/utils/structure_provider.py,sha256=eWtxjkPpmRfmil_DKR1J6miaXR3lQ28DF5O0qrqSgGA,786
 rcsb_embedding_model/writer/batch_writer.py,sha256=rTFNasB0Xp4-XCNTXKeEWZxSrb7lvZytoRldJUWn9Jg,3312
-rcsb_embedding_model-0.0.35.dist-info/METADATA,sha256=h5uREe5bIKpY4o-ZUzXF9tObRb_eewm9GJ44vgijdig,5351
-rcsb_embedding_model-0.0.35.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-rcsb_embedding_model-0.0.35.dist-info/entry_points.txt,sha256=MK11jTIEmaV-x4CkPX5IymDaVs7Ky_f2xxU8BJVZ_9Q,69
-rcsb_embedding_model-0.0.35.dist-info/licenses/LICENSE.md,sha256=oUaHiKgfBkChth_Sm67WemEvatO1U0Go8LHjaskXY0w,1522
-rcsb_embedding_model-0.0.35.dist-info/RECORD,,
+rcsb_embedding_model-0.0.36.dist-info/METADATA,sha256=spFNxlrrwMORe5Su0559-997by2cgkuk9-yEQlhew60,5351
+rcsb_embedding_model-0.0.36.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+rcsb_embedding_model-0.0.36.dist-info/entry_points.txt,sha256=MK11jTIEmaV-x4CkPX5IymDaVs7Ky_f2xxU8BJVZ_9Q,69
+rcsb_embedding_model-0.0.36.dist-info/licenses/LICENSE.md,sha256=oUaHiKgfBkChth_Sm67WemEvatO1U0Go8LHjaskXY0w,1522
+rcsb_embedding_model-0.0.36.dist-info/RECORD,,