rcsb-embedding-model 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

rcsb_embedding_model/inference/assembly_inferece.py

@@ -0,0 +1,53 @@
+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
+from rcsb_embedding_model.inference.chain_inference import predict as chain_predict
+
+
+def predict(
+        src_stream: FileOrStreamTuple,
+        res_embedding_location: EmbeddingPath,
+        src_location: SrcLocation = SrcLocation.local,
+        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,
+        batch_size: int = 1,
+        num_workers: int = 0,
+        num_nodes: int = 1,
+        accelerator: Accelerator = Accelerator.auto,
+        devices: Devices = 'auto',
+        out_path: OptionalPath = None
+):
+    inference_set = ResidueAssemblyEmbeddingFromTensorFile(
+        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
+    ) if src_from == SrcAssemblyFrom.assembly else ResidueAssemblyDatasetFromStructure(
+        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
+    )
+
+    return chain_predict(
+        src_stream=src_stream,
+        src_location=src_location,
+        batch_size=batch_size,
+        num_workers=num_workers,
+        num_nodes=num_nodes,
+        accelerator=accelerator,
+        devices=devices,
+        out_path=out_path,
+        inference_set=inference_set
+    )

rcsb_embedding_model/inference/chain_inference.py

@@ -1,26 +1,30 @@
 from torch.utils.data import DataLoader
 from lightning import Trainer
-from typer import FileText
 
-from rcsb_embedding_model.dataset.residue_embedding_from_csv import ResidueEmbeddingFromCSV
+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
+from rcsb_embedding_model.types.api_types import Accelerator, Devices, OptionalPath, FileOrStreamTuple, SrcLocation
 from rcsb_embedding_model.utils.data import collate_seq_embeddings
 from rcsb_embedding_model.writer.batch_writer import CsvBatchWriter
 
 
 def predict(
-        csv_file: FileText,
+        src_stream: FileOrStreamTuple,
+        src_location: SrcLocation = SrcLocation.local,
         batch_size: int = 1,
         num_workers: int = 0,
         num_nodes: int = 1,
         accelerator: Accelerator = Accelerator.auto,
         devices: Devices = 'auto',
-        out_path: OptionalPath = None
+        out_path: OptionalPath = None,
+        inference_set=None
 ):
-    inference_set = ResidueEmbeddingFromCSV(
-        csv_file=csv_file
-    )
+
+    if inference_set is None:
+        inference_set = ResidueEmbeddingFromTensorFile(
+            src_stream=src_stream,
+            src_location=src_location
+        )
 
     inference_dataloader = DataLoader(
         dataset=inference_set,

rcsb_embedding_model/inference/esm_inference.py

@@ -1,17 +1,20 @@
 from torch.utils.data import DataLoader
 from lightning import Trainer
-from typer import FileText
 
-from rcsb_embedding_model.dataset.esm_prot_from_csv import EsmProtFromCsv
+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 SrcFormat, Accelerator, Devices, OptionalPath, SrcLocation
+from rcsb_embedding_model.types.api_types import StructureFormat, Accelerator, Devices, OptionalPath, StructureLocation, SrcProteinFrom, FileOrStreamTuple, SrcLocation
 from rcsb_embedding_model.writer.batch_writer import TensorBatchWriter
 
 
 def predict(
-        csv_file: FileText,
+        src_stream: FileOrStreamTuple,
         src_location: SrcLocation = SrcLocation.local,
-        src_format: SrcFormat = SrcFormat.mmcif,
+        src_from: SrcProteinFrom = SrcProteinFrom.chain,
+        structure_location: StructureLocation = StructureLocation.local,
+        structure_format: StructureFormat = StructureFormat.mmcif,
+        min_res_n: int = 0,
         batch_size: int = 1,
         num_workers: int = 0,
         num_nodes: int = 1,
@@ -20,10 +23,17 @@ def predict(
         out_path: OptionalPath = None
 ):
 
-    inference_set = EsmProtFromCsv(
-        csv_file=csv_file,
+    inference_set = EsmProtFromChain(
+        src_stream=src_stream,
         src_location=src_location,
-        src_format=src_format
+        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
     )
 
     inference_dataloader = DataLoader(

rcsb_embedding_model/inference/structure_inference.py

@@ -0,0 +1,61 @@
+from torch.utils.data import DataLoader
+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, SrcProteinFrom, FileOrStreamTuple, SrcLocation
+from rcsb_embedding_model.writer.batch_writer import DataFrameStorage
+
+
+def predict(
+        src_stream: FileOrStreamTuple,
+        src_location: SrcLocation = SrcLocation.local,
+        src_from: SrcProteinFrom = SrcProteinFrom.chain,
+        structure_location: StructureLocation = StructureLocation.local,
+        structure_format: StructureFormat = StructureFormat.mmcif,
+        min_res_n: int = 0,
+        batch_size: int = 1,
+        num_workers: int = 0,
+        num_nodes: int = 1,
+        accelerator: Accelerator = Accelerator.auto,
+        devices: Devices = 'auto',
+        out_path: OptionalPath = None,
+        out_df_name: str = None
+):
+
+    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
+    )
+
+    inference_dataloader = DataLoader(
+        dataset=inference_set,
+        batch_size=batch_size,
+        num_workers=num_workers,
+        collate_fn=lambda _: _
+    )
+
+    module = StructureModule()
+    inference_writer = DataFrameStorage(out_path, out_df_name) if out_path is not None and out_df_name is not None else None
+    trainer = Trainer(
+        callbacks=[inference_writer] if inference_writer is not None else None,
+        num_nodes=num_nodes,
+        accelerator=accelerator,
+        devices=devices
+    )
+
+    prediction = trainer.predict(
+        module,
+        inference_dataloader
+    )
+
+    return prediction

rcsb_embedding_model/modules/structure_module.py

@@ -0,0 +1,27 @@
+from esm.sdk.api import SamplingConfig
+from lightning import LightningModule
+
+from rcsb_embedding_model.utils.data import collate_seq_embeddings
+from rcsb_embedding_model.utils.model import get_residue_model, get_aggregator_model
+
+
+class StructureModule(LightningModule):
+
+    def __init__(
+            self
+    ):
+        super().__init__()
+        self.esm3 = get_residue_model(self.device)
+        self.aggregator = get_aggregator_model(device=self.device)
+
+    def predict_step(self, prot_batch, batch_idx):
+        prot_embeddings = []
+        prot_names = []
+        for esm_prot, name in prot_batch:
+            embeddings = self.esm3.forward_and_sample(
+                self.esm3.encode(esm_prot), SamplingConfig(return_per_residue_embeddings=True)
+            ).per_residue_embedding
+            prot_embeddings.append(embeddings)
+            prot_names.append(name)
+        res_batch_embedding, res_batch_mask = collate_seq_embeddings(prot_embeddings)
+        return self.aggregator(res_batch_embedding, res_batch_mask), tuple(prot_names)

rcsb_embedding_model/rcsb_structure_embedding.py

@@ -2,9 +2,8 @@ import torch
 from biotite.structure import get_residues, chain_iter, filter_amino_acids
 from esm.sdk.api import ESMProtein, SamplingConfig
 from esm.utils.structure.protein_chain import ProteinChain
-from huggingface_hub import hf_hub_download
 
-from rcsb_embedding_model.types.api_types import StreamSrc, SrcFormat
+from rcsb_embedding_model.types.api_types import StreamSrc, StructureFormat
 from rcsb_embedding_model.utils.model import get_aggregator_model, get_residue_model
 from rcsb_embedding_model.utils.structure_parser import get_structure_from_src
 
@@ -42,23 +41,23 @@ class RcsbStructureEmbedding:
 
     def structure_embedding(
             self,
-            structure_src: StreamSrc,
-            src_format: SrcFormat = SrcFormat.mmcif,
+            src_structure: StreamSrc,
+            structure_format: StructureFormat = StructureFormat.mmcif,
             chain_id: str = None,
             assembly_id: str = None
     ):
-        res_embedding = self.residue_embedding(structure_src, src_format, chain_id, assembly_id)
+        res_embedding = self.residue_embedding(src_structure, structure_format, chain_id, assembly_id)
         return self.aggregator_embedding(res_embedding)
 
     def residue_embedding(
             self,
-            structure_src: StreamSrc,
-            src_format: SrcFormat = SrcFormat.mmcif,
+            src_structure: StreamSrc,
+            structure_format: StructureFormat = StructureFormat.mmcif,
             chain_id: str = None,
             assembly_id: str = None
     ):
         self.__check_residue_embedding()
-        structure = get_structure_from_src(structure_src, src_format, chain_id, assembly_id)
+        structure = get_structure_from_src(src_structure, structure_format, chain_id, assembly_id)
         embedding_ch = []
         for atom_ch in chain_iter(structure):
             atom_res = atom_ch[filter_amino_acids(atom_ch)]

rcsb_embedding_model/types/api_types.py

@@ -1,16 +1,23 @@
 from enum import Enum
-from os import PathLike
 from typing import NewType, Union, IO, Tuple, List, Optional
 
-StreamSrc = NewType('StreamSrc', Union[PathLike, IO])
-StreamTuple = NewType('StreamTuple', Tuple[StreamSrc, str, str])
+from typer import FileText
+
+StreamSrc = NewType('StreamSrc', Union[FileText, IO])
+StreamTuple = NewType('StreamTuple', Union[
+    Tuple[str, StreamSrc, str, str],
+    Tuple[str, StreamSrc, str],
+    Tuple[str, str]
+])
+FileOrStreamTuple = NewType('FileOrStreamTuple', Union[FileText, StreamTuple])
 
 Devices = NewType('Devices', Union[int, List[int], "auto"])
 
-OptionalPath = NewType('OptionalPath', Optional[PathLike])
+EmbeddingPath = Union[str, FileText]
+OptionalPath = NewType('OptionalPath', Optional[FileText])
 
 
-class SrcFormat(str, Enum):
+class StructureFormat(str, Enum):
     pdb = "pdb"
     mmcif = "mmcif"
     bciff = "binarycif"
@@ -25,5 +32,20 @@ class Accelerator(str, Enum):
 
 
 class SrcLocation(str, Enum):
+    local = "local"
+    stream = "stream"
+
+
+class StructureLocation(str, Enum):
     local = "local"
     remote = "remote"
+
+
+class SrcProteinFrom(str, Enum):
+    chain = "chain"
+    structure = "structure"
+
+
+class SrcAssemblyFrom(str, Enum):
+    assembly = "assembly"
+    structure = "structure"

rcsb_embedding_model/utils/data.py

@@ -44,4 +44,34 @@ def stringio_from_url(url):
         print(f"Error fetching URL: {e}")
         return None
 
+def concatenate_tensors(file_list, max_residues, dim=0):
+    """
+    Concatenates a list of tensors stored in individual files along a specified dimension.
+
+    Args:
+        file_list (list of str): List of file paths to tensor files.
+        max_residues (int): Maximum number of residues allowed in the assembly
+        dim (int): The dimension along which to concatenate the tensors. Default is 0.
 
+    Returns:
+        torch.Tensor: The concatenated tensor.
+    """
+    tensors = []
+    total_residues = 0
+    for file in file_list:
+        try:
+            tensor = torch.load(
+                file,
+                map_location=torch.device('cpu')
+            )
+            total_residues += tensor.shape[0]
+            tensors.append(tensor)
+        except Exception as e:
+            continue
+        if total_residues > max_residues:
+            break
+    if tensors and len(tensors) > 0:
+        tensor_cat = torch.cat(tensors, dim=dim)
+        return tensor_cat
+    else:
+        raise ValueError("No valid tensors were loaded to concatenate.")

rcsb_embedding_model/utils/structure_parser.py

@@ -1,32 +1,62 @@
-
-from biotite.structure.io.pdb import PDBFile, get_structure as get_pdb_structure, get_assembly as get_pdb_assembly
-from biotite.structure.io.pdbx import CIFFile, get_structure, get_assembly, BinaryCIFFile
+from biotite.structure import filter_amino_acids, 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(
-        structure_src,
-        src_format="mmcif",
+        src_structure,
+        structure_format="mmcif",
         chain_id=None,
         assembly_id=None
 ):
-    if src_format == "pdb":
-        pdb_file = PDBFile.read(structure_src)
+    if structure_format == "pdb":
+        pdb_file = PDBFile.read(src_structure)
         structure = __get_pdb_structure(pdb_file, assembly_id)
-    elif src_format == "mmcif":
-        cif_file = CIFFile.read(structure_src)
+    elif structure_format == "mmcif":
+        cif_file = CIFFile.read(src_structure)
         structure = __get_structure(cif_file, assembly_id)
-    elif src_format == "binarycif":
-        cif_file = BinaryCIFFile.read(structure_src)
+    elif structure_format == "binarycif":
+        cif_file = BinaryCIFFile.read(src_structure)
         structure = __get_structure(cif_file, assembly_id)
     else:
-        raise RuntimeError(f"Unknown file format {src_format}")
+        raise RuntimeError(f"Unknown file format {structure_format}")
 
     if chain_id is not None:
-        structure = structure[structure.chain_id == chain_id]
+        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_amino_acids(atom_ch)]
+        if len(atom_res) > 0 and len(get_residues(atom_res)) > min_res_n:
+            chain_ids.append(str(get_chains(atom_res)[0]))
+    return tuple(chain_ids)
+
+
+def get_assemblies(src_structure, structure_format="mmcif"):
+    if structure_format == "pdb":
+        return tuple(list_pdb_assemblies(PDBFile.read(src_structure)))
+    elif structure_format == "mmcif":
+        return tuple(list_assemblies(CIFFile.read(src_structure)).keys())
+    elif structure_format == "binarycif":
+        return tuple(list_assemblies(BinaryCIFFile.read(src_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))
+    n = 0
+    for atom in atom_ch:
+        atom.chain_id = ch
+        renamed_atom_ch[n] = atom
+        n += 1
+    return renamed_atom_ch
+
+
 def __get_pdb_structure(pdb_file, assembly_id=None):
     return get_pdb_structure(
         pdb_file,

rcsb_embedding_model/utils/structure_provider.py

@@ -0,0 +1,27 @@
+from rcsb_embedding_model.utils.structure_parser import get_structure_from_src
+
+
+class StructureProvider:
+
+    def __init__(self):
+        self.__src_name = None
+        self.__structure = None
+
+    def get_structure(
+        self,
+        src_name,
+        src_structure,
+        structure_format="mmcif",
+        chain_id=None,
+        assembly_id=None
+    ):
+        if src_name != self.__src_name:
+            self.__src_name = src_name
+            self.__structure = get_structure_from_src(
+                src_structure=src_structure,
+                structure_format=structure_format,
+                assembly_id=assembly_id
+            )
+        if chain_id is not None:
+            return self.__structure[self.__structure.chain_id == chain_id]
+        return self.__structure

rcsb_embedding_model-0.0.8.dist-info/METADATA

@@ -0,0 +1,129 @@
+Metadata-Version: 2.4
+Name: rcsb-embedding-model
+Version: 0.0.8
+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
+Author-email: Joan Segura <joan.segura@rcsb.org>
+License-Expression: BSD-3-Clause
+License-File: LICENSE.md
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.10
+Requires-Dist: esm>=3.2.0
+Requires-Dist: lightning>=2.5.0
+Requires-Dist: torch>=2.2.0
+Requires-Dist: typer>=0.15.0
+Description-Content-Type: text/markdown
+
+# RCSB Embedding Model
+
+**Version** 0.0.8
+
+
+## Overview
+
+RCSB Embedding Model is a neural network architecture designed to encode macromolecular 3D structures into fixed-length vector embeddings for efficient large-scale structure similarity search.
+
+Preprint: [Multi-scale structural similarity embedding search across entire proteomes](https://www.biorxiv.org/content/10.1101/2025.02.28.640875v1).
+
+A web-based implementation using this model for structure similarity search is available at [rcsb-embedding-search](http://embedding-search.rcsb.org).
+
+If you are interested in training the model with a new dataset, visit the [rcsb-embedding-search repository](https://github.com/bioinsilico/rcsb-embedding-search), which provides scripts and documentation for training.
+
+
+## Features
+
+- **Residue-level embeddings** computed using the ESM3 protein language model  
+- **Structure-level embeddings** aggregated via a transformer-based aggregator network  
+- **Command-line interface** implemented with Typer for high-throughput inference workflows  
+- **Python API** for interactive embedding computation and integration into analysis pipelines  
+- **High-performance inference** leveraging PyTorch Lightning, with multi-node and multi-GPU support  
+
+---
+
+## Installation
+
+    pip install rcsb-embedding-model
+
+**Requirements:**
+
+- Python ≥ 3.10  
+- ESM ≥ 3.2.0  
+- PyTorch ≥ 2.2.0  
+- Lightning ≥ 2.5.0  
+- Typer ≥ 0.15.0  
+
+---
+
+## Quick Start
+
+### CLI
+
+    # 1. Compute residue embeddings: Calculate residue level embeddings of protein structures using ESM3. Predictions are stored as torch tensor files.
+    inference residue-embedding --src-file data/structures.csv --output-path results/residue_embeddings --structure-format mmcif --batch-size 8 --devices auto
+
+    # 2. Compute structure embeddings: Calculate single-chain protein embeddings from structural files. Predictions are stored in a single pandas DataFrame file.
+    inference structure-embedding --src-file data/structures.csv --output-path results/residue_embeddings --out-df-name df-res-embeddings --batch-size 4 --devices 0 --devives 1
+
+    # 3. Compute chain embeddings: Calculate single-chain protein embeddings from residue level embeddings stored as torch tensor files. Predictions a re stored as csv files.
+    inference chain-embedding --src-file data/structures.csv --output-path results/chain_embeddings --batch-size 4
+
+    # 4. Compute assembly embeddings: Calculate assembly embeddings from residue level embeddings stored as torch tensor files. Predictions are stored as csv files.
+    inference assembly-embedding --src-file data/structures.csv --res-embedding-location results/residue_embeddings --output-path results/assembly_embeddings
+
+### Python API
+
+    from rcsb_embedding_model import RcsbStructureEmbedding
+
+    model = RcsbStructureEmbedding()
+
+    # Compute per-residue embeddings
+    res_emb = model.residue_embedding(
+        src_structure="examples/1abc.cif",
+        src_format="mmcif",
+        chain_id="A"
+    )
+
+    # Aggregate to structure-level embedding
+    struct_emb = model.aggregator_embedding(res_emb)
+
+See the examples and tests directories for more use cases.
+
+---
+
+## Model Architecture
+
+The embedding model is trained to predict structural similarity by approximating TM-scores using cosine distances between embeddings. It consists of two main components:
+
+- **Protein Language Model (PLM)**: Computes residue-level embeddings from a given 3D structure.
+- **Residue Embedding Aggregator**: A transformer-based neural network that aggregates these residue-level embeddings into a single vector.
+
+![Embedding model architecture](assets/embedding-model-architecture.png)
+
+### **Protein Language Model (PLM)**
+Residue-wise embeddings of protein structures are computed using the [ESM3](https://www.evolutionaryscale.ai/) generative protein language model.
+
+### **Residue Embedding Aggregator**
+The aggregation component consists of six transformer encoder layers, each with a 3,072-neuron feedforward layer and ReLU activations. After processing through these layers, a summation pooling operation is applied, followed by 12 fully connected residual layers that refine the embeddings into a single 1,536-dimensional vector.
+
+---
+
+## Development
+
+    git clone https://github.com/rcsb/rcsb-embedding-model.git
+    cd rcsb-embedding-model
+    pip install -e .
+    pytest
+
+---
+
+## Citation
+
+Segura, J., Bittrich, S., et al. (2024). *Multi-scale structural similarity embedding search across entire proteomes*. bioRxiv. (Preprint: https://www.biorxiv.org/content/10.1101/2025.02.28.640875v1)
+
+---
+
+## License
+
+This project is licensed under the BSD 3-Clause License. See [LICENSE.md](LICENSE.md) for details.

rcsb_embedding_model-0.0.8.dist-info/RECORD

@@ -0,0 +1,29 @@
+rcsb_embedding_model/__init__.py,sha256=r3gLdeBIXkQEQA_K6QcRPO-TtYuAQSutk6pXRUE_nas,120
+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=KPZLqznbxZE_CBCGigUGg7yOfGsi8ID4aWMTExniRj4,11464
+rcsb_embedding_model/dataset/esm_prot_from_chain.py,sha256=dBD2N0Y-GoN6p3z2yLnOvv6JGn-skAxwgbOYhXKDngc,3487
+rcsb_embedding_model/dataset/esm_prot_from_structure.py,sha256=kOqgHfHjiym5InaAgpgMmHBgCAPEqW88PCoHHQy0ROI,2490
+rcsb_embedding_model/dataset/resdiue_assembly_embedding_from_structure.py,sha256=d8C7HRJBZWuOKhPQpihv1koT4aIvyt5QN2yndC2ABuE,2842
+rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py,sha256=KXiohnPjjfZEFbPZQ46HGE8eEYWrVX8bfbTz4zPlo7o,3451
+rcsb_embedding_model/dataset/residue_embedding_from_tensor_file.py,sha256=cOxT--Spkel10JJCeGlqgLXN5vNCZzPdfSxDgUSrdPI,1268
+rcsb_embedding_model/inference/assembly_inferece.py,sha256=MPssN5bsOqOU-LGwa6AKX99cv5LD43Mnbaqhuuww1Tw,2165
+rcsb_embedding_model/inference/chain_inference.py,sha256=R9gi0MZ_HaM3v9c433W_5w4suse4nJmy4SgUTHJVZLg,1713
+rcsb_embedding_model/inference/esm_inference.py,sha256=oVN4r9_6V8TS0pYoNn7GR92Xo0Zn7eBsnt_OfDSaH6g,2126
+rcsb_embedding_model/inference/structure_inference.py,sha256=QIUEo8eEc-kTSYKGdlX2rxT74huw4ZAw6U8Px9kYajE,2216
+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=sDSPXJmWuU2C3lt1NorlbUVWZvRSLzumPdFQk01h3VI,403
+rcsb_embedding_model/modules/esm_module.py,sha256=CTHGOATXiarqZsBsZ8oxGJBj20A73186Slpr0EzMJsE,770
+rcsb_embedding_model/modules/structure_module.py,sha256=dEtDNdWo1j2sSDa0JiOHQfEfQzIWqSLEKpvOX0GrXZ4,1048
+rcsb_embedding_model/types/api_types.py,sha256=3sPh33yb3Ya9r3O5vuiTfhb1WyFuhQWCQmewSbqEyG0,1076
+rcsb_embedding_model/utils/data.py,sha256=x6ca_bVdBXEAp9ugCi1rVEQ-G5nGTFKpzDKqZKpkFBE,2933
+rcsb_embedding_model/utils/model.py,sha256=rpZa-gfm3cEtbBd7UXMHrZv3x6f0AC8TJT3gtrSxr5I,852
+rcsb_embedding_model/utils/structure_parser.py,sha256=jat4SCtPHYMZ6JJR-T7lPQoMbT_E8CwYSGDNSZjG86U,2697
+rcsb_embedding_model/utils/structure_provider.py,sha256=eWtxjkPpmRfmil_DKR1J6miaXR3lQ28DF5O0qrqSgGA,786
+rcsb_embedding_model/writer/batch_writer.py,sha256=ekgzFZyoKpcnZ3IDP9hfOWBpuHxUQ31P35ViDAi-Edw,2843
+rcsb_embedding_model-0.0.8.dist-info/METADATA,sha256=XvNb99X9GWdMEdz-A_o-ngTxlfiWrr8KMvjKh_rk3x0,5366
+rcsb_embedding_model-0.0.8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+rcsb_embedding_model-0.0.8.dist-info/entry_points.txt,sha256=MK11jTIEmaV-x4CkPX5IymDaVs7Ky_f2xxU8BJVZ_9Q,69
+rcsb_embedding_model-0.0.8.dist-info/licenses/LICENSE.md,sha256=oUaHiKgfBkChth_Sm67WemEvatO1U0Go8LHjaskXY0w,1522
+rcsb_embedding_model-0.0.8.dist-info/RECORD,,