dayhoff-tools 1.1.36__py3-none-any.whl → 1.1.37__py3-none-any.whl

dayhoff_tools/embedders.py

@@ -7,14 +7,11 @@ import h5py
 import numpy as np
 import pandas as pd
 import torch
-import torch.utils.data
 from dayhoff_tools.deployment.processors import Processor
 from dayhoff_tools.fasta import (
     clean_noncanonical_fasta,
     clean_noncanonical_fasta_to_dict,
 )
-from esm import FastaBatchedDataset, pretrained
-from transformers import T5EncoderModel, T5Tokenizer
 
 logger = logging.getLogger(__name__)
 
@@ -52,6 +49,8 @@ class ESMEmbedder(Processor):
 
     def _load_model(self):
         """Download pre-trained model and load onto device"""
+        from esm import pretrained
+
         self.model, self.alphabet = pretrained.load_model_and_alphabet(self.model_name)
         self.model.eval()
         if torch.cuda.is_available():
@@ -62,6 +61,8 @@ class ESMEmbedder(Processor):
 
     def _load_dataset(self, fasta_file: str) -> None:
         """Load FASTA file into batched dataset and dataloader"""
+        from esm import FastaBatchedDataset
+
         if not fasta_file.endswith(".fasta"):
             raise ValueError("Input file must have .fasta extension.")
 
@@ -763,6 +764,8 @@ class ProstT5Embedder(Embedder):
             The model automatically selects half precision (float16) when running on GPU
             and full precision (float32) when running on CPU.
         """
+        from transformers import T5EncoderModel, T5Tokenizer
+
         tokenizer = T5Tokenizer.from_pretrained(
             "Rostlab/ProstT5", do_lower_case=False, legacy=True
         )
@@ -851,6 +854,8 @@ class T5Embedder(Embedder):
             The model automatically handles memory management and batch processing
             based on sequence sizes and available resources.
         """
+        from transformers import T5EncoderModel, T5Tokenizer
+
         tokenizer = T5Tokenizer.from_pretrained(
             "Rostlab/prot_t5_xl_half_uniref50-enc", do_lower_case=False
         )

dayhoff_tools/fasta.py

@@ -11,10 +11,6 @@ from pathlib import Path
 from typing import Dict, Iterator, List, Optional, Set, Tuple, Union
 
 import requests
-from Bio import SeqIO
-from Bio.SeqRecord import SeqRecord
-from tqdm import tqdm
-from tqdm.notebook import tqdm as tqdm_notebook
 
 logger = logging.getLogger(__name__)
 
@@ -441,6 +437,8 @@ def subtract_fasta_files(file1: str, file2: str, output_file: str):
     Raises:
         FileExistsError: If the output file already exists.
     """
+    from Bio import SeqIO
+
     _check_output_file(output_file)
 
     # Load sequences from file1 with a progress bar
@@ -497,6 +495,8 @@ def simplify_fasta_ids(
     Raises:
         FileExistsError: If the output file already exists.
     """
+    from Bio import SeqIO
+
     _check_output_file(output_fasta)
 
     count = 0
@@ -575,6 +575,9 @@ def extract_ids_from_fasta(fasta_file: str) -> Set[str]:
     Raises:
         ValueError: If there's an issue reading or parsing the input file.
     """
+    from Bio import SeqIO
+    from tqdm import tqdm
+
     sequence_ids: Set[str] = set()
     try:
         estimated_records = estimate_sequences(fasta_file)
@@ -769,7 +772,7 @@ def subset_fasta(
     return all_written_ids if return_written_ids else None
 
 
-def load_fasta_as_dict(fasta_file: str) -> Dict[str, SeqRecord]:
+def load_fasta_as_dict(fasta_file: str) -> Dict[str, "SeqRecord"]:
     """
     Load a FASTA file into a dictionary with record IDs as keys.
     Keep only the first instance of each identifier.
@@ -780,6 +783,10 @@ def load_fasta_as_dict(fasta_file: str) -> Dict[str, SeqRecord]:
     Returns:
         Dict[str, SeqRecord]: A dictionary with record IDs as keys and SeqRecord objects as values.
     """
+    from Bio import SeqIO
+    from Bio.SeqRecord import SeqRecord
+    from tqdm import tqdm
+
     record_dict: Dict[str, SeqRecord] = {}
     estimated_sequences = estimate_sequences(fasta_file)
 
@@ -815,6 +822,9 @@ def fasta_to_sqlite(fasta_file: str, db_file: str, batch_size: int = 1000) -> No
     Example:
         fasta_to_sqlite("proteins.fasta", "proteins.db")
     """
+    from Bio import SeqIO
+    from tqdm import tqdm
+
     _check_output_file(db_file)
 
     if not os.path.exists(fasta_file):
@@ -881,6 +891,8 @@ def _protein_generator(
     Yields:
         tuple[str, str]: A tuple containing protein_id and sequence.
     """
+    from Bio import SeqIO
+
     # Ensure we use 'rt' for text mode reading, especially if gzipped
     open_func = gzip.open if str(fasta_path).endswith(".gz") else open
     mode = "rt"
@@ -911,6 +923,9 @@ def check_fasta_duplicates(fasta_path: str) -> tuple[set[str], set[str]]:
         FileNotFoundError: If the input file doesn't exist
         ValueError: If the FASTA file is malformed
     """
+    from Bio import SeqIO
+    from tqdm import tqdm
+
     if not os.path.exists(fasta_path):
         raise FileNotFoundError(f"FASTA file not found: {fasta_path}")
 
@@ -987,6 +1002,12 @@ def clean_fasta_duplicates(
         FileExistsError: If the output file already exists
         FileNotFoundError: If the input file doesn't exist
     """
+    from Bio import SeqIO
+    from tqdm import tqdm
+
+    if not os.path.exists(input_path):
+        raise FileNotFoundError(f"Input FASTA file not found: {input_path}")
+
     _check_output_file(output_path)
 
     # First pass: collect sequence hashes for each ID
@@ -1075,6 +1096,8 @@ def fetch_uniprot_fasta(
     Returns:
         tuple: (success_count, failed_count, output_filepath, failed_accessions)
     """
+    from tqdm.notebook import tqdm as tqdm_notebook
+
     # Convert set to list for batch processing
     accession_list = list(accession_set)
 

{dayhoff_tools-1.1.36.dist-info → dayhoff_tools-1.1.37.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.1.36
+Version: 1.1.37
 Summary: Common tools for all the repos at Dayhoff Labs
 Author: Daniel Martin-Alarcon
 Author-email: dma@dayhofflabs.com

{dayhoff_tools-1.1.36.dist-info → dayhoff_tools-1.1.37.dist-info}/RECORD

@@ -13,8 +13,8 @@ dayhoff_tools/deployment/deploy_utils.py,sha256=StFwbqnr2_FWiKVg3xnJF4kagTHzndqq
 dayhoff_tools/deployment/job_runner.py,sha256=hljvFpH2Bw96uYyUup5Ths72PZRL_X27KxlYzBMgguo,5086
 dayhoff_tools/deployment/processors.py,sha256=A7zvF47TfCkuLTCvaqZmk1M9ZgZcv6CAoXZCV6rEXuE,34599
 dayhoff_tools/deployment/swarm.py,sha256=MGcS2_x4RNFtnVjWlU_SwNfhICz8NlGYr9cYBK4ZKDA,21688
-dayhoff_tools/embedders.py,sha256=svP_ksm3FdyVZ8i8R9R5uoGu2qI_hVQ_eztG0drXkN8,36477
-dayhoff_tools/fasta.py,sha256=Ls6AG84IgG8COgAefqB3KS6iMbnixP_Up5EwUur-VUs,49780
+dayhoff_tools/embedders.py,sha256=yO13jwVSqd-gk-PUhBE_7lnlRUIHn2tirxZ_mFAVAgM,36557
+dayhoff_tools/fasta.py,sha256=UARjl3w4O6hlZSgzuZZkG-Mi89TLxvxUDL-WEt0-5OU,50210
 dayhoff_tools/file_ops.py,sha256=JlGowvr-CUJFidV-4g_JmhUTN9bsYuaxtqKmnKomm-Q,8506
 dayhoff_tools/h5.py,sha256=j1nxxaiHsMidVX_XwB33P1Pz9d7K8ZKiDZwJWQUUQSY,21158
 dayhoff_tools/intake/gcp.py,sha256=uCeEskhbEwJIYpN6ne6siT1dbpTizCjjel-hRe0kReE,3030
@@ -26,7 +26,7 @@ dayhoff_tools/intake/uniprot.py,sha256=BZYJQF63OtPcBBnQ7_P9gulxzJtqyorgyuDiPeOJq
 dayhoff_tools/logs.py,sha256=DKdeP0k0kliRcilwvX0mUB2eipO5BdWUeHwh-VnsICs,838
 dayhoff_tools/sqlite.py,sha256=jV55ikF8VpTfeQqqlHSbY8OgfyfHj8zgHNpZjBLos_E,18672
 dayhoff_tools/warehouse.py,sha256=TqV8nex1AluNaL4JuXH5zuu9P7qmE89lSo6f_oViy6U,14965
-dayhoff_tools-1.1.36.dist-info/METADATA,sha256=71FGAv8K1KGE-Q7MN3W2bfZYDHCYUb7GGnsLkwPLQPw,2843
-dayhoff_tools-1.1.36.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-dayhoff_tools-1.1.36.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
-dayhoff_tools-1.1.36.dist-info/RECORD,,
+dayhoff_tools-1.1.37.dist-info/METADATA,sha256=wN6qyLCZ5vAQaZdS-8KNuzFnlHIWSz1moDJSugGyVjY,2843
+dayhoff_tools-1.1.37.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+dayhoff_tools-1.1.37.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
+dayhoff_tools-1.1.37.dist-info/RECORD,,