dayhoff-tools 1.1.37__py3-none-any.whl → 1.1.38__py3-none-any.whl

dayhoff_tools/deployment/deploy_gcp.py

@@ -61,6 +61,7 @@ def create_batch_job_config(config: dict, image_uri: str) -> dict:
         "allocation_policy",  # Goes into batch_config.allocationPolicy
         "logs_policy",  # Goes into batch_config.logsPolicy
         "batch_job",  # Contains detailed task and resource specs
+        "image_uri",
         # Keys like job_name, region, registry_uri, repository are used by other functions
         # or for other purposes, not directly for constructing the core batch_config JSON here.
     }

dayhoff_tools/embedders.py

@@ -7,11 +7,14 @@ 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__)
 
@@ -49,8 +52,6 @@ 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():
@@ -61,8 +62,6 @@ 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.")
 
@@ -764,8 +763,6 @@ 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
         )
@@ -854,8 +851,6 @@ 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

@@ -11,6 +11,8 @@ 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
 
 logger = logging.getLogger(__name__)
 
@@ -136,6 +138,8 @@ def combine_fasta_files(input_path: Union[str, List[str]], output_path: str) ->
     Raises:
         FileExistsError: If the output file already exists.
     """
+    from tqdm import tqdm
+
     _check_output_file(output_path)
 
     if isinstance(input_path, str):
@@ -286,6 +290,11 @@ def split_fasta(
     Returns:
         int: The number of output files created.
     """
+    from typing import TYPE_CHECKING, Optional
+
+    if TYPE_CHECKING:
+        from tqdm import tqdm
+
     # Ensure the target folder exists
     os.makedirs(target_folder, exist_ok=True)
 
@@ -295,7 +304,7 @@ def split_fasta(
     files_created = 0
     current_output_file_sequence_count = 0
     current_output_file_bytes_written = 0
-    pbar: tqdm | None = None
+    pbar: Optional["tqdm"] = None
     output_file = None  # Will be opened when we encounter the first header line
     output_file_path = ""
 
@@ -310,6 +319,8 @@ def split_fasta(
         # Open the large FASTA file for reading
         with open(fasta_file, "r", buffering=1024 * 1024) as fasta:
             if show_progress:
+                from tqdm import tqdm
+
                 total_size = os.path.getsize(fasta_file)
                 pbar = tqdm(
                     total=total_size,
@@ -438,6 +449,7 @@ def subtract_fasta_files(file1: str, file2: str, output_file: str):
         FileExistsError: If the output file already exists.
     """
     from Bio import SeqIO
+    from tqdm import tqdm
 
     _check_output_file(output_file)
 
@@ -738,6 +750,8 @@ def subset_fasta(
                 actual_num_chunks_for_tqdm = num_chunks  # Use the calculated num_chunks
 
                 try:
+                    from tqdm import tqdm
+
                     results_buffer = []
                     for result_tuple in tqdm(
                         pool.imap(process_func, chunk_reader(input_file, chunk_size)),

{dayhoff_tools-1.1.37.dist-info → dayhoff_tools-1.1.38.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.1.37
+Version: 1.1.38
 Summary: Common tools for all the repos at Dayhoff Labs
 Author: Daniel Martin-Alarcon
 Author-email: dma@dayhofflabs.com

{dayhoff_tools-1.1.37.dist-info → dayhoff_tools-1.1.38.dist-info}/RECORD

@@ -8,13 +8,13 @@ dayhoff_tools/cli/swarm_commands.py,sha256=5EyKj8yietvT5lfoz8Zx0iQvVaNgc3SJX1z2z
 dayhoff_tools/cli/utility_commands.py,sha256=ER4VrJt4hu904MwrcltUXjwBWT4uFrP-aPXjdXyT3F8,24685
 dayhoff_tools/deployment/base.py,sha256=8tXwsPYvRo-zV-aNhHw1c7Rji-KWg8S5xoCCznFnVVI,17412
 dayhoff_tools/deployment/deploy_aws.py,sha256=jQyQ0fbm2793jEHFO84lr5tNqiOpdBg6U0S5zCVJr1M,17884
-dayhoff_tools/deployment/deploy_gcp.py,sha256=jiEE_tBVeSavAI8o_6qPDPpaoXKexcaNIa4uXcv3y0M,8839
+dayhoff_tools/deployment/deploy_gcp.py,sha256=xgaOVsUDmP6wSEMYNkm1yRNcVskfdz80qJtCulkBIAM,8860
 dayhoff_tools/deployment/deploy_utils.py,sha256=StFwbqnr2_FWiKVg3xnJF4kagTHzndqqDkpaIOaAn_4,26027
 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=yO13jwVSqd-gk-PUhBE_7lnlRUIHn2tirxZ_mFAVAgM,36557
-dayhoff_tools/fasta.py,sha256=UARjl3w4O6hlZSgzuZZkG-Mi89TLxvxUDL-WEt0-5OU,50210
+dayhoff_tools/embedders.py,sha256=svP_ksm3FdyVZ8i8R9R5uoGu2qI_hVQ_eztG0drXkN8,36477
+dayhoff_tools/fasta.py,sha256=_kA2Cpiy7JAGbBqLrjElkzbcUD_p-nO2d5Aj1LVmOvc,50509
 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-1.1.37.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,,
+dayhoff_tools-1.1.38.dist-info/METADATA,sha256=nDSK0SHTOMdieTxWDLScNArXB4g5TLAocONnt4xD89k,2843
+dayhoff_tools-1.1.38.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+dayhoff_tools-1.1.38.dist-info/entry_points.txt,sha256=iAf4jteNqW3cJm6CO6czLxjW3vxYKsyGLZ8WGmxamSc,49
+dayhoff_tools-1.1.38.dist-info/RECORD,,