dayhoff-tools 1.1.36__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/fasta.py

@@ -13,8 +13,6 @@ 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__)
 
@@ -140,6 +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):
@@ -290,6 +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)
 
@@ -299,7 +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 = ""
 
@@ -314,6 +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,
@@ -441,6 +448,9 @@ def subtract_fasta_files(file1: str, file2: str, output_file: str):
     Raises:
         FileExistsError: If the output file already exists.
     """
+    from Bio import SeqIO
+    from tqdm import tqdm
+
     _check_output_file(output_file)
 
     # Load sequences from file1 with a progress bar
@@ -497,6 +507,8 @@ 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 +587,9 @@ 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)
@@ -735,6 +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)),
@@ -769,7 +786,7 @@ 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 +797,10 @@ 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 +836,9 @@ 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 +905,8 @@ 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 +937,9 @@ 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 +1016,12 @@ 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 +1110,8 @@ 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-1.1.38.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.1.36
+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-1.1.36.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=svP_ksm3FdyVZ8i8R9R5uoGu2qI_hVQ_eztG0drXkN8,36477
-dayhoff_tools/fasta.py,sha256=Ls6AG84IgG8COgAefqB3KS6iMbnixP_Up5EwUur-VUs,49780
+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-1.1.36.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-1.1.38.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,,