dayhoff-tools 1.2.5__tar.gz → 1.3.1__tar.gz

{dayhoff_tools-1.2.5 → dayhoff_tools-1.3.1}/PKG-INFO

@@ -1,11 +1,13 @@
 Metadata-Version: 2.3
 Name: dayhoff-tools
-Version: 1.2.5
+Version: 1.3.1
 Summary: Common tools for all the repos at Dayhoff Labs
 Author: Daniel Martin-Alarcon
 Author-email: dma@dayhofflabs.com
-Requires-Python: >=3.12,<4.0
+Requires-Python: >=3.10,<4.0
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Provides-Extra: embedders
@@ -24,13 +26,13 @@ Requires-Dist: pandas (>=2.2.3) ; extra == "embedders"
 Requires-Dist: pandas (>=2.2.3) ; extra == "full"
 Requires-Dist: pyyaml (>=6.0)
 Requires-Dist: questionary (>=2.0.1)
-Requires-Dist: rdkit (>=2025.3.2) ; extra == "full"
+Requires-Dist: rdkit-pypi (>=2022.9.5) ; extra == "full"
 Requires-Dist: requests (>=2.31.0)
 Requires-Dist: sentencepiece (>=0.2.0) ; extra == "embedders"
 Requires-Dist: sentencepiece (>=0.2.0) ; extra == "full"
 Requires-Dist: sqlalchemy (>=2.0.40,<3.0.0) ; extra == "full"
 Requires-Dist: toml (>=0.10)
-Requires-Dist: torch (>=2.5.0) ; extra == "embedders"
+Requires-Dist: torch (>=2.4.0) ; extra == "embedders"
 Requires-Dist: tqdm (>=4.67.1) ; extra == "embedders"
 Requires-Dist: tqdm (>=4.67.1) ; extra == "full"
 Requires-Dist: transformers (==4.36.2) ; extra == "full"

{dayhoff_tools-1.2.5 → dayhoff_tools-1.3.1}/dayhoff_tools/embedders.py

@@ -683,7 +683,7 @@ class Embedder(Processor):
         sequence_ids, sequences, sequence_lengths = zip(*batch)
 
         # Prepare sequences for tokenization
-        tokenizer_input = self.prepare_tokenizer_input(sequences)
+        tokenizer_input = self.prepare_tokenizer_input(list(sequences))
 
         # Tokenize sequences
         encoded_input = self.tokenizer.batch_encode_plus(

{dayhoff_tools-1.2.5 → dayhoff_tools-1.3.1}/dayhoff_tools/fasta.py

@@ -25,7 +25,7 @@ def _clean_noncanonical_fasta(
 ) -> Optional[dict[str, str]]:
     """
     Read in a FASTA file containing multiple sequences, replace non-canonical amino acids,
-    remove empty sequences, and either write the sequences to a new FASTA file or return them as a dictionary.
+    remove stop codons, remove empty sequences, and either write the sequences to a new FASTA file or return them as a dictionary.
 
     Args:
         input_path (str): Path to the input FASTA file.
@@ -48,7 +48,11 @@ def _clean_noncanonical_fasta(
         for line in fasta_file:
             if line.startswith(">"):
                 if seq_id and seq_lines:
-                    seq = "".join(seq_lines).translate(str.maketrans("OJUZB", "XLCED"))
+                    seq = (
+                        "".join(seq_lines)
+                        .translate(str.maketrans("OJUZB", "XLCED"))
+                        .replace("*", "")
+                    )
                     if seq.strip():  # Only process non-empty sequences
                         sequences[seq_id] = seq
                         if output_path:
@@ -61,7 +65,11 @@ def _clean_noncanonical_fasta(
 
         # Process the last sequence
         if seq_id and seq_lines:
-            seq = "".join(seq_lines).translate(str.maketrans("OJUZB", "XLCED"))
+            seq = (
+                "".join(seq_lines)
+                .translate(str.maketrans("OJUZB", "XLCED"))
+                .replace("*", "")
+            )
             if seq.strip():  # Only process non-empty sequences
                 sequences[seq_id] = seq
                 if output_path:
@@ -92,7 +100,7 @@ def clean_noncanonical_fasta(
 ):
     """
     Read in a FASTA file containing multiple sequences and write the sequences to a new FASTA file.
-    Replace non-canonical amino acids along the way.
+    Replace non-canonical amino acids and remove stop codons along the way.
 
     Args:
         input_path (str): Path to the input FASTA file.
@@ -112,7 +120,7 @@ def clean_noncanonical_fasta_to_dict(
 ) -> dict[str, str]:
     """
     Read in a FASTA file containing multiple sequences and return the sequences as a dictionary.
-    Replace non-canonical amino acids along the way.
+    Replace non-canonical amino acids and remove stop codons along the way.
 
     Args:
         input_path (str): Path to the input FASTA file.

{dayhoff_tools-1.2.5 → dayhoff_tools-1.3.1}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "dayhoff-tools"
-version = "1.2.5"
+version = "1.3.1"
 description = "Common tools for all the repos at Dayhoff Labs"
 authors = [
     {name = "Daniel Martin-Alarcon", email = "dma@dayhofflabs.com"}
@@ -21,7 +21,7 @@ dependencies = [
     "questionary>=2.0.1",
     "tzdata>=2025.2",
 ]
-requires-python = ">=3.12,<4.0"
+requires-python = ">=3.10,<4.0"
 
 [project.optional-dependencies]
 full = [
@@ -31,7 +31,7 @@ full = [
     "fair-esm>=2.0.0",
     "h5py>=3.11.0",
     "pandas>=2.2.3",
-    "rdkit>=2025.3.2",
+    "rdkit-pypi>=2022.9.5",
     "sqlalchemy (>=2.0.40,<3.0.0)",
     "transformers==4.36.2",
     "sentencepiece>=0.2.0",
@@ -44,7 +44,7 @@ embedders = [
     "numpy>=1.26.4",
     "pandas>=2.2.3",
     "sentencepiece>=0.2.0",
-    "torch>=2.5.0",
+    "torch>=2.4.0",
     "tqdm>=4.67.1",
     "transformers>=4.36.2",
 ]
@@ -79,8 +79,8 @@ dev-dependencies = [
     "pytest>=8.0.2,<9",
     "pytest-cov>=4.1.0,<5",
     "pytest-mock>=3.12.0,<4",
-    "torch>=2.5.0",
-    "torchvision>=0.20.0",
+    "torch==2.4.0+cu121",
+    "torchvision==0.19.0+cu121",
 ]
 
 [project.scripts]