Merge pull request #6 from AlfonsoJan/dev

Version 1.0.1

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "sbsgenerator"
-version = "1.0.0"
+version = "1.0.1"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

README.md

@@ -3,7 +3,7 @@
 
 # SBSGenerator
 
-SBSGenerator is a comprehensive Python package designed for bioinformaticians and researchers working in the field of genomics. This package offers a robust set of tools for generating, analyzing, and interpreting single base substitutions (SBS) mutations from Variant Call Format (VCF) files. With a focus on ease of use, efficiency, and scalability, SBSGenerator facilitates the detailed study of genomic mutations, aiding in the understanding of their roles in various biological processes and diseases. Uniquely developed using a hybrid of Python and Rust, SBSGenerator leverages the PyO3 library for seamless integration between Python's flexible programming capabilities and Rust's unparalleled performance. This innovative approach ensures that SBSGen is not only user-friendly but also incredibly efficient and capable of handling large-scale genomic data with ease.
+SBSGenerator is a comprehensive Python package designed for bioinformaticians and researchers working in the field of genomics. This package offers a robust set of tools for generating, analyzing, and interpreting single base substitutions (SBS) mutations from Variant Call Format (VCF) files. With a focus on ease of use, efficiency, and scalability, SBSGenerator facilitates the detailed study of genomic mutations, aiding in the understanding of their roles in various biological processes and diseases. Uniquely developed using a hybrid of Python and Rust, SBSGenerator leverages the PyO3 library for seamless integration between Python's flexible programming capabilities and Rust's unparalleled performance. This innovative approach ensures that SBSGenerator is not only user-friendly but also incredibly efficient and capable of handling large-scale genomic data with ease.
 
 - [Installation](#installation)
 - [Usage](#usage)
@@ -18,37 +18,37 @@ $ pip install sbsgenerator
 
 ## Usage
 
-Create mutliple SBS files. With increasing context.
+The `SBSGenerator` package is designed to facilitate the generation and analysis of SBS mutation data from VCF files across different genomic contexts. Depending on the specified context size, it can create comprehensive dataframes listing all possible SBS mutations, ranging from simple 3-nucleotide contexts to more complex 7-nucleotide contexts, with the potential number of mutation combinations exponentially increasing with context size.
 
-The sbs.96.txt file contains all of the following the pyrimidine single nucleotide variants, N[{C > A, G, or T} or {T > A, G, or C}]N.
-*4 possible starting nucleotides x 6 pyrimidine variants x 4 ending nucleotides = 96 total combinations.*
+- Context 3: The dataframe contains all of the following the pyrimidine single nucleotide variants, N[{C > A, G, or T} or {T > A, G, or C}]N. *4 possible starting nucleotides x 6 pyrimidine variants x 4 ending nucleotides = 96 total combinations.*
 
-The sbs.1536.txt file contains all of the following the pyrimidine single nucleotide variants, NN[{C > A, G, or T} or {T > A, G, or C}]NN.
+- Context 5: The dataframe contains all of the following the pyrimidine single nucleotide variants, NN[{C > A, G, or T} or {T > A, G, or C}]NN.
 *16 (4x4) possible starting nucleotides x 6 pyrimidine variants x 16 (4x4) possible ending nucleotides = 1536 total combinations.*
 
-The sbs.24576.txt file contains all of the following the pyrimidine single nucleotide variants, NNN[{C > A, G, or T} or {T > A, G, or C}]NNN.
+- Context 7: The dataframe contains all of the following the pyrimidine single nucleotide variants, NNN[{C > A, G, or T} or {T > A, G, or C}]NNN.
 *64 (4x4x4) nucleotides x 6 pyrimidine variants x 64 (4x4x4) possible ending dinucleotides = 24576 total combinations.*
 
+
 ```python
 from sbsgenerator import generator
 # Context number (must be larger than 3 and uneven)
 context_size = 7
 # List with all the vcf files
-vcf_files = [str(Path(__file__).parent / "files" / "test.vcf")]
+vcf_files = ["data/test.vcf"]
 # Where the ref genomes will be downloaded to
-ref_genome = Path(__file__).parent / "files"
+ref_genome = "temp/ref_genomes"
 sbsgen = generator.SBSGenerator(
     context=context_size,
     vcf_files=vcf_files,
-    ref_genome=Path(__file__).parent / "files"
+    ref_genome=ref_genome
 )
 sbsgen.count_mutations()
 ```
 
 ## Contributing
 
-I welcome contributions to SBSGen! If you have suggestions for improvements or bug fixes, please open an issue or submit a pull request.
+I welcome contributions to SBSGenerator! If you have suggestions for improvements or bug fixes, please open an issue or submit a pull request.
 
 ## License
 
-SBSGen is released under the MIT License. See the LICENSE file for more details.
+SBSGenerator is released under the MIT License. See the LICENSE file for more details.

pyproject.toml

@@ -4,11 +4,32 @@ build-backend = "maturin"
 
 [project]
 name = "sbsgenerator"
+description = "Blazingly fast SBS matrix generator library"
+readme = "README.md"
+authors = [
+  { name = "Jan Alfonso Busker", email = "alfonsobusker@gmail.com" },
+]
+license = { file = "LICENSE" }
+repository = "https://github.com/AlfonsoJan/sbsgenerator"
 requires-python = ">=3.8"
+keywords = ["sbs", "matrix", "sbsgenerator", "Single Base Substitution", "bioinformatics", "genomics", "genetics", "biology", "sequence", "sequence analysis"]
 classifiers = [
-    "Programming Language :: Rust",
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: MacOS",
+    "Operating System :: Microsoft :: Windows",
+    "Operating System :: POSIX :: Linux",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
     "Programming Language :: Python :: Implementation :: CPython",
-    "Programming Language :: Python :: Implementation :: PyPy",
+    "Programming Language :: Python",
+    "Programming Language :: Rust",
 ]
 dependencies = [
     "numpy == 1.23.1",

python/sbsgenerator/generator.py

@@ -21,6 +21,7 @@
 import itertools
 from pathlib import Path
 import math
+from functools import wraps
 
 import numpy as np
 import pandas as pd
@@ -82,26 +83,56 @@ def increase_mutations(context: int) -> list[str]:
 	return new_mutations
 
 
-class NoCorrectSBSMutationsFound(Exception):
+class NotCorrectSBSMutationsFound(Exception):
 	"""Exception raised when no correct SBS mutations are found."""
 
 	pass
 
 
+class NotADirectoryError(Exception):
+	"""Exception raised when the argument is not a folder."""
+
+	pass
+
+
+def validate_input(func):
+	@wraps(func)
+	def wrapper(context, vcf_files, ref_genome, **kwargs):
+		# Check if context is an odd number greater than 1 and an integer
+		if not isinstance(context, int) or context < 2 or context % 2 == 0:
+			raise ValueError("Context must be an odd number greater than 1.")
+		# Ensure vcf_files is a list or tuple
+		if not isinstance(vcf_files, (list, tuple)):
+			raise TypeError("Input 'vcf_files' must be a list or tuple.")
+		# Verify that vcf_files contain existing file paths
+		exist_vcf_files = [str(vcf_file) for vcf_file in vcf_files if Path(vcf_file).exists()]
+		if len(exist_vcf_files) < len(vcf_files):
+			missing_files = set(vcf_files) - set(exist_vcf_files)
+			raise FileNotFoundError(f"The following files do not exist: {', '.join(missing_files)}")
+		# Normalize ref_genome to a Path object, ensuring it exists
+		ref_genome_path = Path(ref_genome)
+		if not ref_genome_path.is_dir():
+			raise NotADirectoryError("This argument must be a folder.")
+		return func(context, vcf_files, ref_genome_path, **kwargs)
+
+	return wrapper
+
+
+@validate_input
 class SBSGenerator:
-	def __init__(self, context: int, vcf_files: list[str], ref_genome: str) -> None:
+	def __init__(self, context: int, vcf_files: list[str], ref_genome: Path) -> None:
 		"""
 		Initialize the Generator object.
 
 		Args:
 		    context (int): The context value.
 		    vcf_files (list[str]): List of VCF file paths.
-		    ref_genome (str): Path to the reference genome.
+		    ref_genome (Path): Path to the reference genome.
 
 		Returns:
 		    None
 		"""
-		download.download_ref_genomes(Path(ref_genome))
+		download.download_ref_genomes(ref_genome)
 		self._logger = logging.SingletonLogger()
 		self.context = context
 		self.vcf_files = vcf_files
@@ -133,7 +164,7 @@ def parse_vcf_files(self, vcf_files) -> tuple[np.ndarray, np.ndarray]:
 		self._logger.log_info("Parsing VCF files")
 		filtered_vcf = parse_vcf_files(vcf_files, str(self.ref_genome), self.context)
 		if filtered_vcf.shape[0] == 0:
-			raise NoCorrectSBSMutationsFound("No correct SBS mutations found in VCF files")
+			raise NotCorrectSBSMutationsFound("No correct SBS mutations found in VCF files")
 		samples = np.unique(filtered_vcf[:, 0])
 		self._logger.log_info("Done parsing VCF files")
 		return filtered_vcf, samples

python/tests/test_sbsgenerator.py

@@ -49,21 +49,21 @@ def test_sbsgenerator_with_context(context_size: int, expected_shape: tuple[int,
 		3,  # For context size 3
 	],
 )
-def test_bad_sbsgenerator(context_size: int) -> None:
+def test_bad_vcf_sbsgenerator(context_size: int) -> None:
 	"""
 	Test case for the SBSGenerator class when no correct SBS mutations are found in VCF files.
 
 	Args:
 	    context_size (int): The size of the context to consider for SBS mutations.
 
 	Raises:
-	    generator.NoCorrectSBSMutationsFound: If no correct SBS mutations are found in the VCF files.
+	    generator.NotCorrectSBSMutationsFound: If no correct SBS mutations are found in the VCF files.
 
 	Returns:
 	    None
 	"""
 	with pytest.raises(
-		generator.NoCorrectSBSMutationsFound,
+		generator.NotCorrectSBSMutationsFound,
 		match="No correct SBS mutations found in VCF files",
 	) as _:
 		sbsgen = generator.SBSGenerator(
@@ -72,3 +72,52 @@ def test_bad_sbsgenerator(context_size: int) -> None:
 			ref_genome=Path(__file__).parent / "files",
 		)
 		sbsgen.count_mutations()
+
+
+def test_bad_context() -> None:
+	"""
+	Test case for when the context is invalid.
+
+	This test ensures that a ValueError is raised when the context is not an odd number greater than 1.
+	"""
+	with pytest.raises(
+		ValueError,
+		match="Context must be an odd number greater than 1.",
+	) as _:
+		generator.SBSGenerator(
+			context=1,
+			vcf_files=[str(Path(__file__).parent / "files" / "bad_test.vcf")],
+			ref_genome=Path(__file__).parent / "files",
+		)
+
+
+def test_file_does_not_exist() -> None:
+	"""
+	Test case to verify that the SBSGenerator raises a FileNotFoundError
+	when the specified VCF file does not exist.
+	"""
+	vcf_file = str(Path(__file__).parent / "files" / "does_not_exist.vcf")
+	with pytest.raises(
+		FileNotFoundError,
+		match=f"The following files do not exist: {vcf_file}",
+	) as _:
+		generator.SBSGenerator(
+			context=3,
+			vcf_files=[vcf_file],
+			ref_genome=Path(__file__).parent / "files",
+		)
+
+
+def test_folder_is_a_file() -> None:
+	"""
+	Test case to verify that an exception is raised when the provided folder is actually a file.
+	"""
+	with pytest.raises(
+		generator.NotADirectoryError,
+		match=f"This argument must be a folder.",
+	) as _:
+		generator.SBSGenerator(
+			context=3,
+			vcf_files=[str(Path(__file__).parent / "files" / "bad_test.vcf")],
+			ref_genome=Path(__file__).parent / "files.txt",
+		)