seqmat 0.1.0__py3-none-any.whl

seqmat/__init__.py

@@ -0,0 +1,46 @@
+"""
+SeqMat - Lightning-fast genomic sequence matrix library
+
+A comprehensive Python library for genomic sequence analysis with full mutation tracking,
+splicing analysis, and sequence manipulation.
+"""
+
+__version__ = "0.1.0"
+__author__ = "Nicolas Lynn Vila"
+__email__ = "nicolasalynn@gmail.com"
+
+from .seqmat import SeqMat
+from .gene import Gene
+from .transcript import Transcript
+from .utils import (
+    setup_genomics_data, 
+    load_config, 
+    save_config,
+    list_available_organisms,
+    list_supported_organisms,
+    get_organism_info,
+    list_gene_biotypes,
+    count_genes,
+    get_gene_list,
+    data_summary,
+    print_data_summary,
+    search_genes
+)
+
+__all__ = [
+    "SeqMat",
+    "Gene", 
+    "Transcript",
+    "setup_genomics_data",
+    "load_config",
+    "save_config",
+    "list_available_organisms",
+    "list_supported_organisms", 
+    "get_organism_info",
+    "list_gene_biotypes",
+    "count_genes",
+    "get_gene_list",
+    "data_summary",
+    "print_data_summary",
+    "search_genes"
+]

seqmat/cli.py

@@ -0,0 +1,280 @@
+#!/usr/bin/env python3
+"""Command-line interface for SeqMat data management"""
+
+import argparse
+import sys
+from typing import Optional
+
+from .utils import (
+    setup_genomics_data,
+    print_data_summary,
+    list_available_organisms,
+    list_supported_organisms,
+    list_gene_biotypes,
+    count_genes,
+    get_gene_list,
+    search_genes,
+    get_organism_info
+)
+from .config import get_available_organisms, get_default_organism, get_organism_info as get_organism_config_info
+
+
+def cmd_setup(args):
+    """Setup genomics data for an organism"""
+    try:
+        setup_genomics_data(
+            basepath=args.path,
+            organism=args.organism,
+            force=args.force
+        )
+        print(f"✅ Successfully set up {args.organism} data in {args.path}")
+    except Exception as e:
+        print(f"❌ Error setting up data: {e}")
+        sys.exit(1)
+
+
+def cmd_list_organisms(args):
+    """List available and supported organisms"""
+    print("🌍 Organism Support Status:")
+    print("-" * 30)
+    
+    supported = list_supported_organisms()
+    configured = list_available_organisms()
+    
+    # Get organism names from config
+    organism_names = {}
+    for org in set(supported + configured):
+        try:
+            info = get_organism_config_info(org)
+            organism_names[org] = info.get('name', org)
+        except:
+            organism_names[org] = org
+    
+    for org in supported:
+        name = organism_names.get(org, org)
+        status = "✅ Configured" if org in configured else "❌ Not configured"
+        print(f"{org}: {name} - {status}")
+    
+    if not configured:
+        print("\nTo set up data, run:")
+        print("  seqmat-setup --path /your/data/path --organism hg38")
+
+
+def cmd_summary(args):
+    """Print data summary"""
+    print_data_summary()
+
+
+def cmd_biotypes(args):
+    """List gene biotypes for an organism"""
+    if not args.organism:
+        print("❌ Please specify an organism with --organism")
+        sys.exit(1)
+    
+    biotypes = list_gene_biotypes(args.organism)
+    
+    if not biotypes:
+        print(f"❌ No data found for organism '{args.organism}'")
+        print("Available organisms:", ", ".join(list_available_organisms()))
+        sys.exit(1)
+    
+    print(f"📊 Gene biotypes in {args.organism}:")
+    print("-" * 30)
+    
+    # Get counts for each biotype
+    counts = count_genes(args.organism)
+    
+    for biotype in biotypes:
+        count = counts.get(biotype, 0)
+        print(f"{biotype}: {count:,} genes")
+
+
+def cmd_count(args):
+    """Count genes for an organism/biotype"""
+    if not args.organism:
+        print("❌ Please specify an organism with --organism")
+        sys.exit(1)
+    
+    counts = count_genes(args.organism, args.biotype)
+    
+    if not counts:
+        print(f"❌ No data found for organism '{args.organism}'")
+        sys.exit(1)
+    
+    if args.biotype:
+        count = counts.get(args.biotype, 0)
+        print(f"📊 {args.organism} {args.biotype}: {count:,} genes")
+    else:
+        print(f"📊 Gene counts for {args.organism}:")
+        print("-" * 30)
+        total = 0
+        for biotype, count in sorted(counts.items()):
+            print(f"{biotype}: {count:,} genes")
+            total += count
+        print("-" * 30)
+        print(f"Total: {total:,} genes")
+
+
+def cmd_list_genes(args):
+    """List genes for an organism/biotype"""
+    if not args.organism or not args.biotype:
+        print("❌ Please specify both --organism and --biotype")
+        sys.exit(1)
+    
+    genes = get_gene_list(args.organism, args.biotype, limit=args.limit)
+    
+    if not genes:
+        print(f"❌ No genes found for {args.organism} {args.biotype}")
+        sys.exit(1)
+    
+    print(f"📋 {args.organism} {args.biotype} genes ({len(genes)} shown):")
+    print("-" * 50)
+    
+    for i, gene in enumerate(genes, 1):
+        print(f"{i:4d}. {gene}")
+    
+    if args.limit and len(genes) == args.limit:
+        total_count = count_genes(args.organism, args.biotype)
+        total = total_count.get(args.biotype, 0)
+        print(f"\n(Showing first {args.limit} of {total:,} total genes)")
+
+
+def cmd_search(args):
+    """Search for genes by name pattern"""
+    if not args.organism or not args.query:
+        print("❌ Please specify both --organism and --query")
+        sys.exit(1)
+    
+    results = search_genes(
+        organism=args.organism,
+        query=args.query,
+        biotype=args.biotype,
+        limit=args.limit
+    )
+    
+    if not results:
+        print(f"❌ No genes found matching '{args.query}' in {args.organism}")
+        sys.exit(1)
+    
+    print(f"🔍 Search results for '{args.query}' in {args.organism}:")
+    print("-" * 50)
+    
+    for i, result in enumerate(results, 1):
+        print(f"{i:2d}. {result['gene_name']} ({result['biotype']})")
+    
+    if len(results) == args.limit:
+        print(f"\n(Showing first {args.limit} results)")
+
+
+def cmd_info(args):
+    """Show detailed information about an organism"""
+    if not args.organism:
+        print("❌ Please specify an organism with --organism")
+        sys.exit(1)
+    
+    info = get_organism_info(args.organism)
+    
+    if "error" in info:
+        print(f"❌ {info['error']}")
+        sys.exit(1)
+    
+    print(f"ℹ️  Detailed information for {args.organism}:")
+    print("=" * 40)
+    
+    # Data availability
+    data_avail = info.get("data_available", {})
+    
+    if "gene_counts" in data_avail:
+        print("📊 Gene Data:")
+        total_genes = 0
+        for biotype, count in sorted(data_avail["gene_counts"].items()):
+            print(f"  {biotype}: {count:,} genes")
+            total_genes += count
+        print(f"  Total: {total_genes:,} genes")
+        print()
+    
+    if "chromosomes" in data_avail:
+        chroms = data_avail["chromosomes"]
+        print(f"🧬 Chromosome Data: {len(chroms)} chromosomes")
+        print(f"  Available: {', '.join(sorted(chroms))}")
+        print()
+    
+    print("📁 Data Paths:")
+    for path_name, path_value in info["paths"].items():
+        from pathlib import Path
+        exists = "✅" if Path(path_value).exists() else "❌"
+        print(f"  {path_name}: {exists} {path_value}")
+
+
+def main():
+    """Main CLI entry point"""
+    parser = argparse.ArgumentParser(
+        prog="seqmat",
+        description="SeqMat genomics data management CLI"
+    )
+    
+    subparsers = parser.add_subparsers(dest="command", help="Commands")
+    
+    # Setup command
+    setup_parser = subparsers.add_parser("setup", help="Set up genomics data")
+    setup_parser.add_argument("--path", required=True, help="Base path for data storage")
+    # Get available organisms dynamically
+    available_organisms = get_available_organisms()
+    default_organism = get_default_organism()
+    setup_parser.add_argument("--organism", default=default_organism, choices=available_organisms, 
+                             help=f"Organism to set up (default: {default_organism})")
+    setup_parser.add_argument("--force", action="store_true", help="Force overwrite existing data")
+    setup_parser.set_defaults(func=cmd_setup)
+    
+    # List organisms command
+    organisms_parser = subparsers.add_parser("organisms", help="List supported/configured organisms")
+    organisms_parser.set_defaults(func=cmd_list_organisms)
+    
+    # Summary command
+    summary_parser = subparsers.add_parser("summary", help="Show data summary")
+    summary_parser.set_defaults(func=cmd_summary)
+    
+    # Biotypes command
+    biotypes_parser = subparsers.add_parser("biotypes", help="List gene biotypes")
+    biotypes_parser.add_argument("--organism", help="Organism to query")
+    biotypes_parser.set_defaults(func=cmd_biotypes)
+    
+    # Count command
+    count_parser = subparsers.add_parser("count", help="Count genes")
+    count_parser.add_argument("--organism", help="Organism to query")
+    count_parser.add_argument("--biotype", help="Specific biotype to count")
+    count_parser.set_defaults(func=cmd_count)
+    
+    # List genes command
+    list_parser = subparsers.add_parser("list", help="List genes")
+    list_parser.add_argument("--organism", help="Organism to query")
+    list_parser.add_argument("--biotype", help="Gene biotype")
+    list_parser.add_argument("--limit", type=int, default=50, help="Maximum genes to show")
+    list_parser.set_defaults(func=cmd_list_genes)
+    
+    # Search command
+    search_parser = subparsers.add_parser("search", help="Search genes by name")
+    search_parser.add_argument("--organism", help="Organism to search")
+    search_parser.add_argument("--query", help="Gene name pattern to search")
+    search_parser.add_argument("--biotype", help="Filter by biotype")
+    search_parser.add_argument("--limit", type=int, default=20, help="Maximum results")
+    search_parser.set_defaults(func=cmd_search)
+    
+    # Info command
+    info_parser = subparsers.add_parser("info", help="Show organism information")
+    info_parser.add_argument("--organism", help="Organism to query")
+    info_parser.set_defaults(func=cmd_info)
+    
+    # Parse arguments
+    args = parser.parse_args()
+    
+    if not args.command:
+        parser.print_help()
+        sys.exit(1)
+    
+    # Execute command
+    args.func(args)
+
+
+if __name__ == "__main__":
+    main()

seqmat/config.py

@@ -0,0 +1,100 @@
+"""Configuration management for SeqMat"""
+import os
+import json
+from pathlib import Path
+from typing import Dict, Any, List, Optional
+
+DEFAULT_CONFIG_DIR = Path.home() / '.seqmat'
+CONFIG_FILE = DEFAULT_CONFIG_DIR / 'config.json'
+
+# Default organism data sources - can be overridden in config
+DEFAULT_ORGANISM_DATA = {
+    'hg38': {
+        'name': 'Homo sapiens (Human)',
+        'urls': {
+            'fasta': 'https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/latest/hg38.fa.gz',
+            'gtf': 'https://ftp.ensembl.org/pub/release-111/gtf/homo_sapiens/Homo_sapiens.GRCh38.111.gtf.gz',
+            'conservation': 'https://genome-data-public-access.s3.eu-north-1.amazonaws.com/conservation.pkl',
+            'gtex': 'https://storage.googleapis.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_median_tpm.gct.gz'
+        }
+    },
+    'mm39': {
+        'name': 'Mus musculus (Mouse)',
+        'urls': {
+            'fasta': 'https://hgdownload.soe.ucsc.edu/goldenPath/mm39/bigZips/mm39.fa.gz',
+            'gtf': 'https://ftp.ensembl.org/pub/release-112/gtf/mus_musculus/Mus_musculus.GRCm39.112.gtf.gz'
+        }
+    }
+}
+
+DEFAULT_SETTINGS = {
+    'default_organism': 'hg38',
+    'directory_structure': {
+        'chromosomes': 'chromosomes',
+        'annotations': 'annotations'
+    }
+}
+
+def load_config() -> Dict[str, Any]:
+    """Load configuration from user's home directory"""
+    if CONFIG_FILE.exists():
+        with open(CONFIG_FILE, 'r') as f:
+            config = json.load(f)
+            # Merge with default settings
+            merged_config = DEFAULT_SETTINGS.copy()
+            merged_config.update(config)
+            return merged_config
+    return DEFAULT_SETTINGS.copy()
+
+def save_config(config: Dict[str, Any]) -> None:
+    """Save configuration to user's home directory"""
+    DEFAULT_CONFIG_DIR.mkdir(exist_ok=True)
+    with open(CONFIG_FILE, 'w') as f:
+        json.dump(config, f, indent=2)
+
+def get_default_organism() -> str:
+    """Get the default organism from config or fallback"""
+    config = load_config()
+    return config.get('default_organism', DEFAULT_SETTINGS['default_organism'])
+
+def get_available_organisms() -> List[str]:
+    """Get list of available organisms from config and defaults"""
+    config = load_config()
+    configured_organisms = set(config.keys()) - {'default_organism', 'directory_structure'}
+    default_organisms = set(DEFAULT_ORGANISM_DATA.keys())
+    return sorted(configured_organisms | default_organisms)
+
+def get_organism_info(organism: str) -> Dict[str, Any]:
+    """Get organism information including name and URLs"""
+    config = load_config()
+    
+    if organism in config and isinstance(config[organism], dict):
+        org_config = config[organism]
+        # Merge with defaults if available
+        if organism in DEFAULT_ORGANISM_DATA:
+            default_data = DEFAULT_ORGANISM_DATA[organism].copy()
+            default_data.update(org_config)
+            return default_data
+        return org_config
+    elif organism in DEFAULT_ORGANISM_DATA:
+        return DEFAULT_ORGANISM_DATA[organism]
+    else:
+        raise ValueError(f"Organism '{organism}' not configured. Available: {get_available_organisms()}")
+
+def get_organism_config(organism: Optional[str] = None) -> Dict[str, Path]:
+    """Get configuration paths for a specific organism"""
+    if organism is None:
+        organism = get_default_organism()
+        
+    config = load_config()
+    if organism not in config:
+        raise ValueError(f"Organism '{organism}' not configured. Run setup_genomics_data() first.")
+    
+    # Convert string paths to Path objects
+    org_config = config[organism]
+    return {k: Path(v) for k, v in org_config.items() if isinstance(v, str)}
+
+def get_directory_config() -> Dict[str, str]:
+    """Get directory structure configuration"""
+    config = load_config()
+    return config.get('directory_structure', DEFAULT_SETTINGS['directory_structure'])

seqmat/gene.py

@@ -0,0 +1,178 @@
+"""Gene class for representing genomic genes with associated transcripts"""
+import copy
+from typing import Any, Dict, List, Tuple, Optional, Iterator, Union
+from collections import Counter
+from pathlib import Path
+
+from .config import get_organism_config, get_default_organism
+from .utils import unload_pickle
+from .transcript import Transcript
+
+
+class Gene:
+    """
+    A class representing a Gene, with associated transcripts and metadata.
+
+    Attributes:
+        organism (str): The organism build (e.g. 'hg38').
+        transcripts (dict): A dictionary of transcript annotations keyed by transcript ID.
+        gene_name (str): The name of the gene.
+        gene_id (str): The unique identifier for the gene.
+        chrm (str): The chromosome on which the gene resides.
+        rev (bool): Whether the gene is on the reverse strand.
+    """
+
+    def __init__(self, gene_name: str, gene_id: str, rev: bool, chrm: str, 
+                 transcripts: Optional[Dict[str, Any]] = None, organism: Optional[str] = None):
+        """
+        Initialize a Gene instance.
+
+        Args:
+            gene_name: Name of the gene
+            gene_id: Unique identifier for the gene
+            rev: Whether gene is on reverse strand
+            chrm: Chromosome identifier
+            transcripts: Dictionary of transcript annotations
+            organism: Organism reference build (default from config)
+        """
+        self.gene_name = gene_name
+        self.gene_id = gene_id
+        self.rev = rev
+        self.chrm = chrm
+        self.organism = organism if organism is not None else get_default_organism()
+        self.transcripts = transcripts if transcripts is not None else {}
+
+    def __repr__(self) -> str:
+        """Official string representation of the Gene object."""
+        return f"Gene({self.gene_name})"
+
+    def __str__(self) -> str:
+        """User-friendly string representation of the Gene object."""
+        return f"Gene: {self.gene_name}, ID: {self.gene_id}, Chr: {self.chrm}, Transcripts: {len(self.transcripts)}"
+
+    def __len__(self) -> int:
+        """Returns the number of transcripts associated with this gene."""
+        return len(self.transcripts)
+
+    def __copy__(self):
+        """Returns a shallow copy of the Gene object."""
+        return copy.copy(self)
+
+    def __deepcopy__(self, memo):
+        """Returns a deep copy of the Gene object."""
+        return copy.deepcopy(self, memo)
+
+    def __iter__(self) -> Iterator[Transcript]:
+        """Allow iteration over the gene's transcripts, yielding Transcript objects."""
+        for tid, annotations in self.transcripts.items():
+            yield Transcript(annotations, organism=self.organism)
+
+    def __getitem__(self, item: str) -> Optional[Transcript]:
+        """Get a transcript by ID."""
+        if item not in self.transcripts:
+            print(f"{item} not an annotated transcript of this gene.")
+            return None
+        return Transcript(self.transcripts[item], organism=self.organism)
+
+    @classmethod
+    def from_file(cls, gene_name: str, organism: Optional[str] = None) -> Optional['Gene']:
+        """
+        Load gene data from file.
+        
+        Args:
+            gene_name: Name of the gene to load
+            organism: Organism reference build
+            
+        Returns:
+            Gene object or None if not found
+        """
+        if organism is None:
+            organism = get_default_organism()
+        try:
+            config = get_organism_config(organism)
+        except ValueError:
+            print(f"Organism '{organism}' not configured. Run setup_genomics_data() first.")
+            return None
+            
+        # Find gene data files in the configured organism MRNA path
+        gene_files = list((config['MRNA_PATH'] / 'protein_coding').glob(f'*_{gene_name}.pkl'))
+        if not gene_files:
+            print(f"No files available for gene '{gene_name}'.")
+            return None
+
+        # Load gene data from the first matching file
+        data = unload_pickle(gene_files[0])
+        
+        return cls(
+            gene_name=data.get('gene_name'),
+            gene_id=data.get('gene_id'),
+            rev=data.get('rev'),
+            chrm=data.get('chrm'),
+            transcripts=data.get('transcripts', {}),
+            organism=organism
+        )
+
+    def splice_sites(self) -> Tuple[Counter, Counter]:
+        """
+        Aggregates splice sites (acceptors and donors) from all transcripts.
+
+        Returns:
+            tuple(Counter, Counter): A tuple of two Counters for acceptors and donors.
+        """
+        acceptors: List[Any] = []
+        donors: List[Any] = []
+
+        # Collect acceptor and donor sites from each transcript
+        for transcript in self.transcripts.values():
+            acceptors.extend(transcript.get('acceptors', []))
+            donors.extend(transcript.get('donors', []))
+
+        return Counter(acceptors), Counter(donors)
+
+    def transcript(self, tid: Optional[str] = None) -> Optional[Transcript]:
+        """
+        Retrieve a Transcript object by ID, or the primary transcript if no ID is given.
+
+        Args:
+            tid: Transcript ID. If None, returns primary transcript.
+
+        Returns:
+            The Transcript object with the given ID or the primary transcript.
+        """
+        if tid is None:
+            tid = self.primary_transcript
+            
+        if tid is None or tid not in self.transcripts:
+            return None
+
+        return Transcript(self.transcripts[tid], organism=self.organism)
+
+    @property
+    def primary_transcript(self) -> Optional[str]:
+        """
+        Returns the primary transcript ID for this gene.
+        
+        Returns:
+            The primary transcript ID or None if not available.
+        """
+        # If already calculated, return it
+        if hasattr(self, '_primary_transcript'):
+            return self._primary_transcript
+
+        # Try to find a primary transcript
+        primary_transcripts = [k for k, v in self.transcripts.items() 
+                             if v.get('primary_transcript')]
+        if primary_transcripts:
+            self._primary_transcript = primary_transcripts[0]
+            return self._primary_transcript
+
+        # Fallback: find a protein-coding transcript
+        protein_coding = [k for k, v in self.transcripts.items() 
+                        if v.get('transcript_biotype') == 'protein_coding']
+        if protein_coding:
+            self._primary_transcript = protein_coding[0]
+            return self._primary_transcript
+
+        # No primary or protein-coding transcript found
+        self._primary_transcript = None
+        return None