valuesets 0.3.1__py3-none-any.whl

valuesets/enums/bio/sequencing_platforms.py

@@ -0,0 +1,302 @@
+"""
+Sequencing Platform Value Sets
+
+Value sets for DNA/RNA sequencing platforms, technologies, and methodologies
+
+Generated from: bio/sequencing_platforms.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class SequencingPlatform(RichEnum):
+    """
+    Major DNA/RNA sequencing platforms and instruments used in genomics research
+    """
+    # Enum members
+    ILLUMINA_HISEQ_2000 = "ILLUMINA_HISEQ_2000"
+    ILLUMINA_HISEQ_2500 = "ILLUMINA_HISEQ_2500"
+    ILLUMINA_HISEQ_3000 = "ILLUMINA_HISEQ_3000"
+    ILLUMINA_HISEQ_4000 = "ILLUMINA_HISEQ_4000"
+    ILLUMINA_HISEQ_X = "ILLUMINA_HISEQ_X"
+    ILLUMINA_NOVASEQ_6000 = "ILLUMINA_NOVASEQ_6000"
+    ILLUMINA_NEXTSEQ_500 = "ILLUMINA_NEXTSEQ_500"
+    ILLUMINA_NEXTSEQ_550 = "ILLUMINA_NEXTSEQ_550"
+    ILLUMINA_NEXTSEQ_1000 = "ILLUMINA_NEXTSEQ_1000"
+    ILLUMINA_NEXTSEQ_2000 = "ILLUMINA_NEXTSEQ_2000"
+    ILLUMINA_MISEQ = "ILLUMINA_MISEQ"
+    ILLUMINA_ISEQ_100 = "ILLUMINA_ISEQ_100"
+    PACBIO_RS = "PACBIO_RS"
+    PACBIO_RS_II = "PACBIO_RS_II"
+    PACBIO_SEQUEL = "PACBIO_SEQUEL"
+    PACBIO_SEQUEL_II = "PACBIO_SEQUEL_II"
+    PACBIO_REVIO = "PACBIO_REVIO"
+    NANOPORE_MINION = "NANOPORE_MINION"
+    NANOPORE_GRIDION = "NANOPORE_GRIDION"
+    NANOPORE_PROMETHION = "NANOPORE_PROMETHION"
+    NANOPORE_FLONGLE = "NANOPORE_FLONGLE"
+    ELEMENT_AVITI = "ELEMENT_AVITI"
+    MGI_DNBSEQ_T7 = "MGI_DNBSEQ_T7"
+    MGI_DNBSEQ_G400 = "MGI_DNBSEQ_G400"
+    MGI_DNBSEQ_G50 = "MGI_DNBSEQ_G50"
+    SANGER_SEQUENCING = "SANGER_SEQUENCING"
+    ROCHE_454_GS = "ROCHE_454_GS"
+    LIFE_TECHNOLOGIES_ION_TORRENT = "LIFE_TECHNOLOGIES_ION_TORRENT"
+    ABI_SOLID = "ABI_SOLID"
+
+# Set metadata after class creation
+SequencingPlatform._metadata = {
+    "ILLUMINA_HISEQ_2000": {'description': 'Illumina HiSeq 2000', 'meaning': 'OBI:0002001', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_HISEQ_2500": {'description': 'Illumina HiSeq 2500', 'meaning': 'OBI:0002002', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_HISEQ_3000": {'description': 'Illumina HiSeq 3000', 'meaning': 'OBI:0002048', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_HISEQ_4000": {'description': 'Illumina HiSeq 4000', 'meaning': 'OBI:0002049', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_HISEQ_X": {'description': 'Illumina HiSeq X', 'meaning': 'OBI:0002129', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}, 'aliases': ['Illumina HiSeq X Ten']},
+    "ILLUMINA_NOVASEQ_6000": {'description': 'Illumina NovaSeq 6000', 'meaning': 'OBI:0002630', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_NEXTSEQ_500": {'description': 'Illumina NextSeq 500', 'meaning': 'OBI:0002021', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_NEXTSEQ_550": {'description': 'Illumina NextSeq 550', 'meaning': 'OBI:0003387', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_NEXTSEQ_1000": {'description': 'Illumina NextSeq 1000', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_NEXTSEQ_2000": {'description': 'Illumina NextSeq 2000', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_MISEQ": {'description': 'Illumina MiSeq', 'meaning': 'OBI:0002003', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "ILLUMINA_ISEQ_100": {'description': 'Illumina iSeq 100', 'annotations': {'manufacturer': 'Illumina', 'read_type': 'short', 'chemistry': 'sequencing by synthesis'}},
+    "PACBIO_RS": {'description': 'PacBio RS', 'annotations': {'manufacturer': 'Pacific Biosciences', 'read_type': 'long', 'chemistry': 'single molecule real time'}},
+    "PACBIO_RS_II": {'description': 'PacBio RS II', 'meaning': 'OBI:0002012', 'annotations': {'manufacturer': 'Pacific Biosciences', 'read_type': 'long', 'chemistry': 'single molecule real time'}},
+    "PACBIO_SEQUEL": {'description': 'PacBio Sequel', 'meaning': 'OBI:0002632', 'annotations': {'manufacturer': 'Pacific Biosciences', 'read_type': 'long', 'chemistry': 'single molecule real time'}},
+    "PACBIO_SEQUEL_II": {'description': 'PacBio Sequel II', 'meaning': 'OBI:0002633', 'annotations': {'manufacturer': 'Pacific Biosciences', 'read_type': 'long', 'chemistry': 'single molecule real time'}},
+    "PACBIO_REVIO": {'description': 'PacBio Revio', 'annotations': {'manufacturer': 'Pacific Biosciences', 'read_type': 'long', 'chemistry': 'single molecule real time'}},
+    "NANOPORE_MINION": {'description': 'Oxford Nanopore MinION', 'meaning': 'OBI:0002750', 'annotations': {'manufacturer': 'Oxford Nanopore Technologies', 'read_type': 'long', 'chemistry': 'nanopore sequencing'}, 'aliases': ['Oxford Nanopore MinION']},
+    "NANOPORE_GRIDION": {'description': 'Oxford Nanopore GridION', 'meaning': 'OBI:0002751', 'annotations': {'manufacturer': 'Oxford Nanopore Technologies', 'read_type': 'long', 'chemistry': 'nanopore sequencing'}, 'aliases': ['Oxford Nanopore GridION Mk1']},
+    "NANOPORE_PROMETHION": {'description': 'Oxford Nanopore PromethION', 'meaning': 'OBI:0002752', 'annotations': {'manufacturer': 'Oxford Nanopore Technologies', 'read_type': 'long', 'chemistry': 'nanopore sequencing'}, 'aliases': ['Oxford Nanopore PromethION']},
+    "NANOPORE_FLONGLE": {'description': 'Oxford Nanopore Flongle', 'annotations': {'manufacturer': 'Oxford Nanopore Technologies', 'read_type': 'long', 'chemistry': 'nanopore sequencing'}},
+    "ELEMENT_AVITI": {'description': 'Element Biosciences AVITI', 'annotations': {'manufacturer': 'Element Biosciences', 'read_type': 'short', 'chemistry': 'sequencing by avidity'}},
+    "MGI_DNBSEQ_T7": {'description': 'MGI DNBSEQ-T7', 'annotations': {'manufacturer': 'MGI/BGI', 'read_type': 'short', 'chemistry': 'DNA nanoball sequencing'}},
+    "MGI_DNBSEQ_G400": {'description': 'MGI DNBSEQ-G400', 'annotations': {'manufacturer': 'MGI/BGI', 'read_type': 'short', 'chemistry': 'DNA nanoball sequencing'}},
+    "MGI_DNBSEQ_G50": {'description': 'MGI DNBSEQ-G50', 'annotations': {'manufacturer': 'MGI/BGI', 'read_type': 'short', 'chemistry': 'DNA nanoball sequencing'}},
+    "SANGER_SEQUENCING": {'description': 'Sanger chain termination sequencing', 'meaning': 'OBI:0000695', 'annotations': {'manufacturer': 'Various', 'read_type': 'short', 'chemistry': 'chain termination'}, 'aliases': ['chain termination sequencing assay']},
+    "ROCHE_454_GS": {'description': 'Roche 454 Genome Sequencer', 'meaning': 'OBI:0000702', 'annotations': {'manufacturer': 'Roche/454', 'read_type': 'short', 'chemistry': 'pyrosequencing', 'status': 'discontinued'}, 'aliases': ['454 Genome Sequencer FLX']},
+    "LIFE_TECHNOLOGIES_ION_TORRENT": {'description': 'Life Technologies Ion Torrent', 'annotations': {'manufacturer': 'Life Technologies/Thermo Fisher', 'read_type': 'short', 'chemistry': 'semiconductor sequencing'}},
+    "ABI_SOLID": {'description': 'ABI SOLiD', 'annotations': {'manufacturer': 'Life Technologies/Applied Biosystems', 'read_type': 'short', 'chemistry': 'sequencing by ligation', 'status': 'discontinued'}},
+}
+
+class SequencingChemistry(RichEnum):
+    """
+    Fundamental chemical methods used for DNA/RNA sequencing
+    """
+    # Enum members
+    SEQUENCING_BY_SYNTHESIS = "SEQUENCING_BY_SYNTHESIS"
+    SINGLE_MOLECULE_REAL_TIME = "SINGLE_MOLECULE_REAL_TIME"
+    NANOPORE_SEQUENCING = "NANOPORE_SEQUENCING"
+    PYROSEQUENCING = "PYROSEQUENCING"
+    SEQUENCING_BY_LIGATION = "SEQUENCING_BY_LIGATION"
+    CHAIN_TERMINATION = "CHAIN_TERMINATION"
+    SEMICONDUCTOR_SEQUENCING = "SEMICONDUCTOR_SEQUENCING"
+    DNA_NANOBALL_SEQUENCING = "DNA_NANOBALL_SEQUENCING"
+    SEQUENCING_BY_AVIDITY = "SEQUENCING_BY_AVIDITY"
+
+# Set metadata after class creation
+SequencingChemistry._metadata = {
+    "SEQUENCING_BY_SYNTHESIS": {'description': 'Sequencing by synthesis (Illumina)', 'meaning': 'OBI:0000734', 'aliases': ['DNA sequencing by synthesis assay']},
+    "SINGLE_MOLECULE_REAL_TIME": {'description': 'Single molecule real-time sequencing (PacBio)'},
+    "NANOPORE_SEQUENCING": {'description': 'Nanopore sequencing (Oxford Nanopore)'},
+    "PYROSEQUENCING": {'description': 'Pyrosequencing (454)'},
+    "SEQUENCING_BY_LIGATION": {'description': 'Sequencing by ligation (SOLiD)', 'meaning': 'OBI:0000723', 'aliases': ['DNA sequencing by ligation assay']},
+    "CHAIN_TERMINATION": {'description': 'Chain termination method (Sanger)', 'meaning': 'OBI:0000695', 'aliases': ['chain termination sequencing assay']},
+    "SEMICONDUCTOR_SEQUENCING": {'description': 'Semiconductor/Ion semiconductor sequencing'},
+    "DNA_NANOBALL_SEQUENCING": {'description': 'DNA nanoball sequencing (MGI/BGI)'},
+    "SEQUENCING_BY_AVIDITY": {'description': 'Sequencing by avidity (Element Biosciences)'},
+}
+
+class LibraryPreparation(RichEnum):
+    """
+    Methods for preparing sequencing libraries from nucleic acid samples
+    """
+    # Enum members
+    GENOMIC_DNA = "GENOMIC_DNA"
+    WHOLE_GENOME_AMPLIFICATION = "WHOLE_GENOME_AMPLIFICATION"
+    PCR_AMPLICON = "PCR_AMPLICON"
+    RNA_SEQ = "RNA_SEQ"
+    SMALL_RNA_SEQ = "SMALL_RNA_SEQ"
+    SINGLE_CELL_RNA_SEQ = "SINGLE_CELL_RNA_SEQ"
+    ATAC_SEQ = "ATAC_SEQ"
+    CHIP_SEQ = "CHIP_SEQ"
+    BISULFITE_SEQ = "BISULFITE_SEQ"
+    HI_C = "HI_C"
+    CUT_AND_RUN = "CUT_AND_RUN"
+    CUT_AND_TAG = "CUT_AND_TAG"
+    CAPTURE_SEQUENCING = "CAPTURE_SEQUENCING"
+    EXOME_SEQUENCING = "EXOME_SEQUENCING"
+    METAGENOMICS = "METAGENOMICS"
+    AMPLICON_SEQUENCING = "AMPLICON_SEQUENCING"
+    DIRECT_RNA = "DIRECT_RNA"
+    CDNA_SEQUENCING = "CDNA_SEQUENCING"
+    RIBOSOME_PROFILING = "RIBOSOME_PROFILING"
+
+# Set metadata after class creation
+LibraryPreparation._metadata = {
+    "GENOMIC_DNA": {'description': 'Genomic DNA library preparation'},
+    "WHOLE_GENOME_AMPLIFICATION": {'description': 'Whole genome amplification (WGA)'},
+    "PCR_AMPLICON": {'description': 'PCR amplicon sequencing'},
+    "RNA_SEQ": {'description': 'RNA sequencing library prep'},
+    "SMALL_RNA_SEQ": {'description': 'Small RNA sequencing'},
+    "SINGLE_CELL_RNA_SEQ": {'description': 'Single-cell RNA sequencing'},
+    "ATAC_SEQ": {'description': 'ATAC-seq (chromatin accessibility)'},
+    "CHIP_SEQ": {'description': 'ChIP-seq (chromatin immunoprecipitation)'},
+    "BISULFITE_SEQ": {'description': 'Bisulfite sequencing (methylation)'},
+    "HI_C": {'description': 'Hi-C (chromosome conformation capture)'},
+    "CUT_AND_RUN": {'description': 'CUT&RUN (chromatin profiling)'},
+    "CUT_AND_TAG": {'description': 'CUT&Tag (chromatin profiling)'},
+    "CAPTURE_SEQUENCING": {'description': 'Target capture/enrichment sequencing'},
+    "EXOME_SEQUENCING": {'description': 'Whole exome sequencing'},
+    "METAGENOMICS": {'description': 'Metagenomic sequencing'},
+    "AMPLICON_SEQUENCING": {'description': '16S/ITS amplicon sequencing'},
+    "DIRECT_RNA": {'description': 'Direct RNA sequencing (nanopore)'},
+    "CDNA_SEQUENCING": {'description': 'cDNA sequencing'},
+    "RIBOSOME_PROFILING": {'description': 'Ribosome profiling (Ribo-seq)'},
+}
+
+class SequencingApplication(RichEnum):
+    """
+    Primary applications or assays using DNA/RNA sequencing
+    """
+    # Enum members
+    WHOLE_GENOME_SEQUENCING = "WHOLE_GENOME_SEQUENCING"
+    WHOLE_EXOME_SEQUENCING = "WHOLE_EXOME_SEQUENCING"
+    TRANSCRIPTOME_SEQUENCING = "TRANSCRIPTOME_SEQUENCING"
+    TARGETED_SEQUENCING = "TARGETED_SEQUENCING"
+    EPIGENOMICS = "EPIGENOMICS"
+    METAGENOMICS = "METAGENOMICS"
+    SINGLE_CELL_GENOMICS = "SINGLE_CELL_GENOMICS"
+    SINGLE_CELL_TRANSCRIPTOMICS = "SINGLE_CELL_TRANSCRIPTOMICS"
+    CHROMATIN_IMMUNOPRECIPITATION = "CHROMATIN_IMMUNOPRECIPITATION"
+    CHROMATIN_ACCESSIBILITY = "CHROMATIN_ACCESSIBILITY"
+    DNA_METHYLATION = "DNA_METHYLATION"
+    CHROMOSOME_CONFORMATION = "CHROMOSOME_CONFORMATION"
+    VARIANT_CALLING = "VARIANT_CALLING"
+    PHARMACOGENOMICS = "PHARMACOGENOMICS"
+    CLINICAL_DIAGNOSTICS = "CLINICAL_DIAGNOSTICS"
+    POPULATION_GENOMICS = "POPULATION_GENOMICS"
+
+# Set metadata after class creation
+SequencingApplication._metadata = {
+    "WHOLE_GENOME_SEQUENCING": {'description': 'Whole genome sequencing (WGS)', 'meaning': 'EDAM:topic_3673'},
+    "WHOLE_EXOME_SEQUENCING": {'description': 'Whole exome sequencing (WES)', 'meaning': 'EDAM:topic_3676', 'aliases': ['Exome sequencing']},
+    "TRANSCRIPTOME_SEQUENCING": {'description': 'RNA sequencing (RNA-seq)', 'meaning': 'EDAM:topic_3170', 'aliases': ['RNA-Seq']},
+    "TARGETED_SEQUENCING": {'description': 'Targeted gene panel sequencing'},
+    "EPIGENOMICS": {'description': 'Epigenomic profiling'},
+    "METAGENOMICS": {'description': 'Metagenomic sequencing', 'meaning': 'EDAM:topic_3837', 'aliases': ['Metagenomic sequencing']},
+    "SINGLE_CELL_GENOMICS": {'description': 'Single-cell genomics'},
+    "SINGLE_CELL_TRANSCRIPTOMICS": {'description': 'Single-cell transcriptomics', 'meaning': 'EDAM:topic_4028', 'aliases': ['Single-cell sequencing']},
+    "CHROMATIN_IMMUNOPRECIPITATION": {'description': 'ChIP-seq', 'meaning': 'EDAM:topic_3656', 'aliases': ['Immunoprecipitation experiment']},
+    "CHROMATIN_ACCESSIBILITY": {'description': 'ATAC-seq/FAIRE-seq'},
+    "DNA_METHYLATION": {'description': 'Bisulfite/methylation sequencing'},
+    "CHROMOSOME_CONFORMATION": {'description': 'Hi-C/3C-seq'},
+    "VARIANT_CALLING": {'description': 'Genetic variant discovery'},
+    "PHARMACOGENOMICS": {'description': 'Pharmacogenomic sequencing'},
+    "CLINICAL_DIAGNOSTICS": {'description': 'Clinical diagnostic sequencing'},
+    "POPULATION_GENOMICS": {'description': 'Population-scale genomics'},
+}
+
+class ReadType(RichEnum):
+    """
+    Configuration of sequencing reads generated by different platforms
+    """
+    # Enum members
+    SINGLE_END = "SINGLE_END"
+    PAIRED_END = "PAIRED_END"
+    MATE_PAIR = "MATE_PAIR"
+    LONG_READ = "LONG_READ"
+    ULTRA_LONG_READ = "ULTRA_LONG_READ"
+    CONTINUOUS_LONG_READ = "CONTINUOUS_LONG_READ"
+
+# Set metadata after class creation
+ReadType._metadata = {
+    "SINGLE_END": {'description': 'Single-end reads'},
+    "PAIRED_END": {'description': 'Paired-end reads'},
+    "MATE_PAIR": {'description': 'Mate-pair reads (large insert)'},
+    "LONG_READ": {'description': 'Long reads (>1kb typical)'},
+    "ULTRA_LONG_READ": {'description': 'Ultra-long reads (>10kb)'},
+    "CONTINUOUS_LONG_READ": {'description': 'Continuous long reads (nanopore)'},
+}
+
+class SequenceFileFormat(RichEnum):
+    """
+    Standard file formats used for storing sequence data
+    """
+    # Enum members
+    FASTA = "FASTA"
+    FASTQ = "FASTQ"
+    SAM = "SAM"
+    BAM = "BAM"
+    CRAM = "CRAM"
+    VCF = "VCF"
+    BCF = "BCF"
+    GFF3 = "GFF3"
+    GTF = "GTF"
+    BED = "BED"
+    BIGWIG = "BIGWIG"
+    BIGBED = "BIGBED"
+    HDF5 = "HDF5"
+    SFF = "SFF"
+    FAST5 = "FAST5"
+    POD5 = "POD5"
+
+# Set metadata after class creation
+SequenceFileFormat._metadata = {
+    "FASTA": {'description': 'FASTA sequence format', 'meaning': 'EDAM:format_1929', 'annotations': {'extensions': '.fa, .fasta, .fna, .ffn, .faa, .frn', 'content': 'sequences only'}},
+    "FASTQ": {'description': 'FASTQ sequence with quality format', 'meaning': 'EDAM:format_1930', 'annotations': {'extensions': '.fq, .fastq', 'content': 'sequences and quality scores'}},
+    "SAM": {'description': 'Sequence Alignment Map format', 'meaning': 'EDAM:format_2573', 'annotations': {'extensions': '.sam', 'content': 'aligned sequences (text)'}},
+    "BAM": {'description': 'Binary Alignment Map format', 'meaning': 'EDAM:format_2572', 'annotations': {'extensions': '.bam', 'content': 'aligned sequences (binary)'}},
+    "CRAM": {'description': 'Compressed Reference-oriented Alignment Map', 'annotations': {'extensions': '.cram', 'content': 'compressed aligned sequences'}},
+    "VCF": {'description': 'Variant Call Format', 'meaning': 'EDAM:format_3016', 'annotations': {'extensions': '.vcf', 'content': 'genetic variants'}},
+    "BCF": {'description': 'Binary Variant Call Format', 'meaning': 'EDAM:format_3020', 'annotations': {'extensions': '.bcf', 'content': 'genetic variants (binary)'}},
+    "GFF3": {'description': 'Generic Feature Format version 3', 'annotations': {'extensions': '.gff, .gff3', 'content': 'genomic annotations'}},
+    "GTF": {'description': 'Gene Transfer Format', 'annotations': {'extensions': '.gtf', 'content': 'gene annotations'}},
+    "BED": {'description': 'Browser Extensible Data format', 'annotations': {'extensions': '.bed', 'content': 'genomic intervals'}},
+    "BIGWIG": {'description': 'BigWig format for continuous data', 'annotations': {'extensions': '.bw, .bigwig', 'content': 'continuous genomic data'}},
+    "BIGBED": {'description': 'BigBed format for interval data', 'annotations': {'extensions': '.bb, .bigbed', 'content': 'genomic intervals (indexed)'}},
+    "HDF5": {'description': 'Hierarchical Data Format 5', 'annotations': {'extensions': '.h5, .hdf5', 'content': 'multi-dimensional arrays'}},
+    "SFF": {'description': 'Standard Flowgram Format (454)', 'meaning': 'EDAM:format_3284', 'annotations': {'extensions': '.sff', 'content': '454 sequencing data', 'status': 'legacy'}},
+    "FAST5": {'description': 'Fast5 format (Oxford Nanopore)', 'annotations': {'extensions': '.fast5', 'content': 'nanopore raw signal data'}},
+    "POD5": {'description': 'POD5 format (Oxford Nanopore, newer)', 'annotations': {'extensions': '.pod5', 'content': 'nanopore raw signal data (compressed)'}},
+}
+
+class DataProcessingLevel(RichEnum):
+    """
+    Levels of processing applied to raw sequencing data
+    """
+    # Enum members
+    RAW = "RAW"
+    QUALITY_FILTERED = "QUALITY_FILTERED"
+    TRIMMED = "TRIMMED"
+    ALIGNED = "ALIGNED"
+    DEDUPLICATED = "DEDUPLICATED"
+    RECALIBRATED = "RECALIBRATED"
+    VARIANT_CALLED = "VARIANT_CALLED"
+    NORMALIZED = "NORMALIZED"
+    ASSEMBLED = "ASSEMBLED"
+    ANNOTATED = "ANNOTATED"
+
+# Set metadata after class creation
+DataProcessingLevel._metadata = {
+    "RAW": {'description': 'Raw unprocessed sequencing reads'},
+    "QUALITY_FILTERED": {'description': 'Quality filtered reads'},
+    "TRIMMED": {'description': 'Adapter/quality trimmed reads'},
+    "ALIGNED": {'description': 'Aligned to reference genome'},
+    "DEDUPLICATED": {'description': 'PCR duplicates removed'},
+    "RECALIBRATED": {'description': 'Base quality score recalibrated'},
+    "VARIANT_CALLED": {'description': 'Variants called from alignments'},
+    "NORMALIZED": {'description': 'Expression normalized (RNA-seq)'},
+    "ASSEMBLED": {'description': 'De novo assembled sequences'},
+    "ANNOTATED": {'description': 'Functionally annotated sequences'},
+}
+
+__all__ = [
+    "SequencingPlatform",
+    "SequencingChemistry",
+    "LibraryPreparation",
+    "SequencingApplication",
+    "ReadType",
+    "SequenceFileFormat",
+    "DataProcessingLevel",
+]

valuesets/enums/bio/structural_biology.py

@@ -0,0 +1,320 @@
+"""
+Structural Biology Value Sets
+
+Value sets for structural biology techniques, including cryo-EM, X-ray crystallography, SAXS/SANS, mass spectrometry, and related sample preparation and data processing methods.
+
+
+Generated from: bio/structural_biology.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class SampleType(RichEnum):
+    """
+    Types of biological samples used in structural biology
+    """
+    # Enum members
+    PROTEIN = "PROTEIN"
+    NUCLEIC_ACID = "NUCLEIC_ACID"
+    PROTEIN_COMPLEX = "PROTEIN_COMPLEX"
+    MEMBRANE_PROTEIN = "MEMBRANE_PROTEIN"
+    VIRUS = "VIRUS"
+    ORGANELLE = "ORGANELLE"
+    CELL = "CELL"
+    TISSUE = "TISSUE"
+
+# Set metadata after class creation
+SampleType._metadata = {
+    "PROTEIN": {'description': 'Purified protein sample'},
+    "NUCLEIC_ACID": {'description': 'Nucleic acid sample (DNA or RNA)'},
+    "PROTEIN_COMPLEX": {'description': 'Protein-protein or protein-nucleic acid complex'},
+    "MEMBRANE_PROTEIN": {'description': 'Membrane-associated protein sample'},
+    "VIRUS": {'description': 'Viral particle or capsid'},
+    "ORGANELLE": {'description': 'Cellular organelle (mitochondria, chloroplast, etc.)'},
+    "CELL": {'description': 'Whole cell sample'},
+    "TISSUE": {'description': 'Tissue sample'},
+}
+
+class StructuralBiologyTechnique(RichEnum):
+    """
+    Structural biology experimental techniques
+    """
+    # Enum members
+    CRYO_EM = "CRYO_EM"
+    CRYO_ET = "CRYO_ET"
+    X_RAY_CRYSTALLOGRAPHY = "X_RAY_CRYSTALLOGRAPHY"
+    NEUTRON_CRYSTALLOGRAPHY = "NEUTRON_CRYSTALLOGRAPHY"
+    SAXS = "SAXS"
+    SANS = "SANS"
+    WAXS = "WAXS"
+    NMR = "NMR"
+    MASS_SPECTROMETRY = "MASS_SPECTROMETRY"
+    NEGATIVE_STAIN_EM = "NEGATIVE_STAIN_EM"
+
+# Set metadata after class creation
+StructuralBiologyTechnique._metadata = {
+    "CRYO_EM": {'description': 'Cryo-electron microscopy', 'meaning': 'CHMO:0002413', 'annotations': {'resolution_range': '2-30 Å typical', 'aliases': 'cryoEM, electron cryo-microscopy'}},
+    "CRYO_ET": {'description': 'Cryo-electron tomography', 'annotations': {'resolution_range': '20-100 Å typical', 'aliases': 'cryoET, electron cryo-tomography'}},
+    "X_RAY_CRYSTALLOGRAPHY": {'description': 'X-ray crystallography', 'meaning': 'CHMO:0000159', 'annotations': {'resolution_range': '1-4 Å typical', 'aliases': 'XRC, macromolecular crystallography'}},
+    "NEUTRON_CRYSTALLOGRAPHY": {'description': 'Neutron crystallography', 'annotations': {'advantages': 'hydrogen positions, deuteration studies'}},
+    "SAXS": {'description': 'Small-angle X-ray scattering', 'meaning': 'CHMO:0000204', 'annotations': {'information': 'low-resolution structure, conformational changes'}},
+    "SANS": {'description': 'Small-angle neutron scattering', 'annotations': {'advantages': 'contrast variation with deuteration'}},
+    "WAXS": {'description': 'Wide-angle X-ray scattering'},
+    "NMR": {'description': 'Nuclear magnetic resonance spectroscopy', 'meaning': 'CHMO:0000591', 'annotations': {'information': 'solution structure, dynamics'}},
+    "MASS_SPECTROMETRY": {'description': 'Mass spectrometry', 'meaning': 'CHMO:0000470', 'annotations': {'applications': 'native MS, crosslinking, HDX'}},
+    "NEGATIVE_STAIN_EM": {'description': 'Negative stain electron microscopy', 'annotations': {'resolution_range': '15-30 Å typical'}},
+}
+
+class CryoEMPreparationType(RichEnum):
+    """
+    Types of cryo-EM sample preparation
+    """
+    # Enum members
+    VITREOUS_ICE = "VITREOUS_ICE"
+    CRYO_SECTIONING = "CRYO_SECTIONING"
+    FREEZE_SUBSTITUTION = "FREEZE_SUBSTITUTION"
+    HIGH_PRESSURE_FREEZING = "HIGH_PRESSURE_FREEZING"
+
+# Set metadata after class creation
+CryoEMPreparationType._metadata = {
+    "VITREOUS_ICE": {'description': 'Sample embedded in vitreous ice'},
+    "CRYO_SECTIONING": {'description': 'Cryo-sectioned sample'},
+    "FREEZE_SUBSTITUTION": {'description': 'Freeze-substituted sample'},
+    "HIGH_PRESSURE_FREEZING": {'description': 'High-pressure frozen sample'},
+}
+
+class CryoEMGridType(RichEnum):
+    """
+    Types of electron microscopy grids
+    """
+    # Enum members
+    C_FLAT = "C_FLAT"
+    QUANTIFOIL = "QUANTIFOIL"
+    LACEY_CARBON = "LACEY_CARBON"
+    ULTRATHIN_CARBON = "ULTRATHIN_CARBON"
+    GOLD_GRID = "GOLD_GRID"
+    GRAPHENE_OXIDE = "GRAPHENE_OXIDE"
+
+# Set metadata after class creation
+CryoEMGridType._metadata = {
+    "C_FLAT": {'description': 'C-flat holey carbon grid', 'annotations': {'hole_sizes': '1.2/1.3, 2/1, 2/2 μm common', 'manufacturer': 'Protochips'}},
+    "QUANTIFOIL": {'description': 'Quantifoil holey carbon grid', 'annotations': {'hole_sizes': '1.2/1.3, 2/1, 2/2 μm common', 'manufacturer': 'Quantifoil'}},
+    "LACEY_CARBON": {'description': 'Lacey carbon support film', 'annotations': {'structure': 'irregular holes, thin carbon film'}},
+    "ULTRATHIN_CARBON": {'description': 'Ultrathin carbon film on holey support', 'annotations': {'thickness': '3-5 nm typical'}},
+    "GOLD_GRID": {'description': 'Pure gold grid', 'annotations': {'advantages': 'inert, high-resolution imaging'}},
+    "GRAPHENE_OXIDE": {'description': 'Graphene oxide support', 'annotations': {'advantages': 'atomically thin, good contrast'}},
+}
+
+class VitrificationMethod(RichEnum):
+    """
+    Methods for sample vitrification
+    """
+    # Enum members
+    PLUNGE_FREEZING = "PLUNGE_FREEZING"
+    HIGH_PRESSURE_FREEZING = "HIGH_PRESSURE_FREEZING"
+    SLAM_FREEZING = "SLAM_FREEZING"
+    SPRAY_FREEZING = "SPRAY_FREEZING"
+
+# Set metadata after class creation
+VitrificationMethod._metadata = {
+    "PLUNGE_FREEZING": {'description': 'Plunge freezing in liquid ethane', 'annotations': {'temperature': '-180°C ethane', 'equipment': 'Vitrobot, Leica GP'}},
+    "HIGH_PRESSURE_FREEZING": {'description': 'High pressure freezing', 'annotations': {'pressure': '2100 bar typical', 'advantages': 'thick samples, no ice crystals'}},
+    "SLAM_FREEZING": {'description': 'Slam freezing against metal block', 'annotations': {'cooling_rate': '10,000 K/s'}},
+    "SPRAY_FREEZING": {'description': 'Spray freezing into liquid nitrogen', 'annotations': {'applications': 'large samples, tissues'}},
+}
+
+class CrystallizationMethod(RichEnum):
+    """
+    Methods for protein crystallization
+    """
+    # Enum members
+    VAPOR_DIFFUSION_HANGING = "VAPOR_DIFFUSION_HANGING"
+    VAPOR_DIFFUSION_SITTING = "VAPOR_DIFFUSION_SITTING"
+    MICROBATCH = "MICROBATCH"
+    DIALYSIS = "DIALYSIS"
+    FREE_INTERFACE_DIFFUSION = "FREE_INTERFACE_DIFFUSION"
+    LCP = "LCP"
+
+# Set metadata after class creation
+CrystallizationMethod._metadata = {
+    "VAPOR_DIFFUSION_HANGING": {'description': 'Vapor diffusion hanging drop method', 'annotations': {'volume': '2-10 μL drops typical', 'advantages': 'visual monitoring, easy optimization'}},
+    "VAPOR_DIFFUSION_SITTING": {'description': 'Vapor diffusion sitting drop method', 'annotations': {'advantages': 'automated setup, stable drops'}},
+    "MICROBATCH": {'description': 'Microbatch under oil method', 'annotations': {'oil_type': 'paraffin, silicone oil', 'advantages': 'prevents evaporation'}},
+    "DIALYSIS": {'description': 'Dialysis crystallization', 'annotations': {'applications': 'large volume samples, gentle conditions'}},
+    "FREE_INTERFACE_DIFFUSION": {'description': 'Free interface diffusion', 'annotations': {'setup': 'capillary tubes, gel interface'}},
+    "LCP": {'description': 'Lipidic cubic phase crystallization', 'annotations': {'applications': 'membrane proteins', 'lipid': 'monoolein most common'}},
+}
+
+class XRaySource(RichEnum):
+    """
+    Types of X-ray sources
+    """
+    # Enum members
+    SYNCHROTRON = "SYNCHROTRON"
+    ROTATING_ANODE = "ROTATING_ANODE"
+    MICROFOCUS = "MICROFOCUS"
+    METAL_JET = "METAL_JET"
+
+# Set metadata after class creation
+XRaySource._metadata = {
+    "SYNCHROTRON": {'description': 'Synchrotron radiation source', 'annotations': {'advantages': 'high intensity, tunable wavelength', 'brightness': '10^15-10^18 photons/s/mm²/mrad²'}},
+    "ROTATING_ANODE": {'description': 'Rotating anode generator', 'annotations': {'power': '3-18 kW typical', 'target': 'copper, molybdenum common'}},
+    "MICROFOCUS": {'description': 'Microfocus sealed tube', 'annotations': {'spot_size': '10-50 μm', 'applications': 'small crystals, in-house screening'}},
+    "METAL_JET": {'description': 'Liquid metal jet source', 'annotations': {'advantages': 'higher power density, longer lifetime', 'metals': 'gallium, indium'}},
+}
+
+class Detector(RichEnum):
+    """
+    Types of detectors for structural biology
+    """
+    # Enum members
+    DIRECT_ELECTRON = "DIRECT_ELECTRON"
+    CCD = "CCD"
+    CMOS = "CMOS"
+    HYBRID_PIXEL = "HYBRID_PIXEL"
+    PHOTOSTIMULABLE_PHOSPHOR = "PHOTOSTIMULABLE_PHOSPHOR"
+
+# Set metadata after class creation
+Detector._metadata = {
+    "DIRECT_ELECTRON": {'description': 'Direct electron detector (DED)', 'annotations': {'examples': 'K2, K3, Falcon, DE-series', 'advantages': 'high DQE, fast readout'}},
+    "CCD": {'description': 'Charge-coupled device camera', 'annotations': {'applications': 'legacy EM, some crystallography'}},
+    "CMOS": {'description': 'Complementary metal-oxide semiconductor detector', 'annotations': {'advantages': 'fast readout, low noise'}},
+    "HYBRID_PIXEL": {'description': 'Hybrid pixel detector', 'annotations': {'examples': 'Pilatus, Eiger', 'advantages': 'photon counting, zero noise'}},
+    "PHOTOSTIMULABLE_PHOSPHOR": {'description': 'Photostimulable phosphor (image plate)', 'annotations': {'applications': 'legacy crystallography'}},
+}
+
+class WorkflowType(RichEnum):
+    """
+    Types of computational processing workflows
+    """
+    # Enum members
+    MOTION_CORRECTION = "MOTION_CORRECTION"
+    CTF_ESTIMATION = "CTF_ESTIMATION"
+    PARTICLE_PICKING = "PARTICLE_PICKING"
+    CLASSIFICATION_2D = "CLASSIFICATION_2D"
+    CLASSIFICATION_3D = "CLASSIFICATION_3D"
+    REFINEMENT_3D = "REFINEMENT_3D"
+    MODEL_BUILDING = "MODEL_BUILDING"
+    MODEL_REFINEMENT = "MODEL_REFINEMENT"
+    PHASING = "PHASING"
+    DATA_INTEGRATION = "DATA_INTEGRATION"
+    DATA_SCALING = "DATA_SCALING"
+    SAXS_ANALYSIS = "SAXS_ANALYSIS"
+
+# Set metadata after class creation
+WorkflowType._metadata = {
+    "MOTION_CORRECTION": {'description': 'Motion correction for cryo-EM movies', 'annotations': {'software': 'MotionCorr, Unblur, RELION'}},
+    "CTF_ESTIMATION": {'description': 'Contrast transfer function estimation', 'annotations': {'software': 'CTFFIND, Gctf, RELION'}},
+    "PARTICLE_PICKING": {'description': 'Particle picking from micrographs', 'annotations': {'methods': 'template matching, deep learning', 'software': 'RELION, cryoSPARC, Topaz'}},
+    "CLASSIFICATION_2D": {'description': '2D classification of particles', 'annotations': {'purpose': 'sorting, cleaning particle dataset'}},
+    "CLASSIFICATION_3D": {'description': '3D classification of particles', 'annotations': {'purpose': 'conformational sorting, resolution improvement'}},
+    "REFINEMENT_3D": {'description': '3D refinement of particle orientations', 'annotations': {'algorithms': 'expectation maximization, gradient descent'}},
+    "MODEL_BUILDING": {'description': 'Atomic model building into density', 'annotations': {'software': 'Coot, ChimeraX, Isolde'}},
+    "MODEL_REFINEMENT": {'description': 'Atomic model refinement', 'annotations': {'software': 'PHENIX, REFMAC, Buster'}},
+    "PHASING": {'description': 'Phase determination for crystallography', 'annotations': {'methods': 'SAD, MAD, MR, MIR'}},
+    "DATA_INTEGRATION": {'description': 'Integration of diffraction data', 'annotations': {'software': 'XDS, DIALS, HKL'}},
+    "DATA_SCALING": {'description': 'Scaling and merging of diffraction data', 'annotations': {'software': 'SCALA, AIMLESS, XSCALE'}},
+    "SAXS_ANALYSIS": {'description': 'SAXS data analysis and modeling', 'annotations': {'software': 'PRIMUS, CRYSOL, FoXS'}},
+}
+
+class FileFormat(RichEnum):
+    """
+    File formats used in structural biology
+    """
+    # Enum members
+    MRC = "MRC"
+    TIFF = "TIFF"
+    HDF5 = "HDF5"
+    STAR = "STAR"
+    PDB = "PDB"
+    MMCIF = "MMCIF"
+    MTZ = "MTZ"
+    CBF = "CBF"
+    DM3 = "DM3"
+    SER = "SER"
+
+# Set metadata after class creation
+FileFormat._metadata = {
+    "MRC": {'description': 'MRC format for EM density maps', 'annotations': {'extension': '.mrc, .map', 'applications': 'EM volumes, tomograms'}},
+    "TIFF": {'description': 'Tagged Image File Format', 'annotations': {'extension': '.tif, .tiff', 'applications': 'micrographs, general imaging'}},
+    "HDF5": {'description': 'Hierarchical Data Format 5', 'annotations': {'extension': '.h5, .hdf5', 'applications': 'large datasets, metadata storage'}},
+    "STAR": {'description': 'Self-defining Text Archival and Retrieval format', 'annotations': {'extension': '.star', 'applications': 'RELION metadata, particle parameters'}},
+    "PDB": {'description': 'Protein Data Bank coordinate format', 'annotations': {'extension': '.pdb', 'applications': 'atomic coordinates, legacy format'}},
+    "MMCIF": {'description': 'Macromolecular Crystallographic Information File', 'annotations': {'extension': '.cif', 'applications': 'atomic coordinates, modern PDB format'}},
+    "MTZ": {'description': 'MTZ reflection data format', 'annotations': {'extension': '.mtz', 'applications': 'crystallographic reflections, phases'}},
+    "CBF": {'description': 'Crystallographic Binary Format', 'annotations': {'extension': '.cbf', 'applications': 'detector images, diffraction data'}},
+    "DM3": {'description': 'Digital Micrograph format', 'annotations': {'extension': '.dm3, .dm4', 'applications': 'FEI/Thermo Fisher EM data'}},
+    "SER": {'description': 'FEI series format', 'annotations': {'extension': '.ser', 'applications': 'FEI movie stacks'}},
+}
+
+class DataType(RichEnum):
+    """
+    Types of structural biology data
+    """
+    # Enum members
+    MICROGRAPH = "MICROGRAPH"
+    MOVIE = "MOVIE"
+    DIFFRACTION = "DIFFRACTION"
+    SCATTERING = "SCATTERING"
+    PARTICLES = "PARTICLES"
+    VOLUME = "VOLUME"
+    TOMOGRAM = "TOMOGRAM"
+    MODEL = "MODEL"
+    METADATA = "METADATA"
+
+# Set metadata after class creation
+DataType._metadata = {
+    "MICROGRAPH": {'description': 'Electron micrograph image', 'annotations': {'typical_size': '4k x 4k pixels'}},
+    "MOVIE": {'description': 'Movie stack of frames', 'annotations': {'applications': 'motion correction, dose fractionation'}},
+    "DIFFRACTION": {'description': 'X-ray diffraction pattern', 'annotations': {'information': 'structure factors, crystal lattice'}},
+    "SCATTERING": {'description': 'Small-angle scattering data', 'annotations': {'information': 'I(q) vs scattering vector'}},
+    "PARTICLES": {'description': 'Particle stack for single particle analysis', 'annotations': {'format': 'boxed particles, aligned'}},
+    "VOLUME": {'description': '3D electron density volume', 'annotations': {'applications': 'cryo-EM maps, crystallographic maps'}},
+    "TOMOGRAM": {'description': '3D tomographic reconstruction', 'annotations': {'resolution': '5-50 Å typical'}},
+    "MODEL": {'description': 'Atomic coordinate model', 'annotations': {'formats': 'PDB, mmCIF'}},
+    "METADATA": {'description': 'Associated metadata file', 'annotations': {'formats': 'STAR, XML, JSON'}},
+}
+
+class ProcessingStatus(RichEnum):
+    """
+    Status of data processing workflows
+    """
+    # Enum members
+    RAW = "RAW"
+    PREPROCESSING = "PREPROCESSING"
+    PROCESSING = "PROCESSING"
+    COMPLETED = "COMPLETED"
+    FAILED = "FAILED"
+    QUEUED = "QUEUED"
+    PAUSED = "PAUSED"
+    CANCELLED = "CANCELLED"
+
+# Set metadata after class creation
+ProcessingStatus._metadata = {
+    "RAW": {'description': 'Raw unprocessed data'},
+    "PREPROCESSING": {'description': 'Initial preprocessing in progress'},
+    "PROCESSING": {'description': 'Main processing workflow running'},
+    "COMPLETED": {'description': 'Processing completed successfully'},
+    "FAILED": {'description': 'Processing failed with errors'},
+    "QUEUED": {'description': 'Queued for processing'},
+    "PAUSED": {'description': 'Processing paused by user'},
+    "CANCELLED": {'description': 'Processing cancelled by user'},
+}
+
+__all__ = [
+    "SampleType",
+    "StructuralBiologyTechnique",
+    "CryoEMPreparationType",
+    "CryoEMGridType",
+    "VitrificationMethod",
+    "CrystallizationMethod",
+    "XRaySource",
+    "Detector",
+    "WorkflowType",
+    "FileFormat",
+    "DataType",
+    "ProcessingStatus",
+]