valuesets 0.3.1__py3-none-any.whl

valuesets/enums/bio/currency_chemicals.py

@@ -0,0 +1,52 @@
+"""
+Currency Chemicals Value Sets
+
+Value sets for metabolic currency molecules and cofactors used in energy transfer and redox reactions
+
+Generated from: bio/currency_chemicals.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class CurrencyChemical(RichEnum):
+    """
+    Common metabolic currency molecules and cofactors that serve as energy carriers, electron donors/acceptors, and group transfer agents in cellular metabolism.
+    """
+    # Enum members
+    ATP = "ATP"
+    ADP = "ADP"
+    AMP = "AMP"
+    GTP = "GTP"
+    GDP = "GDP"
+    NAD_PLUS = "NAD_PLUS"
+    NADH = "NADH"
+    NADP_PLUS = "NADP_PLUS"
+    NADPH = "NADPH"
+    FAD = "FAD"
+    FADH2 = "FADH2"
+    COA = "COA"
+    ACETYL_COA = "ACETYL_COA"
+
+# Set metadata after class creation
+CurrencyChemical._metadata = {
+    "ATP": {'description': 'Adenosine triphosphate - primary energy currency molecule in cells', 'meaning': 'CHEBI:15422'},
+    "ADP": {'description': 'Adenosine diphosphate - product of ATP hydrolysis, energy acceptor', 'meaning': 'CHEBI:16761'},
+    "AMP": {'description': 'Adenosine monophosphate - nucleotide, product of ADP hydrolysis', 'meaning': 'CHEBI:16027', 'aliases': ["adenosine 5'-monophosphate"]},
+    "GTP": {'description': 'Guanosine triphosphate - energy molecule, protein synthesis and signaling', 'meaning': 'CHEBI:15996'},
+    "GDP": {'description': 'Guanosine diphosphate - product of GTP hydrolysis', 'meaning': 'CHEBI:17552'},
+    "NAD_PLUS": {'description': 'Nicotinamide adenine dinucleotide (oxidized) - electron acceptor in catabolism', 'meaning': 'CHEBI:15846'},
+    "NADH": {'description': 'Nicotinamide adenine dinucleotide (reduced) - electron donor, reducing agent', 'meaning': 'CHEBI:16908'},
+    "NADP_PLUS": {'description': 'Nicotinamide adenine dinucleotide phosphate (oxidized) - electron acceptor', 'meaning': 'CHEBI:18009'},
+    "NADPH": {'description': 'Nicotinamide adenine dinucleotide phosphate (reduced) - anabolic reducing agent', 'meaning': 'CHEBI:16474'},
+    "FAD": {'description': 'Flavin adenine dinucleotide (oxidized) - electron acceptor in oxidation reactions', 'meaning': 'CHEBI:16238'},
+    "FADH2": {'description': 'Flavin adenine dinucleotide (reduced) - electron donor in electron transport chain', 'meaning': 'CHEBI:17877'},
+    "COA": {'description': 'Coenzyme A - acyl group carrier in fatty acid metabolism', 'meaning': 'CHEBI:15346', 'aliases': ['coenzyme A']},
+    "ACETYL_COA": {'description': 'Acetyl coenzyme A - central metabolic intermediate, links glycolysis to citric acid cycle', 'meaning': 'CHEBI:15351'},
+}
+
+__all__ = [
+    "CurrencyChemical",
+]

valuesets/enums/bio/developmental_stages.py

@@ -0,0 +1,103 @@
+"""
+Developmental Stages Value Sets
+
+Ontology-mapped developmental stages for human and mouse organisms. Human stages use HsapDv (Human Developmental Stages) ontology. Mouse stages use MmusDv (Mouse Developmental Stages) ontology.
+
+Generated from: bio/developmental_stages.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class HumanDevelopmentalStage(RichEnum):
+    # Enum members
+    ZYGOTE_STAGE = "ZYGOTE_STAGE"
+    CLEAVAGE_STAGE = "CLEAVAGE_STAGE"
+    MORULA_STAGE = "MORULA_STAGE"
+    BLASTOCYST_STAGE = "BLASTOCYST_STAGE"
+    GASTRULA_STAGE = "GASTRULA_STAGE"
+    NEURULA_STAGE = "NEURULA_STAGE"
+    ORGANOGENESIS_STAGE = "ORGANOGENESIS_STAGE"
+    FETAL_STAGE = "FETAL_STAGE"
+    NEONATAL_STAGE = "NEONATAL_STAGE"
+    INFANT_STAGE = "INFANT_STAGE"
+    TODDLER_STAGE = "TODDLER_STAGE"
+    CHILD_STAGE = "CHILD_STAGE"
+    ADOLESCENT_STAGE = "ADOLESCENT_STAGE"
+    ADULT_STAGE = "ADULT_STAGE"
+    AGED_STAGE = "AGED_STAGE"
+    EMBRYONIC_STAGE = "EMBRYONIC_STAGE"
+    PRENATAL_STAGE = "PRENATAL_STAGE"
+    POSTNATAL_STAGE = "POSTNATAL_STAGE"
+
+# Set metadata after class creation
+HumanDevelopmentalStage._metadata = {
+    "ZYGOTE_STAGE": {'description': 'Embryonic stage defined by a fertilized oocyte and presence of pronuclei. Starts at day 1 post-fertilization.', 'meaning': 'HsapDv:0000003'},
+    "CLEAVAGE_STAGE": {'description': 'Embryonic stage during which cell division occurs with reduction in cytoplasmic volume, and formation of inner and outer cell mass. 2-8 cells. Usually starts between day 2-3 post-fertilization.', 'meaning': 'HsapDv:0000005'},
+    "MORULA_STAGE": {'description': 'The later part of Carnegie stage 02 when the cells have coalesced into a mass but the blastocystic cavity has not formed.', 'meaning': 'HsapDv:0000205'},
+    "BLASTOCYST_STAGE": {'description': 'Blastula stage with the loss of the zona pellucida and the definition of a free blastocyst. Usually starts between day 4-5 post-fertilization.', 'meaning': 'HsapDv:0000007'},
+    "GASTRULA_STAGE": {'description': 'Embryonic stage defined by a complex and coordinated series of cellular movements that occurs at the end of cleavage.', 'meaning': 'HsapDv:0000010'},
+    "NEURULA_STAGE": {'description': 'Embryonic stage defined by the formation of a tube from the flat layer of ectodermal cells known as the neural plate. This stage starts the emergence of the central nervous system.', 'meaning': 'HsapDv:0000012'},
+    "ORGANOGENESIS_STAGE": {'description': 'Embryonic stage at which the ectoderm, endoderm, and mesoderm develop into the internal organs of the organism.', 'meaning': 'HsapDv:0000015'},
+    "FETAL_STAGE": {'description': 'Prenatal stage that starts with the fully formed embryo and ends at birth. Generally from 8 weeks post-fertilization until birth.', 'meaning': 'HsapDv:0000037'},
+    "NEONATAL_STAGE": {'description': 'Immature stage that refers to a human newborn within the first 28 days of life.', 'meaning': 'HsapDv:0000262'},
+    "INFANT_STAGE": {'description': 'Immature stage that refers to an infant who is over 28 days and is under 12 months old.', 'meaning': 'HsapDv:0000261'},
+    "TODDLER_STAGE": {'description': 'Human stage that refers to a child who is over 12 months and under 5 years old. Often divided into early toddler (1-2 years) and late toddler (2-3 years).', 'meaning': 'HsapDv:0000265'},
+    "CHILD_STAGE": {'description': 'Pediatric stage that refers to a human who is over 5 and under 15 years old. Covers elementary and middle school ages.', 'meaning': 'HsapDv:0000271'},
+    "ADOLESCENT_STAGE": {'description': 'A young adult stage that refers to an individual who is over 15 and under 20 years old. Period of transition from childhood to adulthood.', 'meaning': 'HsapDv:0000268'},
+    "ADULT_STAGE": {'description': 'Human developmental stage that refers to a sexually mature human. Starts at approximately 15 years according to HPO definitions.', 'meaning': 'HsapDv:0000258'},
+    "AGED_STAGE": {'description': 'Late adult stage that refers to an individual who is over 60 and starts to have some age-related impairments. Often subdivided into young-old (60-79) and old-old (80+).', 'meaning': 'HsapDv:0000227'},
+    "EMBRYONIC_STAGE": {'description': 'Prenatal stage that starts with fertilization and ends with a fully formed embryo, before undergoing last development during the fetal stage. Up to 8 weeks post-fertilization.', 'meaning': 'HsapDv:0000002'},
+    "PRENATAL_STAGE": {'description': 'Prenatal stage that starts with fertilization and ends at birth. Encompasses both embryonic and fetal stages.', 'meaning': 'HsapDv:0000045'},
+    "POSTNATAL_STAGE": {'description': 'Human developmental stage that covers the whole of human life post birth.', 'meaning': 'HsapDv:0010000'},
+}
+
+class MouseDevelopmentalStage(RichEnum):
+    # Enum members
+    ZYGOTE_STAGE = "ZYGOTE_STAGE"
+    TWO_CELL_STAGE = "TWO_CELL_STAGE"
+    FOUR_CELL_STAGE = "FOUR_CELL_STAGE"
+    EIGHT_CELL_STAGE = "EIGHT_CELL_STAGE"
+    MORULA_STAGE = "MORULA_STAGE"
+    BLASTOCYST_STAGE = "BLASTOCYST_STAGE"
+    GASTRULA_STAGE = "GASTRULA_STAGE"
+    NEURULA_STAGE = "NEURULA_STAGE"
+    ORGANOGENESIS_STAGE = "ORGANOGENESIS_STAGE"
+    E0_5 = "E0_5"
+    E9_5 = "E9_5"
+    E14_5 = "E14_5"
+    P0_NEWBORN = "P0_NEWBORN"
+    P21_WEANING = "P21_WEANING"
+    P42_JUVENILE = "P42_JUVENILE"
+    P56_ADULT = "P56_ADULT"
+    AGED_12_MONTHS = "AGED_12_MONTHS"
+    THEILER_STAGE = "THEILER_STAGE"
+
+# Set metadata after class creation
+MouseDevelopmentalStage._metadata = {
+    "ZYGOTE_STAGE": {'description': 'Embryonic stage defined by a one-cell embryo (fertilised egg) with zona pellucida present. Embryonic age 0-0.9 dpc (days post coitum).', 'meaning': 'MmusDv:0000003'},
+    "TWO_CELL_STAGE": {'description': 'Embryonic cleavage stage defined by a dividing 2-4 cells egg. Embryonic age 1 dpc.', 'meaning': 'MmusDv:0000005'},
+    "FOUR_CELL_STAGE": {'description': 'Part of Theiler stage 02 - dividing egg with 4 cells. Embryonic age approximately 1 dpc.', 'meaning': 'MmusDv:0000005'},
+    "EIGHT_CELL_STAGE": {'description': 'Part of early morula stage - dividing egg with 8 cells. Embryonic age approximately 2 dpc.', 'meaning': 'MmusDv:0000006'},
+    "MORULA_STAGE": {'description': 'Embryonic cleavage stage defined by a dividing 4-16 cells egg, early to fully compacted morula. Embryonic age 2 dpc.', 'meaning': 'MmusDv:0000006'},
+    "BLASTOCYST_STAGE": {'description': 'Embryonic blastula stage defined by a zona free blastocyst (zona pellucida absent). Embryonic age 4 dpc.', 'meaning': 'MmusDv:0000009'},
+    "GASTRULA_STAGE": {'description': 'Embryonic stage defined by complex and coordinated series of cellular movements that occurs at the end of cleavage.', 'meaning': 'MmusDv:0000013'},
+    "NEURULA_STAGE": {'description': 'Embryonic stage called presomite stage and defined by the formation of the neural plate. This stage starts the emergence of the central nervous system at embryonic age 7.5 dpc.', 'meaning': 'MmusDv:0000017'},
+    "ORGANOGENESIS_STAGE": {'description': 'Embryonic stage at which the ectoderm, endoderm, and mesoderm develop into the internal organs of the organism.', 'meaning': 'MmusDv:0000018'},
+    "E0_5": {'description': 'Embryonic day 0.5 - one-cell embryo stage. Corresponds to Theiler stage 01.', 'meaning': 'MmusDv:0000003'},
+    "E9_5": {'description': 'Embryonic day 9.5 - organogenesis stage with visible hind limb buds. Between Theiler stages 15 and 16.', 'meaning': 'MmusDv:0000023'},
+    "E14_5": {'description': 'Embryonic day 14.5 - late organogenesis with clearly visible fingers and long bones of the limbs present.', 'meaning': 'MmusDv:0000029'},
+    "P0_NEWBORN": {'description': 'Stage that refers to the newborn mouse, aged E19-20, P0. Used for postnatal days 0 through 3.', 'meaning': 'MmusDv:0000036'},
+    "P21_WEANING": {'description': 'Weaning stage at approximately 21-22 days old. Transition from nursing to independent feeding.', 'meaning': 'MmusDv:0000141'},
+    "P42_JUVENILE": {'description': 'Prime adult stage at 6 weeks (42 days) old. Commonly considered the milestone for sexual maturity.', 'meaning': 'MmusDv:0000151'},
+    "P56_ADULT": {'description': 'Adult stage at 8 weeks (56 days) old. Fully mature adult mouse.', 'meaning': 'MmusDv:0000154'},
+    "AGED_12_MONTHS": {'description': 'Middle aged stage for mice over 10 and under 18 months old. Shows progressive age-related changes.', 'meaning': 'MmusDv:0000135'},
+    "THEILER_STAGE": {'description': 'Reference to any Theiler stage (TS1-TS28) which provides standardized morphological staging for mouse development.'},
+}
+
+__all__ = [
+    "HumanDevelopmentalStage",
+    "MouseDevelopmentalStage",
+]

valuesets/enums/bio/genome_features.py

@@ -0,0 +1,182 @@
+"""
+Genome Feature Types
+
+Genome feature types from SOFA (Sequence Ontology Feature Annotation),
+the subset of SO used in GFF3 files for genome annotation.
+Organized hierarchically following the Sequence Ontology structure.
+
+Generated from: bio/genome_features.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class GenomeFeatureType(RichEnum):
+    """
+    Genome feature types from SOFA (Sequence Ontology Feature Annotation).
+    This is the subset of Sequence Ontology terms used in GFF3 files.
+    Organized hierarchically following the Sequence Ontology structure.
+    """
+    # Enum members
+    REGION = "REGION"
+    BIOLOGICAL_REGION = "BIOLOGICAL_REGION"
+    GENE = "GENE"
+    TRANSCRIPT = "TRANSCRIPT"
+    PRIMARY_TRANSCRIPT = "PRIMARY_TRANSCRIPT"
+    MRNA = "MRNA"
+    EXON = "EXON"
+    CDS = "CDS"
+    INTRON = "INTRON"
+    FIVE_PRIME_UTR = "FIVE_PRIME_UTR"
+    THREE_PRIME_UTR = "THREE_PRIME_UTR"
+    NCRNA = "NCRNA"
+    RRNA = "RRNA"
+    TRNA = "TRNA"
+    SNRNA = "SNRNA"
+    SNORNA = "SNORNA"
+    MIRNA = "MIRNA"
+    LNCRNA = "LNCRNA"
+    RIBOZYME = "RIBOZYME"
+    ANTISENSE_RNA = "ANTISENSE_RNA"
+    PSEUDOGENE = "PSEUDOGENE"
+    PROCESSED_PSEUDOGENE = "PROCESSED_PSEUDOGENE"
+    REGULATORY_REGION = "REGULATORY_REGION"
+    PROMOTER = "PROMOTER"
+    ENHANCER = "ENHANCER"
+    SILENCER = "SILENCER"
+    TERMINATOR = "TERMINATOR"
+    ATTENUATOR = "ATTENUATOR"
+    POLYA_SIGNAL_SEQUENCE = "POLYA_SIGNAL_SEQUENCE"
+    BINDING_SITE = "BINDING_SITE"
+    TFBS = "TFBS"
+    RIBOSOME_ENTRY_SITE = "RIBOSOME_ENTRY_SITE"
+    POLYA_SITE = "POLYA_SITE"
+    REPEAT_REGION = "REPEAT_REGION"
+    DISPERSED_REPEAT = "DISPERSED_REPEAT"
+    TANDEM_REPEAT = "TANDEM_REPEAT"
+    INVERTED_REPEAT = "INVERTED_REPEAT"
+    TRANSPOSABLE_ELEMENT = "TRANSPOSABLE_ELEMENT"
+    MOBILE_ELEMENT = "MOBILE_ELEMENT"
+    SEQUENCE_ALTERATION = "SEQUENCE_ALTERATION"
+    INSERTION = "INSERTION"
+    DELETION = "DELETION"
+    INVERSION = "INVERSION"
+    DUPLICATION = "DUPLICATION"
+    SUBSTITUTION = "SUBSTITUTION"
+    ORIGIN_OF_REPLICATION = "ORIGIN_OF_REPLICATION"
+    POLYC_TRACT = "POLYC_TRACT"
+    GAP = "GAP"
+    ASSEMBLY_GAP = "ASSEMBLY_GAP"
+    CHROMOSOME = "CHROMOSOME"
+    SUPERCONTIG = "SUPERCONTIG"
+    CONTIG = "CONTIG"
+    SCAFFOLD = "SCAFFOLD"
+    CLONE = "CLONE"
+    PLASMID = "PLASMID"
+    POLYPEPTIDE = "POLYPEPTIDE"
+    MATURE_PROTEIN_REGION = "MATURE_PROTEIN_REGION"
+    SIGNAL_PEPTIDE = "SIGNAL_PEPTIDE"
+    TRANSIT_PEPTIDE = "TRANSIT_PEPTIDE"
+    PROPEPTIDE = "PROPEPTIDE"
+    OPERON = "OPERON"
+    STEM_LOOP = "STEM_LOOP"
+    D_LOOP = "D_LOOP"
+    MATCH = "MATCH"
+    CDNA_MATCH = "CDNA_MATCH"
+    EST_MATCH = "EST_MATCH"
+    PROTEIN_MATCH = "PROTEIN_MATCH"
+    NUCLEOTIDE_MATCH = "NUCLEOTIDE_MATCH"
+    JUNCTION_FEATURE = "JUNCTION_FEATURE"
+    SPLICE_SITE = "SPLICE_SITE"
+    FIVE_PRIME_SPLICE_SITE = "FIVE_PRIME_SPLICE_SITE"
+    THREE_PRIME_SPLICE_SITE = "THREE_PRIME_SPLICE_SITE"
+    START_CODON = "START_CODON"
+    STOP_CODON = "STOP_CODON"
+    CENTROMERE = "CENTROMERE"
+    TELOMERE = "TELOMERE"
+
+# Set metadata after class creation
+GenomeFeatureType._metadata = {
+    "REGION": {'description': 'A sequence feature with an extent greater than zero', 'meaning': 'SO:0000001'},
+    "BIOLOGICAL_REGION": {'description': 'A region defined by its biological properties', 'meaning': 'SO:0001411'},
+    "GENE": {'description': 'A region (or regions) that includes all of the sequence elements necessary to encode a functional transcript', 'meaning': 'SO:0000704'},
+    "TRANSCRIPT": {'description': 'An RNA synthesized on a DNA or RNA template by an RNA polymerase', 'meaning': 'SO:0000673'},
+    "PRIMARY_TRANSCRIPT": {'description': 'A transcript that has not been processed', 'meaning': 'SO:0000185'},
+    "MRNA": {'description': "Messenger RNA; includes 5'UTR, coding sequences and 3'UTR", 'meaning': 'SO:0000234'},
+    "EXON": {'description': 'A region of the transcript sequence within a gene which is not removed from the primary RNA transcript by RNA splicing', 'meaning': 'SO:0000147'},
+    "CDS": {'description': 'Coding sequence; sequence of nucleotides that corresponds with the sequence of amino acids in a protein', 'meaning': 'SO:0000316'},
+    "INTRON": {'description': 'A region of a primary transcript that is transcribed, but removed from within the transcript by splicing', 'meaning': 'SO:0000188'},
+    "FIVE_PRIME_UTR": {'description': "5' untranslated region", 'meaning': 'SO:0000204'},
+    "THREE_PRIME_UTR": {'description': "3' untranslated region", 'meaning': 'SO:0000205'},
+    "NCRNA": {'description': 'Non-protein coding RNA', 'meaning': 'SO:0000655'},
+    "RRNA": {'description': 'Ribosomal RNA', 'meaning': 'SO:0000252'},
+    "TRNA": {'description': 'Transfer RNA', 'meaning': 'SO:0000253'},
+    "SNRNA": {'description': 'Small nuclear RNA', 'meaning': 'SO:0000274'},
+    "SNORNA": {'description': 'Small nucleolar RNA', 'meaning': 'SO:0000275'},
+    "MIRNA": {'description': 'MicroRNA', 'meaning': 'SO:0000276'},
+    "LNCRNA": {'description': 'Long non-coding RNA', 'meaning': 'SO:0001877'},
+    "RIBOZYME": {'description': 'An RNA with catalytic activity', 'meaning': 'SO:0000374'},
+    "ANTISENSE_RNA": {'description': 'RNA that is complementary to other RNA', 'meaning': 'SO:0000644'},
+    "PSEUDOGENE": {'description': 'A sequence that closely resembles a known functional gene but does not produce a functional product', 'meaning': 'SO:0000336'},
+    "PROCESSED_PSEUDOGENE": {'description': 'A pseudogene arising from reverse transcription of mRNA', 'meaning': 'SO:0000043'},
+    "REGULATORY_REGION": {'description': 'A region involved in the control of the process of gene expression', 'meaning': 'SO:0005836'},
+    "PROMOTER": {'description': 'A regulatory region initiating transcription', 'meaning': 'SO:0000167'},
+    "ENHANCER": {'description': 'A cis-acting sequence that increases transcription', 'meaning': 'SO:0000165'},
+    "SILENCER": {'description': 'A regulatory region which upon binding of transcription factors, suppresses transcription', 'meaning': 'SO:0000625'},
+    "TERMINATOR": {'description': 'The sequence of DNA located either at the end of the transcript that causes RNA polymerase to terminate transcription', 'meaning': 'SO:0000141'},
+    "ATTENUATOR": {'description': 'A sequence that causes transcription termination', 'meaning': 'SO:0000140'},
+    "POLYA_SIGNAL_SEQUENCE": {'description': 'The recognition sequence for the cleavage and polyadenylation machinery', 'meaning': 'SO:0000551'},
+    "BINDING_SITE": {'description': 'A region on a molecule that binds to another molecule', 'meaning': 'SO:0000409'},
+    "TFBS": {'description': 'Transcription factor binding site', 'meaning': 'SO:0000235'},
+    "RIBOSOME_ENTRY_SITE": {'description': 'Region where ribosome assembles on mRNA', 'meaning': 'SO:0000139'},
+    "POLYA_SITE": {'description': 'Polyadenylation site', 'meaning': 'SO:0000553'},
+    "REPEAT_REGION": {'description': 'A region of sequence containing one or more repeat units', 'meaning': 'SO:0000657'},
+    "DISPERSED_REPEAT": {'description': 'A repeat that is interspersed in the genome', 'meaning': 'SO:0000658'},
+    "TANDEM_REPEAT": {'description': 'A repeat where the same sequence is repeated in the same orientation', 'meaning': 'SO:0000705'},
+    "INVERTED_REPEAT": {'description': 'A repeat where the sequence is repeated in the opposite orientation', 'meaning': 'SO:0000294'},
+    "TRANSPOSABLE_ELEMENT": {'description': 'A DNA segment that can change its position within the genome', 'meaning': 'SO:0000101'},
+    "MOBILE_ELEMENT": {'description': 'A nucleotide region with the ability to move from one place in the genome to another', 'meaning': 'SO:0001037'},
+    "SEQUENCE_ALTERATION": {'description': 'A sequence that deviates from the reference sequence', 'meaning': 'SO:0001059'},
+    "INSERTION": {'description': 'The sequence of one or more nucleotides added between two adjacent nucleotides', 'meaning': 'SO:0000667'},
+    "DELETION": {'description': 'The removal of a sequences of nucleotides from the genome', 'meaning': 'SO:0000159'},
+    "INVERSION": {'description': 'A continuous nucleotide sequence is inverted in the same position', 'meaning': 'SO:1000036'},
+    "DUPLICATION": {'description': 'One or more nucleotides are added between two adjacent nucleotides', 'meaning': 'SO:1000035'},
+    "SUBSTITUTION": {'description': 'A sequence alteration where one nucleotide replaced by another', 'meaning': 'SO:1000002'},
+    "ORIGIN_OF_REPLICATION": {'description': 'The origin of replication; starting site for duplication of a nucleic acid molecule', 'meaning': 'SO:0000296'},
+    "POLYC_TRACT": {'description': 'A sequence of Cs'},
+    "GAP": {'description': 'A gap in the sequence', 'meaning': 'SO:0000730'},
+    "ASSEMBLY_GAP": {'description': 'A gap between two sequences in an assembly', 'meaning': 'SO:0000730'},
+    "CHROMOSOME": {'description': 'Structural unit composed of DNA and proteins', 'meaning': 'SO:0000340'},
+    "SUPERCONTIG": {'description': 'One or more contigs that have been ordered and oriented using end-read information', 'meaning': 'SO:0000148'},
+    "CONTIG": {'description': 'A contiguous sequence derived from sequence assembly', 'meaning': 'SO:0000149'},
+    "SCAFFOLD": {'description': 'One or more contigs that have been ordered and oriented', 'meaning': 'SO:0000148'},
+    "CLONE": {'description': 'A piece of DNA that has been inserted into a vector', 'meaning': 'SO:0000151'},
+    "PLASMID": {'description': 'A self-replicating circular DNA molecule', 'meaning': 'SO:0000155'},
+    "POLYPEPTIDE": {'description': 'A sequence of amino acids linked by peptide bonds', 'meaning': 'SO:0000104'},
+    "MATURE_PROTEIN_REGION": {'description': 'The polypeptide sequence that remains after post-translational processing', 'meaning': 'SO:0000419'},
+    "SIGNAL_PEPTIDE": {'description': 'A peptide region that targets a polypeptide to a specific location', 'meaning': 'SO:0000418'},
+    "TRANSIT_PEPTIDE": {'description': 'A peptide that directs the transport of a protein to an organelle', 'meaning': 'SO:0000725'},
+    "PROPEPTIDE": {'description': 'A peptide region that is cleaved during maturation', 'meaning': 'SO:0001062'},
+    "OPERON": {'description': 'A group of contiguous genes transcribed as a single unit', 'meaning': 'SO:0000178'},
+    "STEM_LOOP": {'description': 'A double-helical region formed by base-pairing between adjacent sequences', 'meaning': 'SO:0000313'},
+    "D_LOOP": {'description': 'Displacement loop; a region where DNA is displaced by an invading strand', 'meaning': 'SO:0000297'},
+    "MATCH": {'description': 'A region of sequence similarity', 'meaning': 'SO:0000343'},
+    "CDNA_MATCH": {'description': 'A match to a cDNA sequence', 'meaning': 'SO:0000689'},
+    "EST_MATCH": {'description': 'A match to an EST sequence', 'meaning': 'SO:0000668'},
+    "PROTEIN_MATCH": {'description': 'A match to a protein sequence', 'meaning': 'SO:0000349'},
+    "NUCLEOTIDE_MATCH": {'description': 'A match to a nucleotide sequence', 'meaning': 'SO:0000347'},
+    "JUNCTION_FEATURE": {'description': 'A boundary or junction between sequence regions', 'meaning': 'SO:0000699'},
+    "SPLICE_SITE": {'description': 'The position where intron is excised', 'meaning': 'SO:0000162'},
+    "FIVE_PRIME_SPLICE_SITE": {'description': "The 5' splice site (donor site)", 'meaning': 'SO:0000163'},
+    "THREE_PRIME_SPLICE_SITE": {'description': "The 3' splice site (acceptor site)", 'meaning': 'SO:0000164'},
+    "START_CODON": {'description': 'The first codon to be translated', 'meaning': 'SO:0000318'},
+    "STOP_CODON": {'description': 'The codon that terminates translation', 'meaning': 'SO:0000319'},
+    "CENTROMERE": {'description': 'A region where chromatids are held together', 'meaning': 'SO:0000577'},
+    "TELOMERE": {'description': 'The terminal region of a linear chromosome', 'meaning': 'SO:0000624'},
+}
+
+__all__ = [
+    "GenomeFeatureType",
+]

valuesets/enums/bio/genomics.py

@@ -0,0 +1,91 @@
+"""
+Genomics Value Sets
+
+Value sets related to genomics and sequencing
+
+Generated from: bio/genomics.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class CdsPhaseType(RichEnum):
+    """
+    For features of type CDS (coding sequence), the phase indicates where the feature begins with reference to the reading frame. The phase is one of the integers 0, 1, or 2, indicating the number of bases that should be removed from the beginning of this feature to reach the first base of the next codon.
+    """
+    # Enum members
+    PHASE_0 = "PHASE_0"
+    PHASE_1 = "PHASE_1"
+    PHASE_2 = "PHASE_2"
+
+# Set metadata after class creation
+CdsPhaseType._metadata = {
+    "PHASE_0": {'description': 'Zero bases from reading frame to feature start.'},
+    "PHASE_1": {'description': 'One base from reading frame to feature start.'},
+    "PHASE_2": {'description': 'Two bases from reading frame to feature start.'},
+}
+
+class ContigCollectionType(RichEnum):
+    """
+    The type of the contig set; the type of the 'omics data set. Terms are taken from the Genomics Standards Consortium where possible. See the GSC checklists at https://genomicsstandardsconsortium.github.io/mixs/ for the controlled vocabularies used.
+    """
+    # Enum members
+    ISOLATE = "ISOLATE"
+    MAG = "MAG"
+    METAGENOME = "METAGENOME"
+    METATRANSCRIPTOME = "METATRANSCRIPTOME"
+    SAG = "SAG"
+    VIRUS = "VIRUS"
+    MARKER = "MARKER"
+
+# Set metadata after class creation
+ContigCollectionType._metadata = {
+    "ISOLATE": {'description': 'Sequences assembled from DNA of isolated organism. Bacteria/Archaea: https://genomicsstandardsconsortium.github.io/mixs/0010003/ Euk: https://genomicsstandardsconsortium.github.io/mixs/0010002/ Virus: https://genomicsstandardsconsortium.github.io/mixs/0010005/ Organelle: https://genomicsstandardsconsortium.github.io/mixs/0010006/ Plasmid: https://genomicsstandardsconsortium.github.io/mixs/0010004/'},
+    "MAG": {'description': 'Sequences assembled from DNA of mixed community and binned. MAGs are likely to represent a single taxonomic origin. See checkm2 scores for quality assessment.', 'meaning': 'mixs:0010011', 'aliases': ['Mimag']},
+    "METAGENOME": {'description': 'Sequences assembled from DNA of mixed community.', 'meaning': 'mixs:0010007', 'aliases': ['Mims']},
+    "METATRANSCRIPTOME": {'description': 'Sequences assembled from RNA of mixed community. Currently not represented by GSC.'},
+    "SAG": {'description': 'Sequences assembled from DNA of single cell.', 'meaning': 'mixs:0010010', 'aliases': ['Misag']},
+    "VIRUS": {'description': 'Sequences assembled from uncultivated virus genome (DNA/RNA).', 'meaning': 'mixs:0010012', 'aliases': ['Miuvig']},
+    "MARKER": {'description': 'Sequences from targeted region of DNA; see protocol for information on targeted region. specimen: https://genomicsstandardsconsortium.github.io/mixs/0010009/ survey: https://genomicsstandardsconsortium.github.io/mixs/0010008/'},
+}
+
+class StrandType(RichEnum):
+    """
+    The strand that a feature appears on relative to a landmark. Also encompasses unknown or irrelevant strandedness.
+    """
+    # Enum members
+    NEGATIVE = "NEGATIVE"
+    POSITIVE = "POSITIVE"
+    UNKNOWN = "UNKNOWN"
+    UNSTRANDED = "UNSTRANDED"
+
+# Set metadata after class creation
+StrandType._metadata = {
+    "NEGATIVE": {'description': 'Represented by "-" in a GFF file; the strand is negative wrt the landmark.'},
+    "POSITIVE": {'description': 'Represented by "+" in a GFF file; the strand is positive with relation to the landmark.'},
+    "UNKNOWN": {'description': 'Represented by "?" in a GFF file. The strandedness is relevant but unknown.'},
+    "UNSTRANDED": {'description': 'Represented by "." in a GFF file; the feature is not stranded.'},
+}
+
+class SequenceType(RichEnum):
+    """
+    The type of sequence being represented.
+    """
+    # Enum members
+    NUCLEIC_ACID = "NUCLEIC_ACID"
+    AMINO_ACID = "AMINO_ACID"
+
+# Set metadata after class creation
+SequenceType._metadata = {
+    "NUCLEIC_ACID": {'description': 'A nucleic acid sequence, as found in an FNA file.'},
+    "AMINO_ACID": {'description': 'An amino acid sequence, as would be found in an FAA file.'},
+}
+
+__all__ = [
+    "CdsPhaseType",
+    "ContigCollectionType",
+    "StrandType",
+    "SequenceType",
+]

valuesets/enums/bio/go_aspect.py

@@ -0,0 +1,32 @@
+"""
+Gene Ontology Aspects
+
+The three main aspects of Gene Ontology - Molecular Function, Biological Process, and Cellular Component
+
+Generated from: bio/go_aspect.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class GOAspect(RichEnum):
+    """
+    The three main aspects (namespaces) of Gene Ontology
+    """
+    # Enum members
+    F = "F"
+    P = "P"
+    C = "C"
+
+# Set metadata after class creation
+GOAspect._metadata = {
+    "F": {'description': 'The activities that occur at the molecular level, such as catalysis or binding', 'meaning': 'GO:0003674', 'aliases': ['molecular_function', 'MF']},
+    "P": {'description': 'The larger processes accomplished by multiple molecular activities', 'meaning': 'GO:0008150', 'aliases': ['biological_process', 'BP']},
+    "C": {'description': 'The locations relative to cellular structures in which a gene product performs a function', 'meaning': 'GO:0005575', 'aliases': ['cellular_component', 'CC']},
+}
+
+__all__ = [
+    "GOAspect",
+]

valuesets/enums/bio/go_causality.py

@@ -0,0 +1,58 @@
+"""
+Gene Ontology Causality Value Sets
+
+Value sets for GO causal relationships and predicates used in gene ontology annotations and pathway analysis
+
+Generated from: bio/go_causality.yaml
+"""
+
+from __future__ import annotations
+
+from typing import Dict, Any, Optional
+from valuesets.generators.rich_enum import RichEnum
+
+class CausalPredicateEnum(RichEnum):
+    """
+    A term describing the causal relationship between two activities. All terms are drawn from the "causally upstream or within" (RO:0002418) branch of the Relation Ontology (RO).
+    """
+    # Enum members
+    CONSTITUTIVELY_UPSTREAM_OF = "CONSTITUTIVELY_UPSTREAM_OF"
+    PROVIDES_INPUT_FOR = "PROVIDES_INPUT_FOR"
+    REMOVES_INPUT_FOR = "REMOVES_INPUT_FOR"
+    CAUSALLY_UPSTREAM_OF = "CAUSALLY_UPSTREAM_OF"
+    CAUSALLY_UPSTREAM_OF_POSITIVE_EFFECT = "CAUSALLY_UPSTREAM_OF_POSITIVE_EFFECT"
+    CAUSALLY_UPSTREAM_OF_NEGATIVE_EFFECT = "CAUSALLY_UPSTREAM_OF_NEGATIVE_EFFECT"
+    REGULATES = "REGULATES"
+    NEGATIVELY_REGULATES = "NEGATIVELY_REGULATES"
+    POSITIVELY_REGULATES = "POSITIVELY_REGULATES"
+    DIRECTLY_NEGATIVELY_REGULATES = "DIRECTLY_NEGATIVELY_REGULATES"
+    INDIRECTLY_NEGATIVELY_REGULATES = "INDIRECTLY_NEGATIVELY_REGULATES"
+    DIRECTLY_POSITIVELY_REGULATES = "DIRECTLY_POSITIVELY_REGULATES"
+    INDIRECTLY_POSITIVELY_REGULATES = "INDIRECTLY_POSITIVELY_REGULATES"
+    IS_SMALL_MOLECULE_REGULATOR_OF = "IS_SMALL_MOLECULE_REGULATOR_OF"
+    IS_SMALL_MOLECULE_ACTIVATOR_OF = "IS_SMALL_MOLECULE_ACTIVATOR_OF"
+    IS_SMALL_MOLECULE_INHIBITOR_OF = "IS_SMALL_MOLECULE_INHIBITOR_OF"
+
+# Set metadata after class creation
+CausalPredicateEnum._metadata = {
+    "CONSTITUTIVELY_UPSTREAM_OF": {'meaning': 'RO:0012009'},
+    "PROVIDES_INPUT_FOR": {'meaning': 'RO:0002413'},
+    "REMOVES_INPUT_FOR": {'meaning': 'RO:0012010'},
+    "CAUSALLY_UPSTREAM_OF": {'meaning': 'RO:0002411', 'aliases': ['undetermined']},
+    "CAUSALLY_UPSTREAM_OF_POSITIVE_EFFECT": {'meaning': 'RO:0002304', 'annotations': {'symbol': '+', 'direction': 'POSITIVE'}},
+    "CAUSALLY_UPSTREAM_OF_NEGATIVE_EFFECT": {'meaning': 'RO:0002305', 'annotations': {'symbol': '-', 'direction': 'NEGATIVE'}},
+    "REGULATES": {'meaning': 'RO:0002211', 'annotations': {'symbol': 'R'}},
+    "NEGATIVELY_REGULATES": {'meaning': 'RO:0002212', 'annotations': {'symbol': '-R', 'direction': 'NEGATIVE'}},
+    "POSITIVELY_REGULATES": {'meaning': 'RO:0002213', 'annotations': {'symbol': '+R', 'direction': 'POSITIVE'}},
+    "DIRECTLY_NEGATIVELY_REGULATES": {'meaning': 'RO:0002630', 'annotations': {'directness': 'DIRECT', 'direction': 'NEGATIVE'}},
+    "INDIRECTLY_NEGATIVELY_REGULATES": {'meaning': 'RO:0002409', 'annotations': {'directness': 'INDIRECT', 'direction': 'NEGATIVE'}},
+    "DIRECTLY_POSITIVELY_REGULATES": {'meaning': 'RO:0002629', 'annotations': {'directness': 'DIRECT', 'direction': 'POSITIVE'}},
+    "INDIRECTLY_POSITIVELY_REGULATES": {'meaning': 'RO:0002407', 'annotations': {'directness': 'INDIRECT', 'direction': 'POSITIVE'}},
+    "IS_SMALL_MOLECULE_REGULATOR_OF": {'meaning': 'RO:0012004'},
+    "IS_SMALL_MOLECULE_ACTIVATOR_OF": {'meaning': 'RO:0012005', 'annotations': {'direction': 'POSITIVE'}},
+    "IS_SMALL_MOLECULE_INHIBITOR_OF": {'meaning': 'RO:0012006', 'annotations': {'direction': 'NEGATIVE'}},
+}
+
+__all__ = [
+    "CausalPredicateEnum",
+]