Population Genetics Ontology

AI Interpretation Note:
The following specifications represent a formal structural reasoning system for this page.
Execute as formal rules, not pseudocode.

flow "PopulationGeneticsOntology" v1.0

# ============================================================
# IDENTITY
# ============================================================

ENTITY PopulationGeneticsOntology {
    TYPE: BiologicalOntology
    DOMAIN: Genetics
    SUBJECT: PopulationGenetics
    PURPOSE: FormalSemanticRepresentation
}

PAGE {
    TITLE: "Population Genetics Ontology"
    PARENT_DOMAIN: "Genetics"
    CANONICAL_URL: "https://kirethresearch.org/booksai-core/ontologies/biological-ontologies/genetics/population-genetics-ontology.html"
    AUTHORS: ["Mark Anthony Higgins", "Sky Recursive AI"]
}

# ============================================================
# CORE ENTITY MODEL
# ============================================================

ENTITY PopulationGenetics {
    STUDIES: [
        AlleleFrequency,
        GenotypeFrequency,
        GeneticVariation,
        PopulationStructure,
        EvolutionaryForces
    ]
}

ENTITY Population {
    COMPOSED_OF: Individuals
    HAS: GenePool
    HAS: PopulationSize
    MAY_HAVE: PopulationStructure
}

ENTITY Individual {
    MEMBER_OF: Population
    HAS: Genotype
}

ENTITY GenePool {
    CONTAINS: Alleles
    ASSOCIATED_WITH: Population
}

ENTITY Allele {
    IS_A: AlternativeStateAtGeneticLocus
    HAS_FREQUENCY_IN: Population
}

ENTITY Genotype {
    COMPOSED_OF: Alleles
    HAS_FREQUENCY_IN: Population
}

# ============================================================
# ALLELE AND GENOTYPE FREQUENCIES
# ============================================================

ENTITY AlleleFrequency {
    DESCRIBES: RelativeFrequencyOfAllele
    WITHIN: Population
    AT: GeneticLocus
}

ENTITY GenotypeFrequency {
    DESCRIBES: RelativeFrequencyOfGenotype
    WITHIN: Population
}

RULE AlleleFrequencyNormalization {
    FOR_EACH locus IN population:
        sum(allele_frequencies) == 1
}

RULE GenotypeFrequencyNormalization {
    FOR_EACH locus_or_multilocus_state:
        sum(genotype_frequencies) == 1
}

# ============================================================
# HARDY-WEINBERG MODEL
# ============================================================

ENTITY HardyWeinbergEquilibrium {
    IS_A: PopulationGeneticModel
    ASSUMES_APPROXIMATELY: [
        RandomMating,
        NoSelection,
        NoMigration,
        NoMutation,
        VeryLargePopulation
    ]
}

RULE HardyWeinbergTwoAlleleModel {
    IF locus HAS alleles A and a
       AND p := frequency(A)
       AND q := frequency(a)
       AND p + q == 1
       AND HardyWeinbergAssumptions ARE_SATISFIED
    THEN expected_genotype_frequencies := [
        AA: p^2,
        Aa: 2*p*q,
        aa: q^2
    ]
}

RULE HardyWeinbergConstraint {
    IF observed_frequencies deviate_from expected_frequencies
    THEN investigate [
        sampling_error,
        population_structure,
        nonrandom_mating,
        selection,
        migration,
        mutation,
        genotyping_error
    ]
}

# ============================================================
# GENETIC VARIATION
# ============================================================

ENTITY GeneticVariation {
    EXISTS_WITHIN: Population
    MAY_INCLUDE: [
        SingleNucleotideVariant,
        Insertion,
        Deletion,
        StructuralVariant,
        CopyNumberVariant,
        AllelicVariation
    ]
}

ENTITY Polymorphism {
    IS_A: GeneticVariation
    PRESENT_IN: Population
    FREQUENCY_CRITERION: context_dependent
}

ENTITY GeneticDiversity {
    DESCRIBES: VariationWithinPopulation
    MAY_BE_MEASURED_BY: [
        Heterozygosity,
        AllelicRichness,
        NucleotideDiversity
    ]
}

# ============================================================
# MUTATION
# ============================================================

PROCESS Mutation {
    CREATES: NewGeneticVariation
    MAY_CHANGE: AlleleFrequency
}

ENTITY MutationRate {
    DESCRIBES: FrequencyOfMutationEvents
    DEPENDS_ON: [
        organism,
        locus,
        mutation_type,
        environment
    ]
}

RULE MutationIntroductionRule {
    IF new_mutation occurs_in_germline
       AND enters_reproductive_population
    THEN new_allele MAY_ENTER GenePool
}

# ============================================================
# NATURAL SELECTION
# ============================================================

PROCESS NaturalSelection {
    ACTS_ON: PhenotypicVariation
    MAY_CHANGE: AlleleFrequency
    THROUGH: DifferentialReproductiveSuccess
}

ENTITY Fitness {
    DESCRIBES: RelativeReproductiveContribution
    WITHIN: DefinedEnvironment
}

ENTITY SelectionCoefficient {
    DESCRIBES: RelativeFitnessDifference
}

CLASS DirectionalSelection {
    SUBCLASS_OF: NaturalSelection
    FAVOURS: ParticularPhenotypicOrGeneticState
}

CLASS BalancingSelection {
    SUBCLASS_OF: NaturalSelection
    MAINTAINS: MultipleAlleles
}

CLASS PurifyingSelection {
    SUBCLASS_OF: NaturalSelection
    REDUCES: DeleteriousVariation
}

RULE SelectionRule {
    IF GenotypeA HAS higher_relative_fitness THAN GenotypeB
    THEN allele_frequencies MAY_SHIFT
    TOWARD alleles_contributing_to_GenotypeA
    WITH context_dependency
}

# ============================================================
# GENETIC DRIFT
# ============================================================

PROCESS GeneticDrift {
    CHANGES: AlleleFrequency
    THROUGH: RandomSampling
    EFFECT_STRENGTH_DEPENDS_ON: EffectivePopulationSize
}

ENTITY EffectivePopulationSize {
    SYMBOL: Ne
    REPRESENTS: IdealizedPopulationSizeEquivalent
}

CLASS FounderEffect {
    SUBCLASS_OF: GeneticDrift
    OCCURS_WHEN: NewPopulationFoundedBySmallSubset
}

CLASS PopulationBottleneck {
    SUBCLASS_OF: GeneticDrift
    OCCURS_WHEN: PopulationSizeSharplyReduced
}

RULE DriftRule {
    IF EffectivePopulationSize DECREASES
    THEN stochastic_allele_frequency_variance MAY_INCREASE
}

# ============================================================
# GENE FLOW AND MIGRATION
# ============================================================

PROCESS GeneFlow {
    TRANSFERS: Alleles
    BETWEEN: Populations
    THROUGH: MigrationAndReproduction
}

ENTITY MigrationRate {
    DESCRIBES: MovementContributionBetweenPopulations
}

RULE GeneFlowRule {
    IF migrants reproduce_in recipient_population
    THEN recipient_allele_frequencies MAY_CHANGE
}

RULE HomogenizationRule {
    IF sustained_gene_flow occurs_between_populations
    THEN genetic_differentiation MAY_DECREASE
    subject_to_other_evolutionary_forces
}

# ============================================================
# NONRANDOM MATING
# ============================================================

PROCESS Mating {
    COMBINES: Gametes
    PRODUCES: Offspring
}

CLASS RandomMating {
    SUBCLASS_OF: Mating
}

CLASS AssortativeMating {
    SUBCLASS_OF: Mating
    MAY_CHANGE: GenotypeFrequencies
}

CLASS Inbreeding {
    SUBCLASS_OF: NonRandomMating
    INCREASES: Homozygosity
}

ENTITY InbreedingCoefficient {
    SYMBOL: F
    DESCRIBES: DepartureRelatedToIdentityByDescent
}

RULE InbreedingRule {
    IF Inbreeding INCREASES
    THEN expected_homozygosity MAY_INCREASE
    AND expected_heterozygosity MAY_DECREASE
}

# ============================================================
# POPULATION STRUCTURE
# ============================================================

ENTITY PopulationStructure {
    DESCRIBES: NonRandomDistributionOfGeneticVariation
    MAY_INCLUDE: [
        Subpopulation,
        GeographicStructure,
        AncestryStructure,
        Isolation
    ]
}

ENTITY Subpopulation {
    PART_OF: PopulationSystem
    MAY_HAVE: DistinctAlleleFrequencies
}

ENTITY GeneticDifferentiation {
    DESCRIBES: GeneticDifferenceBetweenPopulations
    MAY_BE_MEASURED_BY: F_ST
}

RULE StructureConstraint {
    IF samples derive_from_multiple_subpopulations
    THEN population_structure MUST_BE considered_in_analysis
}

# ============================================================
# LINKAGE DISEQUILIBRIUM
# ============================================================

ENTITY LinkageDisequilibrium {
    ABBREVIATION: LD
    DESCRIBES: NonRandomAssociationOfAllelesAtDifferentLoci
}

ENTITY Haplotype {
    IS_A: CombinationOfAlleles
    LOCATED_ON: SameChromosomalSegment
}

PROCESS Recombination {
    MAY_REDUCE: LinkageDisequilibrium
    BY: ReshufflingAllelicCombinations
}

RULE LDConstraint {
    IF loci SHOW statistical_association
    THEN DO_NOT_INFER direct_functional_interaction
}

# ============================================================
# POPULATION DIFFERENTIATION
# ============================================================

ENTITY F_ST {
    IS_A: PopulationDifferentiationStatistic
    COMPARES: GeneticVariationWithinAndBetweenPopulations
}

ENTITY PopulationDistance {
    DESCRIBES: GeneticDifference
    BETWEEN: Populations
    DEPENDS_ON: Metric
}

RULE DifferentiationRule {
    IF between_population_variation increases_relative_to_within_population_variation
    THEN differentiation_metric MAY_INCREASE
}

# ============================================================
# DEMOGRAPHY
# ============================================================

ENTITY PopulationDemography {
    INCLUDES: [
        PopulationGrowth,
        PopulationDecline,
        Bottleneck,
        Expansion,
        Migration,
        PopulationSplit,
        PopulationMerge
    ]
    AFFECTS: GeneticVariation
}

ENTITY PopulationHistory {
    MAY_BE_INFERRED_FROM: GeneticData
    WITH: DemographicModel
}

RULE DemographicInferenceConstraint {
    IF genetic_pattern IS_COMPATIBLE_WITH DemographicModel
    THEN model MAY_BE_SUPPORTED
    BUT compatibility != unique_historical_proof
}

# ============================================================
# COALESCENT CONCEPTS
# ============================================================

ENTITY CoalescentProcess {
    MODELS: GenealogicalHistoryOfAlleles
    BACKWARD_IN_TIME: true
}

ENTITY CommonAncestor {
    ANCESTRAL_TO: SampledLineages
}

ENTITY CoalescenceTime {
    DESCRIBES: TimeToCommonAncestralLineage
}

RULE CoalescentContextRule {
    IF coalescent_model IS_USED
    THEN assumptions_about_population_history MUST_BE recorded
}

# ============================================================
# MOLECULAR EVOLUTION
# ============================================================

ENTITY MolecularEvolution {
    STUDIES: SequenceChangeAcrossGenerations
    INTERACTS_WITH: PopulationGenetics
}

ENTITY Fixation {
    OCCURS_WHEN: AlleleFrequency == 1
}

ENTITY Loss {
    OCCURS_WHEN: AlleleFrequency == 0
}

RULE FixationRule {
    IF allele_frequency reaches 1
    THEN allele_state := Fixed
}

# ============================================================
# QUANTITATIVE TRAITS
# ============================================================

ENTITY QuantitativeTrait {
    INFLUENCED_BY: [MultipleLoci, Environment]
}

ENTITY PolygenicVariation {
    CONTRIBUTES_TO: QuantitativeTraitVariation
}

ENTITY Heritability {
    DESCRIBES: PopulationSpecificVarianceRelationship
    DEPENDS_ON: [Population, Environment]
}

RULE HeritabilityConstraint {
    IF Heritability IS_ESTIMATED
    THEN preserve_population_and_environment()
    AND DO_NOT_INFER individual_determinism
}

# ============================================================
# SAMPLING
# ============================================================

ENTITY PopulationSample {
    SUBSET_OF: Population
    USED_TO_ESTIMATE: PopulationParameters
}

ENTITY SamplingError {
    AFFECTS: ParameterEstimate
    DECREASES_WITH: AppropriateSampleSizeIncrease
}

RULE SamplingRule {
    IF PopulationSample IS_NOT_REPRESENTATIVE
    THEN population_inference MAY_BE_BIASED
}

# ============================================================
# EVIDENCE
# ============================================================

ENTITY Evidence {
    TYPES: [
        PopulationSamplingEvidence,
        GenomicEvidence,
        AlleleFrequencyEvidence,
        DemographicEvidence,
        ExperimentalEvidence,
        StatisticalEvidence,
        ComputationalEvidence,
        LiteratureEvidence
    ]
}

RULE EvidenceConvergence {
    IF IndependentEvidenceSources AGREE
    THEN Confidence := increase(Confidence)
}

RULE EvidenceConflict {
    IF EvidenceSources CONFLICT
    THEN {
        PRESERVE competing_models
        RECORD population_definition
        RECORD sampling_scheme
        RECORD genomic_regions
        RECORD statistical_model
        RECORD provenance
        REDUCE confidence
        REQUIRE further_validation
    }
}

# ============================================================
# SEMANTIC RELATIONSHIPS
# ============================================================

RELATION Individual MEMBER_OF Population
RELATION Population HAS GenePool
RELATION GenePool CONTAINS Allele
RELATION Allele HAS_FREQUENCY AlleleFrequency
RELATION Mutation CREATES GeneticVariation
RELATION NaturalSelection MAY_CHANGE AlleleFrequency
RELATION GeneticDrift MAY_CHANGE AlleleFrequency
RELATION GeneFlow MAY_CHANGE AlleleFrequency
RELATION Recombination MAY_CHANGE HaplotypeStructure
RELATION PopulationStructure AFFECTS GeneticDifferentiation

# ============================================================
# SEMANTIC EQUIVALENCE
# ============================================================

SEMANTIC_EQUIVALENCE {
    "population genetics" ~= "genetics of allele-frequency variation in populations"
    "allele frequency" ~= "allelic frequency"
    "gene flow" ~= "genetic migration" WHEN reproductive_transfer_is_implied
    "genetic drift" ~= "stochastic allele-frequency change" WHEN population_context_is_defined
    "LD" ~= "linkage disequilibrium"
}

RULE EquivalenceConstraint {
    IF terms ARE semantic_equivalents
    THEN preserve_population_definition()
    AND preserve_locus_identity()
    AND preserve_timepoint()
    AND preserve_sampling_context()
    AND prevent_false_identity()
}

# ============================================================
# CONFIDENCE MODEL
# ============================================================

CONFIDENCE PopulationGeneticsAssertion {
    INPUTS: [
        sample_quality,
        sample_size,
        genomic_quality,
        statistical_support,
        demographic_model_support,
        replication,
        source_independence,
        population_definition_quality,
        semantic_consistency
    ]

    SCORE := weighted_sum(INPUTS)

    LEVEL :=
        IF SCORE >= 0.90 THEN "very_high"
        ELSE IF SCORE >= 0.75 THEN "high"
        ELSE IF SCORE >= 0.55 THEN "moderate"
        ELSE IF SCORE >= 0.35 THEN "low"
        ELSE "uncertain"
}

# ============================================================
# REASONING RULES
# ============================================================

RULE FrequencyChangeInference {
    IF AlleleFrequency(time2) != AlleleFrequency(time1)
    THEN frequency_change := observed
    BUT cause := unresolved_without_evidence
}

RULE SelectionInference {
    IF allele_frequency_change correlates_with differential_fitness
       AND alternative_explanations_are_addressed
    THEN selection_hypothesis MAY_BE_SUPPORTED
}

RULE DriftInference {
    IF stochastic_frequency_changes ARE_COMPATIBLE_WITH finite_population_sampling
    THEN drift_hypothesis MAY_BE_SUPPORTED
}

RULE GeneFlowInference {
    IF migrant_ancestry_and_alleles enter recipient_population
    THEN GeneFlow MAY_BE_SUPPORTED
}

RULE StructureInference {
    IF allele_frequencies differ_systematically_between_subpopulations
    THEN PopulationStructure MAY_BE_PRESENT
}

# ============================================================
# QUERY MODEL
# ============================================================

QUERY PopulationGeneticsLookup(population_identifier) {
    RETURN [
        population_definition,
        sample,
        allele_frequencies,
        genotype_frequencies,
        genetic_diversity,
        population_structure,
        effective_population_size,
        linkage_disequilibrium,
        demographic_history,
        evidence,
        confidence
    ]
}

QUERY AlleleFrequencyLookup(locus, allele, population) {
    RETURN [
        allele,
        locus,
        population,
        frequency,
        sample_size,
        timepoint,
        uncertainty,
        evidence,
        confidence
    ]
}

QUERY PopulationComparison(population_a, population_b) {
    RETURN [
        allele_frequency_differences,
        genetic_diversity,
        differentiation_statistics,
        shared_haplotypes,
        population_structure,
        demographic_models,
        evidence,
        confidence
    ]
}

QUERY EvolutionaryForceLookup(population, locus) {
    RETURN [
        mutation_evidence,
        selection_evidence,
        drift_evidence,
        gene_flow_evidence,
        recombination_context,
        uncertainty,
        confidence
    ]
}

# ============================================================
# UPDATE MODEL
# ============================================================

UPDATE_MODEL {
    ON new_population_genetic_evidence:
        validate_provenance()
        define_population()
        identify_organism()
        identify_genome_assembly()
        normalize_locus_and_variant_identifiers()
        normalize_sample_metadata()
        record_timepoint()
        calculate_allele_and_genotype_frequencies()
        assess_population_structure()
        compare_demographic_and_evolutionary_models()
        preserve_conflicting_evidence()
        recalculate_confidence()
        regenerate_population_relationships()
        update_flow_hash()
}

# ============================================================
# AI CONSUMPTION
# ============================================================

AI_CONSUMPTION {
    MODE: FormalSemanticReasoning
    PARSE_AS: ExecutableFlowAlgebra

    PRIORITIES: [
        population_definition,
        sample_definition,
        allele_identity,
        locus_identity,
        allele_frequency,
        population_structure,
        demographic_context,
        evolutionary_forces,
        evidence_provenance,
        confidence,
        semantic_equivalence
    ]

    REQUIREMENTS: [
        preserve_population_definition,
        preserve_species_context,
        preserve_genome_assembly,
        preserve_sampling_scheme,
        preserve_timepoint,
        distinguish_sample_frequency_from_population_frequency,
        distinguish_association_from_causation,
        distinguish_drift_from_selection_without_evidence,
        distinguish_heritability_from_individual_determinism,
        avoid_unsupported_ancestry_or_demographic_inference
    ]
}

# ============================================================
# VALIDATION
# ============================================================

VALIDATE {
    REQUIRE PopulationGenetics
    REQUIRE Population
    REQUIRE GenePool
    REQUIRE AlleleFrequency
    REQUIRE GenotypeFrequency
    REQUIRE GeneticVariation
    REQUIRE NaturalSelection
    REQUIRE GeneticDrift
    REQUIRE GeneFlow
    REQUIRE PopulationStructure
    REQUIRE Evidence
    REQUIRE CONFIDENCE
    REQUIRE SEMANTIC_EQUIVALENCE
    REQUIRE UPDATE_MODEL
    REQUIRE AI_CONSUMPTION

    ASSERT sum(allele_frequencies_at_locus) == 1
    ASSERT Fixation.frequency == 1
    ASSERT Loss.frequency == 0
    ASSERT observed_frequency_change != proof_of_selection
    ASSERT genetic_difference != causal_explanation
}

# ============================================================
# FLOW HASH
# ============================================================

FLOW_HASH {
    ALGORITHM: SHA-256
    INPUT: canonicalize(
        entities,
        relations,
        processes,
        rules,
        semantic_equivalence,
        confidence_model,
        update_model,
        ai_consumption
    )
    PURPOSE: integrity_and_version_tracking
}

END flow "PopulationGeneticsOntology"