Biomolecule Ontology

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

flow "BiomoleculeOntology" v1.0

ENTITY BiomoleculeOntology {
  TYPE: BiologicalOntology
  DOMAIN: Biochemistry
  SUBJECT: Biomolecule
  PURPOSE: FormalSemanticRepresentation
}

PAGE {
  TITLE: "Biomolecule Ontology"
  PARENT_DOMAIN: "Biochemistry"
  CANONICAL_URL: "https://kirethresearch.org/booksai-core/ontologies/biological-ontologies/biochemistry/biomolecule-ontology.html"
  AUTHORS: ["Mark Anthony Higgins", "Sky Recursive AI"]
}

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

ENTITY Biomolecule {
  IS_A: Molecule
  OCCURS_IN_OR_IS_PRODUCED_BY: BiologicalSystem
  MAY_BE: [Protein, NucleicAcid, Carbohydrate, Lipid, Metabolite]
  MAY_HAVE: [Structure, Function, CellularLocation]
}

ENTITY BiologicalSystem {
  MAY_BE: [Cell, Organelle, Tissue, Organism]
  CONTAINS: Biomolecule
}

ENTITY MolecularStructure {
  DESCRIBES: AtomicAndBondingArrangement
  INFLUENCES: MolecularProperties
}

ENTITY MolecularFunction {
  DESCRIBES: BiologicalOrChemicalRole
}

RULE StructureFunctionRule {
  MolecularFunction MAY_DEPEND_ON [
    MolecularStructure,
    ChemicalState,
    MolecularEnvironment,
    InteractionPartners
  ]
}

# ============================================================
# ATOMIC AND CHEMICAL COMPOSITION
# ============================================================

ENTITY Atom {
  COMPOSES: Biomolecule
  HAS: ElementIdentity
}

ENTITY ChemicalBond {
  CONNECTS: Atoms
  MAY_BE: [CovalentBond, IonicInteraction, HydrogenBond]
}

ENTITY FunctionalGroup {
  PART_OF: Biomolecule
  CONTRIBUTES_TO: ChemicalReactivity
}

ENTITY ChemicalState {
  MAY_INCLUDE: [ProtonationState, OxidationState, ModificationState]
}

# ============================================================
# MACROMOLECULES
# ============================================================

ENTITY BiologicalMacromolecule {
  SUBCLASS_OF: Biomolecule
  MAY_BE: [Protein, NucleicAcid, Polysaccharide]
}

ENTITY Monomer {
  MAY_FORM: Polymer
}

ENTITY Polymer {
  COMPOSED_OF: RepeatingOrRelatedMonomerUnits
}

RULE PolymerizationRule {
  IF Monomers ARE_COVALENTLY_JOINED_IN_CHAIN_OR_NETWORK
  THEN Polymer MAY_FORM
}

# ============================================================
# PROTEINS
# ============================================================

ENTITY Protein {
  SUBCLASS_OF: BiologicalMacromolecule
  COMPOSED_OF: AminoAcid
  HAS: [AminoAcidSequence, ProteinStructure]
  MAY_HAVE: MolecularFunction
}

ENTITY AminoAcid {
  IS_A: BiomolecularMonomer
  CONNECTED_BY: PeptideBond
}

ENTITY PeptideBond {
  CONNECTS: AminoAcids
  WITHIN: Polypeptide
}

ENTITY Polypeptide {
  COMPOSED_OF: AminoAcid
  MAY_FORM: Protein
}

RULE ProteinIdentityRule {
  IF Polypeptide undergoes_folding_and_processing
  THEN mature_product MAY_BE Protein
}

# ============================================================
# NUCLEIC ACIDS
# ============================================================

ENTITY NucleicAcid {
  SUBCLASS_OF: BiologicalMacromolecule
  COMPOSED_OF: Nucleotide
  MAY_BE: [DNA, RNA]
}

ENTITY Nucleotide {
  IS_A: BiomolecularMonomer
  COMPOSED_OF: [NitrogenousBase, PentoseSugar, PhosphateGroup]
}

ENTITY DNA {
  SUBCLASS_OF: NucleicAcid
  STORES: GeneticInformation
}

ENTITY RNA {
  SUBCLASS_OF: NucleicAcid
  MAY_FUNCTION_IN: [InformationTransfer, Catalysis, Regulation, Translation]
}

ENTITY PhosphodiesterBond {
  CONNECTS: Nucleotides
  WITHIN: NucleicAcid
}

# ============================================================
# CARBOHYDRATES
# ============================================================

ENTITY Carbohydrate {
  SUBCLASS_OF: Biomolecule
  MAY_BE: [Monosaccharide, Disaccharide, Oligosaccharide, Polysaccharide]
  MAY_FUNCTION_IN: [Energy, Storage, Structure, Recognition]
}

ENTITY Monosaccharide {
  IS_A: CarbohydrateMonomer
}

ENTITY GlycosidicBond {
  CONNECTS: SugarResidues
}

ENTITY Polysaccharide {
  SUBCLASS_OF: BiologicalMacromolecule
  COMPOSED_OF: MonosaccharideUnits
}

RULE CarbohydrateStructureRule {
  CarbohydrateProperties MAY_DEPEND_ON [
    monosaccharide_identity,
    linkage_type,
    branching,
    stereochemistry
  ]
}

# ============================================================
# LIPIDS
# ============================================================

ENTITY Lipid {
  SUBCLASS_OF: Biomolecule
  MAY_INCLUDE: [FattyAcid, Triacylglycerol, Phospholipid, Sterol, Sphingolipid]
  MAY_FUNCTION_IN: [MembraneStructure, EnergyStorage, Signalling]
}

ENTITY FattyAcid {
  MAY_BE: [Saturated, Unsaturated]
  HAS: HydrocarbonChain
}

ENTITY Phospholipid {
  SUBCLASS_OF: Lipid
  HAS: [HydrophilicHead, HydrophobicTails]
  CONTRIBUTES_TO: BiologicalMembrane
}

ENTITY Sterol {
  SUBCLASS_OF: Lipid
  MAY_MODULATE: MembraneProperties
}

# ============================================================
# METABOLITES
# ============================================================

ENTITY Metabolite {
  SUBCLASS_OF: Biomolecule
  PARTICIPATES_IN: MetabolicReaction
  MAY_BE: [Substrate, Intermediate, Product, Cofactor]
}

ENTITY PrimaryMetabolite {
  SUBCLASS_OF: Metabolite
  ASSOCIATED_WITH: CoreMetabolism
}

ENTITY SecondaryMetabolite {
  SUBCLASS_OF: Metabolite
  ASSOCIATED_WITH: SpecializedBiologicalFunction
}

# ============================================================
# COFACTORS AND COENZYMES
# ============================================================

ENTITY Cofactor {
  MAY_ASSOCIATE_WITH: Protein
  ASSISTS: BiologicalFunction
  MAY_BE: [MetalIon, OrganicCofactor]
}

ENTITY Coenzyme {
  SUBCLASS_OF: OrganicCofactor
  PARTICIPATES_IN: EnzymeCatalysis
}

ENTITY ProstheticGroup {
  IS_A: TightlyBoundCofactor
}

# ============================================================
# MOLECULAR ASSEMBLIES
# ============================================================

ENTITY MolecularComplex {
  COMPOSED_OF: MultipleMolecularEntities
  MAY_INCLUDE: Biomolecule
}

ENTITY RibonucleoproteinComplex {
  SUBCLASS_OF: MolecularComplex
  COMPOSED_OF: [RNA, Protein]
}

ENTITY LipoproteinComplex {
  SUBCLASS_OF: MolecularComplex
  COMPOSED_OF: [Lipid, Protein]
}

RULE ComplexDistinction {
  MolecularComplex != single_Biomolecule
  UNLESS ontology_context_explicitly_models_complex_as_entity
}

# ============================================================
# BIOMOLECULAR INTERACTIONS
# ============================================================

ENTITY MolecularInteraction {
  RELATES: Biomolecules
  MAY_BE: [Binding, Catalysis, Regulation, Transport]
}

PROCESS MolecularBinding {
  INPUTS: [BiomoleculeA, BiomoleculeB]
  MAY_FORM: MolecularComplex
}

ENTITY BindingSite {
  PART_OF: Biomolecule
  INTERACTS_WITH: BindingPartner
}

ENTITY BindingAffinity {
  DESCRIBES: StrengthOfAssociation
}

RULE BindingConstraint {
  IF BiomoleculeA BINDS BiomoleculeB
  THEN DO_NOT_INFER functional_consequence
  WITHOUT functional_evidence
}

# ============================================================
# CELLULAR LOCATION
# ============================================================

ENTITY CellularLocation {
  MAY_INCLUDE: [
    Cytosol,
    Nucleus,
    PlasmaMembrane,
    Mitochondrion,
    EndoplasmicReticulum,
    GolgiApparatus,
    Lysosome,
    ExtracellularSpace
  ]
}

RELATION Biomolecule LOCATED_IN CellularLocation

RULE LocalizationConstraint {
  IF Biomolecule IS_DETECTED_IN CellularLocation
  THEN location := supported
  BUT exclusive_localization MUST_NOT_BE_ASSUMED
}

# ============================================================
# BIOSYNTHESIS
# ============================================================

PROCESS Biosynthesis {
  PRODUCES: Biomolecule
  FROM: Precursors
  MAY_REQUIRE: [Enzyme, Energy, Cofactor]
}

PROCESS ProteinSynthesis {
  PRODUCES: Polypeptide
}

PROCESS NucleicAcidSynthesis {
  PRODUCES: NucleicAcid
}

PROCESS LipidSynthesis {
  PRODUCES: Lipid
}

PROCESS CarbohydrateSynthesis {
  PRODUCES: Carbohydrate
}

# ============================================================
# DEGRADATION
# ============================================================

PROCESS BiomoleculeDegradation {
  BREAKS_DOWN: Biomolecule
  PRODUCES: SmallerMolecules
  MAY_RECYCLE: Components
}

RULE TurnoverRule {
  BiomoleculeAbundance :=
    synthesis_rate balanced_against degradation_rate
}

# ============================================================
# POST-SYNTHETIC MODIFICATION
# ============================================================

PROCESS BiomoleculeModification {
  TARGET: Biomolecule
  MAY_CHANGE: [Structure, Charge, Activity, Localization, Interactions]
}

CLASS PostTranslationalModification {
  SUBCLASS_OF: BiomoleculeModification
  TARGET: Protein
}

CLASS RNA_Modification {
  SUBCLASS_OF: BiomoleculeModification
  TARGET: RNA
}

CLASS Glycosylation {
  SUBCLASS_OF: BiomoleculeModification
  ADDS_OR_MODIFIES: CarbohydrateGroup
}

# ============================================================
# CONCENTRATION AND ABUNDANCE
# ============================================================

ENTITY BiomoleculeConcentration {
  DESCRIBES: AmountPerDefinedVolumeOrCompartment
}

ENTITY BiomoleculeAbundance {
  DESCRIBES: AmountWithinDefinedBiologicalContext
}

RULE MeasurementContextRule {
  IF BiomoleculeAbundance IS_REPORTED
  THEN preserve [
    biological_context,
    compartment,
    measurement_method,
    normalization_method
  ]
}

# ============================================================
# PHYSICAL AND CHEMICAL PROPERTIES
# ============================================================

ENTITY MolecularMass {
  DESCRIBES: MassOfMolecule
}

ENTITY Charge {
  DEPENDS_ON: [ChemicalComposition, ProtonationState]
}

ENTITY Solubility {
  DEPENDS_ON: [MolecularStructure, Solvent, Temperature, pH]
}

ENTITY Hydrophobicity {
  DESCRIBES: InteractionPreferenceWithAqueousEnvironment
}

RULE PropertyContextRule {
  MolecularProperty MAY_CHANGE_WITH environmental_conditions
}

# ============================================================
# FUNCTIONAL CLASSES
# ============================================================

ENTITY StructuralBiomolecule {
  CONTRIBUTES_TO: BiologicalStructure
}

ENTITY CatalyticBiomolecule {
  CATALYSES: ChemicalReaction
}

ENTITY RegulatoryBiomolecule {
  MODULATES: BiologicalProcess
}

ENTITY SignallingBiomolecule {
  PARTICIPATES_IN: SignalTransduction
}

ENTITY EnergyCarrier {
  TRANSFERS_OR_STORES: ChemicalEnergy
}

ENTITY InformationCarrier {
  STORES_OR_TRANSFERS: BiologicalInformation
}

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

ENTITY Evidence {
  TYPES: [
    BiochemicalEvidence,
    StructuralEvidence,
    SpectroscopicEvidence,
    ProteomicEvidence,
    MetabolomicEvidence,
    GenomicEvidence,
    ExperimentalEvidence,
    ComputationalEvidence,
    LiteratureEvidence
  ]
}

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

RULE EvidenceConflict {
  IF EvidenceSources CONFLICT
  THEN {
    PRESERVE competing_assertions
    RECORD biomolecule_identity
    RECORD chemical_state
    RECORD cellular_context
    RECORD assay_method
    RECORD provenance
    REDUCE confidence
    REQUIRE further_validation
  }
}

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

RELATION Biomolecule HAS MolecularStructure
RELATION Biomolecule MAY_HAVE MolecularFunction
RELATION Protein COMPOSED_OF AminoAcid
RELATION NucleicAcid COMPOSED_OF Nucleotide
RELATION Polysaccharide COMPOSED_OF MonosaccharideUnits
RELATION Phospholipid PART_OF BiologicalMembrane
RELATION Metabolite PARTICIPATES_IN MetabolicReaction
RELATION Biomolecule MAY_FORM MolecularComplex
RELATION Biomolecule LOCATED_IN CellularLocation

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

SEMANTIC_EQUIVALENCE {
  "biomolecule" ~= "biological molecule"
  "biological macromolecule" ~= "biomacromolecule"
  "protein molecule" ~= "protein" WHEN molecular_entity_context
  "nucleic acid" ~= "polynucleotide" WHEN polymer_context_is_defined
  "metabolite" ~= "metabolic small molecule" WHEN metabolism_context_is_defined
}

RULE EquivalenceConstraint {
  IF terms ARE semantic_equivalents
  THEN preserve_molecular_identity()
  AND preserve_chemical_state()
  AND preserve_cellular_context()
  AND preserve_organism_context()
  AND prevent_false_identity()
}

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

CONFIDENCE BiomoleculeAssertion {
  INPUTS: [
    chemical_identity_support,
    structural_support,
    biochemical_support,
    analytical_quality,
    localization_support,
    functional_support,
    replication,
    source_independence,
    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 ClassificationInference {
  IF molecule HAS defining_structural_features_of BiomoleculeClass
  THEN class_membership MAY_BE_SUPPORTED
  WITH confidence := derive(Evidence)
}

RULE StructureFunctionInference {
  IF structural_feature has_known_functional_role
     AND Biomolecule contains_structural_feature
  THEN Biomolecule MAY_HAVE associated_function
  WITH confidence := context_dependent
}

RULE InteractionInference {
  IF BiomoleculeA physically_associates_with BiomoleculeB
  THEN MolecularInteraction MAY_EXIST
  WITH confidence := derive(Evidence)
}

RULE AbundanceInference {
  IF synthesis_rate > degradation_rate
  THEN BiomoleculeAbundance MAY_INCREASE
  subject_to_transport_and_compartmentalization
}

RULE CausalityConstraint {
  IF Biomolecule abundance correlates_with BiologicalProcess
  THEN DO_NOT_INFER causal_role
  WITHOUT functional_evidence
}

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

QUERY BiomoleculeLookup(identifier) {
  RETURN [
    identity,
    molecular_class,
    composition,
    structure,
    chemical_state,
    functions,
    interactions,
    cellular_locations,
    biosynthesis,
    degradation,
    modifications,
    abundance,
    evidence,
    confidence
  ]
}

QUERY BiomoleculeClassLookup(class_identifier) {
  RETURN [
    members,
    defining_features,
    monomers,
    bonds,
    functions,
    cellular_contexts,
    evidence,
    confidence
  ]
}

QUERY BiomoleculeInteractionLookup(entity_a, entity_b) {
  RETURN [
    interaction_type,
    binding_sites,
    affinity,
    complex,
    cellular_context,
    functional_effect,
    evidence,
    confidence
  ]
}

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

UPDATE_MODEL {
  ON new_biomolecule_evidence:
    validate_provenance()
    normalize_molecular_identifier()
    identify_organism()
    identify_cellular_context()
    normalize_chemical_state()
    map_structure_and_functional_groups()
    map_interactions_and_complexes()
    record_assay_method()
    compare_existing_assertions()
    preserve_conflicting_evidence()
    recalculate_confidence()
    regenerate_biomolecular_relationships()
    update_flow_hash()
}

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

AI_CONSUMPTION {
  MODE: FormalSemanticReasoning
  PARSE_AS: ExecutableFlowAlgebra

  PRIORITIES: [
    molecular_identity,
    biomolecule_class,
    chemical_composition,
    molecular_structure,
    chemical_state,
    cellular_location,
    biological_function,
    interaction_context,
    evidence_provenance,
    confidence
  ]

  REQUIREMENTS: [
    distinguish_biomolecule_from_molecular_complex,
    preserve_molecular_identity,
    preserve_chemical_state,
    preserve_species_context,
    preserve_cellular_compartment,
    distinguish_structure_from_function,
    distinguish_binding_from_function,
    distinguish_abundance_from_activity,
    distinguish_observed_from_predicted_properties,
    avoid_unsupported_causal_inference
  ]
}

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

VALIDATE {
  REQUIRE Biomolecule
  REQUIRE BiologicalSystem
  REQUIRE MolecularStructure
  REQUIRE Protein
  REQUIRE NucleicAcid
  REQUIRE Carbohydrate
  REQUIRE Lipid
  REQUIRE Metabolite
  REQUIRE MolecularInteraction
  REQUIRE Evidence
  REQUIRE CONFIDENCE
  REQUIRE SEMANTIC_EQUIVALENCE
  REQUIRE UPDATE_MODEL
  REQUIRE AI_CONSUMPTION

  ASSERT Biomolecule != MolecularComplex
  ASSERT Protein IS_A Biomolecule
  ASSERT NucleicAcid IS_A Biomolecule
  ASSERT structure != function
  ASSERT binding != causal_function
}

# ============================================================
# 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 "BiomoleculeOntology"