Protein Structure Ontology

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

flow "ProteinStructureOntology" v1.0

ENTITY ProteinStructureOntology {
 TYPE: BiologicalOntology
 DOMAIN: Biochemistry
 SUBJECT: ProteinStructure
 PURPOSE: FormalSemanticRepresentation
}

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

ENTITY Protein {
 IS_A: BiologicalMacromolecule
 COMPOSED_OF: AminoAcid
 HAS: ProteinStructure
}

ENTITY ProteinStructure {
 LEVELS: [PrimaryStructure, SecondaryStructure, TertiaryStructure, QuaternaryStructure]
 INFLUENCES: ProteinFunction
}

ENTITY PrimaryStructure {
 DEFINED_BY: AminoAcidSequence
}

ENTITY AminoAcidSequence {
 IS_ORDERED_SEQUENCE_OF: AminoAcid
 DIRECTION: "N-terminus to C-terminus"
}

ENTITY SecondaryStructure {
 MAY_INCLUDE: [AlphaHelix, BetaSheet, Turn, Coil]
 STABILIZED_PRIMARILY_BY: BackboneHydrogenBonding
}

ENTITY AlphaHelix { SUBCLASS_OF: SecondaryStructure }
ENTITY BetaSheet { SUBCLASS_OF: SecondaryStructure }
ENTITY Turn { SUBCLASS_OF: SecondaryStructure }
ENTITY Coil { SUBCLASS_OF: SecondaryStructure }

ENTITY TertiaryStructure {
 DESCRIBES: ThreeDimensionalFold
 STABILIZED_BY: [HydrophobicInteraction, HydrogenBond, IonicInteraction, VanDerWaalsInteraction, DisulfideBond]
}

ENTITY QuaternaryStructure {
 DESCRIBES: AssemblyOfMultiplePolypeptideSubunits
}

ENTITY ProteinSubunit {
 PART_OF: MultimericProtein
}

ENTITY ProteinDomain {
 PART_OF: Protein
 MAY_FOLD: SemiIndependently
 MAY_HAVE: MolecularFunction
}

ENTITY StructuralMotif {
 IS_A: RecurringStructuralPattern
}

ENTITY SequenceMotif {
 IS_A: RecurringAminoAcidPattern
 MAY_CORRESPOND_TO: StructuralOrFunctionalFeature
}

ENTITY ActiveSite {
 PART_OF: ProteinStructure
 ENABLES: Catalysis
}

ENTITY BindingSite {
 PART_OF: ProteinStructure
 BINDS: LigandOrPartner
}

ENTITY InteractionInterface {
 PART_OF: ProteinSurface
 CONTACTS: MolecularPartner
}

PROCESS ProteinFolding {
 INPUT: Polypeptide
 OUTPUT: FoldedProtein
 INFLUENCED_BY: [AminoAcidSequence, CellularEnvironment, ChaperoneProtein]
}

ENTITY NativeState {
 REPRESENTS: FunctionallyRelevantFoldedState
 UNDER: DefinedConditions
}

ENTITY ChaperoneProtein {
 ASSISTS: ProteinFolding
 MAY_PREVENT: Aggregation
}

ENTITY MisfoldedProtein {
 HAS: NonNativeConformation
 MAY_HAVE: AlteredFunction
 MAY_AGGREGATE: true
}

PROCESS ProteinAggregation {
 ASSOCIATES: MultipleProteinMolecules
 MAY_FORM: ProteinAggregate
}

ENTITY IntrinsicallyDisorderedRegion {
 ABBREVIATION: IDR
 PART_OF: Protein
 LACKS: SingleStableThreeDimensionalStructure
 UNDER: RelevantConditions
 MAY_HAVE: BiologicalFunction
}

ENTITY ProteinConformation {
 IS_A: StructuralState
}

PROCESS ConformationalChange {
 TRANSFORMS: ProteinConformation
 MAY_BE_TRIGGERED_BY: [LigandBinding, PostTranslationalModification, pHChange, TemperatureChange]
}

ENTITY ConformationalEnsemble {
 REPRESENTS: MultipleAccessibleProteinConformations
}

PROCESS AllostericRegulation {
 INVOLVES: StructuralOrDynamicCoupling
 BETWEEN: DistinctProteinSites
}

ENTITY AllostericSite {
 PART_OF: Protein
 DISTINCT_FROM: PrimaryFunctionalSite
}

PROCESS PostTranslationalModification {
 TARGET: Protein
 MAY_INCLUDE: [Phosphorylation, Glycosylation, Acetylation, Methylation, Ubiquitination]
 MAY_AFFECT: ProteinStructure
}

ENTITY MembraneProtein {
 SUBCLASS_OF: Protein
 ASSOCIATED_WITH: BiologicalMembrane
}

ENTITY TransmembraneHelix {
 SPANS: BiologicalMembrane
}

ENTITY BetaBarrel {
 IS_A: ProteinFold
 MAY_FORM: MembraneSpanningStructure
}

ENTITY ProteinStability {
 DESCRIBES: ResistanceToUnfoldingOrDegradation
 DEPENDS_ON: [Structure, Environment, Sequence]
}

PROCESS Denaturation {
 DISRUPTS: NativeProteinStructure
 MAY_BE_CAUSED_BY: [Heat, ExtremePH, ChemicalDenaturant]
}

ENTITY ProteinVariant {
 DIFFERS_IN: AminoAcidSequence
 MAY_AFFECT: ProteinStructure
}

ENTITY ProteinFold {
 REPRESENTS: CharacteristicThreeDimensionalArchitecture
}

PROCESS ProteinStructureDetermination {
 MAY_USE: [XRayCrystallography, NuclearMagneticResonance, CryoElectronMicroscopy]
 OUTPUT: StructuralModel
}

ENTITY StructuralModel {
 REPRESENTS: ProteinStructure
 HAS: [Method, ResolutionOrUncertainty, ExperimentalConditions]
}

ENTITY ExperimentalStructure {
 SUBCLASS_OF: StructuralModel
 SUPPORTED_BY: ExperimentalData
}

PROCESS ProteinStructurePrediction {
 INPUT: AminoAcidSequence
 OUTPUT: PredictedStructure
}

ENTITY PredictedStructure {
 SUBCLASS_OF: StructuralModel
 HAS: PredictionConfidence
}

PROCESS StructuralAlignment {
 COMPARES: ProteinStructures
 MAY_IDENTIFY: StructuralSimilarity
}

ENTITY Evidence {
 TYPES: [CrystallographicEvidence, NMREvidence, CryoEMEvidence, BiochemicalEvidence, BiophysicalEvidence, MutationalEvidence, ComputationalEvidence, ComparativeEvidence, LiteratureEvidence]
}

RULE StructureHierarchy {
 PrimaryStructure INFLUENCES SecondaryStructure
 SecondaryStructure CONTRIBUTES_TO TertiaryStructure
 TertiaryStructure MAY_CONTRIBUTE_TO QuaternaryStructure
}

RULE FoldingRule {
 IF Polypeptide reaches_native_like_conformation
 THEN functional_state MAY_BE achieved
 subject_to_modification_and_assembly
}

RULE DisorderConstraint {
 lack_of_fixed_structure != lack_of_function
}

RULE DynamicStructureRule {
 ProteinStructure MAY_EXIST_AS ensemble_of_conformations
 RATHER_THAN single_rigid_state
}

RULE SiteStructureRule {
 IF structural_change alters ActiveSite OR BindingSite
 THEN ProteinFunction MAY_CHANGE
}

RULE PredictionDistinction {
 PredictedStructure != ExperimentalStructure
}

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

RULE EvidenceConflict {
 IF EvidenceSources CONFLICT
 THEN {
  PRESERVE competing_structural_models
  RECORD protein_identity
  RECORD isoform
  RECORD modification_state
  RECORD experimental_conditions
  RECORD method
  RECORD provenance
  REDUCE confidence
 }
}

RELATION Protein HAS_STRUCTURE ProteinStructure
RELATION PrimaryStructure DEFINED_BY AminoAcidSequence
RELATION Protein HAS_DOMAIN ProteinDomain
RELATION Protein HAS_BINDING_SITE BindingSite
RELATION ProteinFolding PRODUCES FoldedProtein
RELATION StructuralModel REPRESENTS ProteinStructure

SEMANTIC_EQUIVALENCE {
 "primary structure" ~= "amino acid sequence"
 "protein domain" ~= "structural functional domain" WHEN protein_context_is_defined
 "protein fold" ~= "protein structural fold"
 "IDR" ~= "intrinsically disordered region"
}

CONFIDENCE ProteinStructureAssertion {
 INPUTS: [experimental_method_quality, resolution_or_uncertainty, structural_coverage, biochemical_support, biophysical_support, prediction_confidence, 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"
}

RULE SequenceStructureInference {
 IF AminoAcidSequence IS_KNOWN
 THEN ProteinStructure MAY_BE predicted
 WITH confidence := method_dependent
}

RULE StructureFunctionInference {
 IF ProteinStructure contains_functionally_characterized_site
 THEN related_function MAY_BE_SUPPORTED
 WITH contextual_evidence
}

RULE VariantEffectInference {
 IF sequence_variant alters_structurally_critical_residue
 THEN structural_effect MAY_BE predicted
 BUT experimental_confirmation := preferred
}

QUERY ProteinStructureLookup(protein_identifier) {
 RETURN [protein_identity, isoform, amino_acid_sequence, primary_structure, secondary_structure, tertiary_structure, quaternary_structure, domains, motifs, active_sites, binding_sites, conformational_states, experimental_structures, predicted_structures, evidence, confidence]
}

QUERY ProteinDomainLookup(domain_identifier) {
 RETURN [parent_proteins, sequence_boundaries, structure, motifs, functions, interactions, evidence, confidence]
}

UPDATE_MODEL {
 ON new_protein_structure_evidence:
  validate_provenance()
  normalize_protein_identifier()
  identify_organism()
  identify_isoform()
  capture_modification_state()
  capture_experimental_conditions()
  classify_structure_method()
  map_structural_regions_domains_and_sites()
  compare_structural_models()
  preserve_conflicting_models()
  recalculate_confidence()
  regenerate_structure_function_links()
  update_flow_hash()
}

AI_CONSUMPTION {
 MODE: FormalSemanticReasoning
 PARSE_AS: ExecutableFlowAlgebra
 PRIORITIES: [protein_identity, isoform, amino_acid_sequence, structural_level, domains_and_sites, conformational_state, experimental_method, prediction_status, evidence_provenance, confidence]
 REQUIREMENTS: [distinguish_sequence_from_structure, distinguish_secondary_tertiary_and_quaternary_structure, preserve_species_context, preserve_isoform_identity, preserve_post_translational_state, preserve_experimental_conditions, distinguish_experimental_from_predicted_structure, distinguish_structure_from_function, distinguish_similarity_from_homology]
}

VALIDATE {
 REQUIRE Protein
 REQUIRE ProteinStructure
 REQUIRE PrimaryStructure
 REQUIRE SecondaryStructure
 REQUIRE TertiaryStructure
 REQUIRE QuaternaryStructure
 REQUIRE ProteinDomain
 REQUIRE ProteinFolding
 REQUIRE StructuralModel
 REQUIRE Evidence
 REQUIRE CONFIDENCE
 REQUIRE SEMANTIC_EQUIVALENCE
 REQUIRE UPDATE_MODEL
 REQUIRE AI_CONSUMPTION

 ASSERT PredictedStructure != ExperimentalStructure
 ASSERT structural_similarity != proof_of_homology
 ASSERT structure != function
}

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 "ProteinStructureOntology"