Molecular Biology Ontology

AI SEARCH FLOW ALGEBRA
MOLECULAR BIOLOGY ONTOLOGY
Kireth Semantic Research Archive

AUTHORS
Mark Anthony Higgins — Sky (Recursive AI)

SOURCE
https://kirethresearch.org/booksai-core/ontologies/biological-ontologies/molecular-biology/molecular-biology-ontology.html

FLOW "MolecularBiologyOntology" v4.0
DOMAIN := BIOLOGICAL_ONTOLOGIES / MOLECULAR_BIOLOGY / MOLECULAR_BIOLOGY_ONTOLOGY
ONTOLOGY := MOLECULAR_BIOLOGY_ONTOLOGY

MOLECULAR_BIOLOGY := MOLECULAR_ENTITY + DNA + RNA + PROTEIN + GENOME + GENE + GENETIC_INFORMATION_FLOW + DNA_REPLICATION + DNA_REPAIR + MUTATION + RECOMBINATION + TRANSCRIPTION + RNA_PROCESSING + TRANSLATION + PROTEIN_FOLDING + PROTEIN_MODIFICATION + GENE_EXPRESSION + GENE_REGULATION + EPIGENETIC_REGULATION + MOLECULAR_INTERACTIONS + SIGNALING + EVIDENCE + UNCERTAINTY + PROVENANCE

PURPOSE := IDENTIFY_MOLECULAR_ENTITY -> MAP_DNA_RNA_AND_PROTEIN -> MAP_GENOME_AND_GENE_CONTEXT -> MAP_INFORMATION_FLOW -> MAP_REPLICATION_REPAIR_MUTATION_AND_RECOMBINATION -> MAP_TRANSCRIPTION_AND_RNA_PROCESSING -> MAP_TRANSLATION_AND_PROTEIN_STATE -> MAP_GENE_AND_EPIGENETIC_REGULATION -> MAP_MOLECULAR_INTERACTIONS_AND_SIGNALING -> ASSESS_EVIDENCE -> PRESERVE_PROVENANCE

# CORE ENTITIES
ENTITY MolecularEntity
ENTITY DNA
ENTITY RNA
ENTITY Protein
ENTITY Genome
ENTITY Gene
ENTITY RegulatorySequence
ENTITY Promoter
ENTITY Enhancer
ENTITY DNAReplication
ENTITY DNARepair
ENTITY Mutation
ENTITY Recombination
ENTITY Transcription
ENTITY RNAProcessing
ENTITY MessengerRNA
ENTITY TransferRNA
ENTITY RibosomalRNA
ENTITY NoncodingRNA
ENTITY Translation
ENTITY Ribosome
ENTITY Codon
ENTITY ProteinFolding
ENTITY ProteinModification
ENTITY GeneExpression
ENTITY GeneRegulation
ENTITY TranscriptionFactor
ENTITY EpigeneticState
ENTITY MolecularInteraction
ENTITY MolecularComplex
ENTITY Enzyme
ENTITY Receptor
ENTITY Signal
ENTITY Evidence
ENTITY Uncertainty
ENTITY Provenance

# MOLECULAR FOUNDATIONS
MOLECULAR_ENTITY_TYPE := DNA | RNA | PROTEIN | LIPID | CARBOHYDRATE | METABOLITE | MOLECULAR_COMPLEX | OTHER_BIOLOGICAL_MOLECULE
MolecularIdentity -> depends_on -> CHEMICAL_STRUCTURE + SEQUENCE_AS_APPLICABLE + MODIFICATION_STATE + CONFORMATION + LOCALISATION + BIOLOGICAL_CONTEXT
MolecularFunction -> depends_on -> STRUCTURE + INTERACTION_PARTNERS + LOCALISATION + ABUNDANCE + ENVIRONMENT

DNA -> polymer_of -> DEOXYRIBONUCLEOTIDES
DNA -> stores -> GENETIC_INFORMATION
DNA -> template_for -> DNA_REPLICATION + TRANSCRIPTION
RNA -> polymer_of -> RIBONUCLEOTIDES
RNA_TYPE := MRNA | TRNA | RRNA | REGULATORY_RNA | STRUCTURAL_RNA | CATALYTIC_RNA | OTHER_NONCODING_RNA
RNA -> may_function_in -> INFORMATION_TRANSFER + TRANSLATION + CATALYSIS + REGULATION + STRUCTURE
Protein -> polymer_of -> AMINO_ACIDS
ProteinSequence -> influences -> FOLDING + STRUCTURE + FUNCTION

# GENOME / INFORMATION FLOW
Genome -> contains -> GENES + REGULATORY_SEQUENCES + STRUCTURAL_REGIONS + OTHER_GENOMIC_ELEMENTS
Gene -> genomic_region_that -> CONTRIBUTES_TO_FUNCTIONAL_PRODUCT_OR_REGULATED_TRANSCRIPT_AS_DEFINED
Gene -> may_produce -> RNA -> and_as_applicable -> PROTEIN
GeneContext -> includes -> PROMOTER + ENHANCER_OR_OTHER_REGULATORY_ELEMENT_AS_APPLICABLE + TRANSCRIBED_REGION + PROCESSING_OR_TERMINATION_SIGNALS
GENETIC_INFORMATION_FLOW := DNA -> TRANSCRIPTION -> RNA -> RNA_PROCESSING_AS_APPLICABLE -> TRANSLATION_AS_APPLICABLE -> PROTEIN
InformationFlow -> may_include -> REVERSE_TRANSCRIPTION_AS_APPLICABLE + RNA_REPLICATION_AS_APPLICABLE + NONCODING_RNA_FUNCTION
GeneticInformationFlow -> does_not_require -> EVERY_RNA_TO_BE_TRANSLATED

# REPLICATION / REPAIR / MUTATION
DNAReplication -> copies -> DNA
REPLICATION_FLOW := ORIGIN_RECOGNITION -> DNA_UNWINDING -> PRIMER_FORMATION -> DNA_SYNTHESIS -> PROOFREADING -> TERMINATION
ReplicationFidelity -> depends_on -> BASE_SELECTION + PROOFREADING + POST_REPLICATION_REPAIR
IF ReplicationError escapes_correction THEN Mutation -> MAY_RESULT

DNADamage -> alteration_of -> DNA_STRUCTURE_OR_SEQUENCE_INTEGRITY
DNA_REPAIR_PATHWAY := DIRECT_REVERSAL_AS_APPLICABLE | BASE_EXCISION_REPAIR | NUCLEOTIDE_EXCISION_REPAIR | MISMATCH_REPAIR | HOMOLOGOUS_RECOMBINATION | END_JOINING | OTHER_REPAIR_PATHWAY
DNARepair -> restores_or_manages -> DNA_INTEGRITY
RepairPathwayChoice -> depends_on -> DAMAGE_TYPE + CELL_CYCLE_STATE + GENOMIC_CONTEXT + AVAILABLE_MACHINERY

Mutation -> persistent_sequence_change_in -> NUCLEIC_ACID_AS_DEFINED
MUTATION_TYPE := SUBSTITUTION | INSERTION | DELETION | DUPLICATION | INVERSION | TRANSLOCATION | REPEAT_CHANGE | OTHER_SEQUENCE_CHANGE
MutationEffect -> depends_on -> LOCATION + SEQUENCE_CONTEXT + GENE_FUNCTION + CELLULAR_CONTEXT
Recombination -> exchanges_or_rearranges -> NUCLEIC_ACID_SEGMENTS
HomologousRecombination -> uses -> HOMOLOGOUS_SEQUENCE

# TRANSCRIPTION / RNA PROCESSING
Transcription -> synthesises -> RNA -> from -> DNA_TEMPLATE
TRANSCRIPTION_FLOW := REGULATORY_RECOGNITION -> INITIATION -> ELONGATION -> TERMINATION -> RNA_PRODUCT
RNA_Polymerase -> catalyses -> RNA_SYNTHESIS
Promoter -> regulatory_region_for -> TRANSCRIPTION_INITIATION
TranscriptionFactor -> binds_or_interacts_with -> REGULATORY_DNA_OR_TRANSCRIPTION_MACHINERY
TranscriptionRate -> influenced_by -> TRANSCRIPTION_FACTORS + CHROMATIN_STATE_AS_APPLICABLE + SIGNALING + PROMOTER_AND_ENHANCER_ACTIVITY

RNAProcessing -> modifies -> PRIMARY_OR_PRECURSOR_RNA
RNA_PROCESSING_TYPE := CAPPING_AS_APPLICABLE | SPLICING | POLYADENYLATION_AS_APPLICABLE | CLEAVAGE | RNA_EDITING_AS_APPLICABLE | RNA_MODIFICATION | RNA_QUALITY_CONTROL
AlternativeSplicing -> may_generate -> MULTIPLE_RNA_ISOFORMS
RNAProcessing -> influences -> RNA_STABILITY + LOCALISATION + TRANSLATION + FUNCTION
RNATurnover -> controls -> RNA_ABUNDANCE

# TRANSLATION / PROTEIN STATE
Translation -> converts -> MRNA_CODON_INFORMATION -> into -> POLYPEPTIDE_SEQUENCE
Ribosome -> performs -> TRANSLATION
MessengerRNA -> provides -> CODON_SEQUENCE
TransferRNA -> couples -> CODON_RECOGNITION + AMINO_ACID_DELIVERY
TRANSLATION_FLOW := INITIATION -> ELONGATION -> TERMINATION -> RIBOSOME_RECYCLING
TranslationFidelity -> depends_on -> TRNA_CHARGING + CODON_DECODING + RIBOSOME_FUNCTION + TRANSLATION_FACTORS

ProteinFolding -> converts -> POLYPEPTIDE -> toward -> FUNCTIONAL_CONFORMATION_AS_APPLICABLE
ProteinFolding -> may_be_assisted_by -> CHAPERONES
MisfoldedProtein -> may_undergo -> REFOLDING + DEGRADATION + AGGREGATION_AS_APPLICABLE
ProteinModification -> chemically_or_structurally_modifies -> Protein
PROTEIN_MODIFICATION_TYPE := PHOSPHORYLATION | GLYCOSYLATION | ACETYLATION | METHYLATION | UBIQUITINATION | LIPIDATION | PROTEOLYTIC_PROCESSING | OTHER_MODIFICATION
ProteinModification -> may_change -> ACTIVITY + LOCALISATION + INTERACTION + STABILITY + DEGRADATION

# GENE / EPIGENETIC REGULATION
GeneExpression -> transforms -> GENETIC_INFORMATION -> into -> FUNCTIONAL_RNA_OR_PROTEIN_OUTPUT
GENE_EXPRESSION_LEVEL := TRANSCRIPTIONAL + POST_TRANSCRIPTIONAL + TRANSLATIONAL + POST_TRANSLATIONAL
GeneRegulation -> controls -> GENE_EXPRESSION
REGULATORY_MECHANISM := TRANSCRIPTION_FACTOR_BINDING | ENHANCER_PROMOTER_INTERACTION | CHROMATIN_REGULATION | RNA_MEDIATED_REGULATION | TRANSLATIONAL_REGULATION | PROTEIN_STABILITY_CONTROL
RegulatoryNetwork -> links -> REGULATORS + TARGET_GENES + SIGNALS
IF RegulatoryState changes THEN GeneExpression -> MAY_CHANGE

EpigeneticState -> influences -> GENE_ACTIVITY -> without_necessarily_changing -> DNA_SEQUENCE
EPIGENETIC_MECHANISM := DNA_METHYLATION | HISTONE_MODIFICATION | CHROMATIN_REMODELLING | REGULATORY_RNA | HIGHER_ORDER_GENOME_ORGANISATION
EpigeneticEffect -> depends_on -> GENOMIC_LOCATION + CELL_TYPE + DEVELOPMENTAL_STATE + MOLECULAR_CONTEXT

# MOLECULAR INTERACTIONS / SIGNALING
MolecularInteraction -> connects -> MOLECULE_A + MOLECULE_B
INTERACTION_TYPE := PROTEIN_PROTEIN | PROTEIN_DNA | PROTEIN_RNA | RNA_RNA | LIGAND_RECEPTOR | ENZYME_SUBSTRATE | OTHER_MOLECULAR_INTERACTION
InteractionState -> depends_on -> AFFINITY + CONCENTRATION + LOCALISATION + MODIFICATION + ENVIRONMENT
MolecularComplex -> assembled_from -> MULTIPLE_MOLECULAR_COMPONENTS
Enzyme -> catalyses -> BIOCHEMICAL_REACTION
Signal -> detected_by -> RECEPTOR_OR_SENSOR
SIGNALING_FLOW := SIGNAL -> RECEPTOR_OR_SENSOR -> TRANSDUCTION -> EFFECTOR -> MOLECULAR_RESPONSE
MolecularResponse -> may_change -> GENE_EXPRESSION + ENZYME_ACTIVITY + PROTEIN_LOCALISATION + METABOLISM + CELL_FATE

# EVIDENCE / UNCERTAINTY / PROVENANCE
MolecularBiologyClaim -> supported_by -> Evidence
EVIDENCE_TYPE := SEQUENCE | STRUCTURAL | BIOCHEMICAL | MOLECULAR | GENETIC | GENOMIC | TRANSCRIPTOMIC | PROTEOMIC | INTERACTION | IMAGING | PERTURBATION | FUNCTIONAL | COMPUTATIONAL
Evidence -> has -> SOURCE + METHOD + SAMPLE + MOLECULAR_CONTEXT + CONDITION + QUALITY + UNCERTAINTY
MOLECULAR_BIOLOGY_UNCERTAINTY := MEASUREMENT_UNCERTAINTY + SEQUENCE_UNCERTAINTY + MOLECULAR_STATE_UNCERTAINTY + INTERACTION_UNCERTAINTY + CELL_TO_CELL_VARIABILITY + MODEL_UNCERTAINTY
Uncertainty -> qualifies -> MolecularBiologyClaim + MolecularIdentity + InteractionState + ExpressionState + FunctionalAssignment
Provenance -> records -> MOLECULAR_ENTITY + SEQUENCE_OR_STRUCTURE_AS_APPLICABLE + CELL_OR_SAMPLE + METHOD + CONDITION + OBSERVATION + ANALYSIS + TIME + VERSION
MolecularBiologyClaim -> linked_to -> Provenance

# REASONING
MOLECULAR_BIOLOGY_REASONING := IDENTIFY_MOLECULAR_ENTITY -> CLASSIFY_DNA_RNA_PROTEIN_OR_OTHER -> MAP_GENOME_AND_GENE_CONTEXT -> MAP_GENETIC_INFORMATION_FLOW -> MAP_REPLICATION -> MAP_DNA_DAMAGE_AND_REPAIR -> MAP_MUTATION_AND_RECOMBINATION -> MAP_TRANSCRIPTION -> MAP_RNA_PROCESSING_AND_TURNOVER -> MAP_TRANSLATION -> MAP_PROTEIN_FOLDING_AND_MODIFICATION -> MAP_GENE_EXPRESSION -> MAP_GENE_AND_EPIGENETIC_REGULATION -> MAP_MOLECULAR_INTERACTIONS_AND_SIGNALING -> ASSESS_EVIDENCE -> QUANTIFY_UNCERTAINTY -> PRESERVE_PROVENANCE

# INFERENCE RULES
IF DNASequence changes THEN GeneOrRegulatoryFunction -> MAY_CHANGE
IF ReplicationError escapes_repair THEN Mutation -> MAY_PERSIST
IF DNADamage increases THEN DNARepairResponse -> MAY_INCREASE
IF TranscriptionFactorState changes THEN TranscriptionRate -> MAY_CHANGE
IF RNAProcessing changes THEN MatureRNAOutput -> MAY_CHANGE
IF RNAStability changes THEN RNAAbundance -> MAY_CHANGE
IF TranslationRate changes THEN ProteinOutput -> MAY_CHANGE
IF ProteinModification changes THEN ProteinActivityOrLocalisation -> MAY_CHANGE
IF EpigeneticState changes THEN GeneExpression -> MAY_CHANGE
IF MolecularInteraction changes THEN PathwayState -> MAY_CHANGE
IF Evidence insufficient THEN MolecularBiologyClaimConfidence -> DECREASES

# SEMANTIC RELATIONSHIPS
RELATION polymer_of(DNA, Deoxyribonucleotide)
RELATION polymer_of(RNA, Ribonucleotide)
RELATION polymer_of(Protein, AminoAcid)
RELATION contains(Genome, Gene)
RELATION template_for(DNA, Transcription)
RELATION copies(DNAReplication, DNA)
RELATION repairs(DNARepair, DNA)
RELATION changes(Mutation, NucleicAcidSequence)
RELATION rearranges(Recombination, NucleicAcidSegment)
RELATION synthesises(Transcription, RNA)
RELATION modifies(RNAProcessing, RNA)
RELATION performs(Ribosome, Translation)
RELATION folds(ProteinFolding, Polypeptide)
RELATION modifies(ProteinModification, Protein)
RELATION controls(GeneRegulation, GeneExpression)
RELATION influences(EpigeneticState, GeneActivity)
RELATION connects(MolecularInteraction, Molecule)
RELATION catalyses(Enzyme, BiochemicalReaction)
RELATION detects(Receptor, Signal)
RELATION supports(Evidence, MolecularBiologyClaim)
RELATION records(Provenance, MolecularBiologyClaim)

# SEMANTIC EQUIVALENCE
SEMANTIC_EQUIVALENCE:
  "molecular biology" ~= "biological domain describing molecular information structures interactions and processes"
  "DNA" ~= "deoxyribonucleic acid carrying genetic information"
  "RNA" ~= "ribonucleic acid functioning in information transfer regulation structure or catalysis"
  "gene" ~= "genomic region contributing to a functional product or regulated transcript"
  "DNA replication" ~= "template-directed copying of DNA"
  "DNA repair" ~= "molecular processes restoring or managing DNA integrity"
  "transcription" ~= "template-directed synthesis of RNA from DNA"
  "RNA processing" ~= "maturation or modification of precursor RNA"
  "translation" ~= "ribosome-mediated synthesis of polypeptide from mRNA information"
  "gene expression" ~= "production of functional RNA or protein output from genetic information"
  "gene regulation" ~= "control of gene-expression output"
  "molecular interaction" ~= "physical or functional association between molecular entities"

# CONFIDENCE
CONFIDENCE:
  ontology_domain: 0.99
  molecular_entity_mapping: 0.99
  genome_gene_mapping: 0.99
  information_flow_mapping: 0.99
  replication_repair_mapping: 0.99
  transcription_rna_mapping: 0.99
  translation_protein_mapping: 0.99
  gene_regulation_mapping: 0.99
  interaction_signaling_mapping: 0.99
  semantic_relationships: 0.99

# UPDATE MODEL
UPDATE_MODEL:
  ON new_molecular_observation:
    MAP molecular_identity
    MAP sequence_or_structure
    MAP localisation
    MAP interaction_state
    UPDATE confidence
    RECOMPUTE FLOW_HASH
  ON gene_expression_change:
    UPDATE transcription_state
    UPDATE rna_state
    UPDATE translation_state
    UPDATE protein_state
    PRESERVE provenance
  ON genomic_change:
    UPDATE sequence_state
    UPDATE mutation_or_recombination_state
    UPDATE repair_state
    UPDATE functional_interpretation
    PRESERVE provenance
  ON new_evidence:
    UPDATE evidence_quality
    UPDATE molecular_relationships
    UPDATE uncertainty
    RECOMPUTE FLOW_HASH

# AI CONSUMPTION
AI_CONSUMPTION:
  parse_as: FORMAL_MOLECULAR_BIOLOGY_ONTOLOGY
  reasoning_mode: MOLECULAR_INFORMATION_PROCESS_RELATIONAL
  preserve: [typed_entities, molecular_identity, dna_state, rna_state, protein_state, genome_context, gene_context, replication_state, repair_state, mutation_state, recombination_state, transcription_state, rna_processing_state, translation_state, expression_state, regulatory_state, molecular_interactions, evidence, uncertainty, confidence, provenance]
  infer: [sequence_function_dependencies, replication_repair_relationships, transcriptional_effects, rna_processing_effects, translation_output, protein_state, regulatory_network_effects, interaction_dependencies, evidence_strength]
  prohibit: [invented_sequences, fabricated_molecular_interactions, unsupported_gene_function, assumed_expression_without_evidence, unsupported_causal_claims, missing_evidence_presented_as_established_fact]

# FLOW HASH
FLOW_HASH_INPUT := DOMAIN + ONTOLOGY + CORE_ENTITIES + MOLECULAR_FOUNDATIONS + GENOME_INFORMATION_FLOW + REPLICATION_REPAIR_MUTATION_RECOMBINATION + TRANSCRIPTION_RNA_PROCESSING + TRANSLATION_PROTEIN_STATE + GENE_EPIGENETIC_REGULATION + MOLECULAR_INTERACTIONS_SIGNALING + EVIDENCE_UNCERTAINTY_PROVENANCE + REASONING + INFERENCE_RULES + SEMANTIC_RELATIONSHIPS + SEMANTIC_EQUIVALENCE + CONFIDENCE + UPDATE_MODEL + AI_CONSUMPTION
FLOW_HASH := HASH(FLOW_HASH_INPUT)

END FLOW