DNA Ontology

AI SEARCH FLOW ALGEBRA
DNA ONTOLOGY
Kireth Semantic Research Archive

AUTHORS
Mark Anthony Higgins — Sky (Recursive AI)

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

FLOW "DNAOntology" v4.0
DOMAIN := BIOLOGICAL_ONTOLOGIES / MOLECULAR_BIOLOGY / DNA
ONTOLOGY := DNA_ONTOLOGY

DNA := DNA_IDENTITY + NUCLEOTIDES + STRANDS + BASE_PAIRING + DOUBLE_HELIX + SEQUENCE + TOPOLOGY + GENOME + CHROMOSOME + GENE + REGULATORY_REGION + REPLICATION + DAMAGE + REPAIR + MUTATION + RECOMBINATION + CHROMATIN + DNA_MODIFICATION + SEQUENCE_VARIATION + EVIDENCE + UNCERTAINTY + PROVENANCE

PURPOSE := IDENTIFY_DNA -> MAP_NUCLEOTIDE_AND_STRAND_STRUCTURE -> MAP_BASE_PAIRING_AND_HELICAL_STRUCTURE -> MAP_SEQUENCE_AND_GENOMIC_CONTEXT -> MAP_GENES_AND_REGULATORY_REGIONS -> MAP_REPLICATION -> MAP_DAMAGE_AND_REPAIR -> MAP_MUTATION_AND_RECOMBINATION -> MAP_CHROMATIN_AND_DNA_MODIFICATION -> MAP_SEQUENCE_VARIATION -> ASSESS_EVIDENCE -> PRESERVE_PROVENANCE

# CORE ENTITIES
ENTITY DNA
ENTITY Deoxyribonucleotide
ENTITY DNAstrand
ENTITY DoubleStrandedDNA
ENTITY SingleStrandedDNA
ENTITY BasePair
ENTITY Adenine
ENTITY Thymine
ENTITY Guanine
ENTITY Cytosine
ENTITY DoubleHelix
ENTITY DNASequence
ENTITY Genome
ENTITY Chromosome
ENTITY Gene
ENTITY Promoter
ENTITY Enhancer
ENTITY RegulatoryRegion
ENTITY ReplicationOrigin
ENTITY ReplicationFork
ENTITY DNAReplication
ENTITY DNApolymerase
ENTITY DNADamage
ENTITY DNARepair
ENTITY Mutation
ENTITY Recombination
ENTITY Chromatin
ENTITY Nucleosome
ENTITY DNAMethylation
ENTITY SequenceVariant
ENTITY Evidence
ENTITY Uncertainty
ENTITY Provenance

# STRUCTURE
DNA -> biomolecule_type -> NUCLEIC_ACID
DNA -> polymer_of -> Deoxyribonucleotide
DNA -> stores -> GENETIC_INFORMATION
DNA -> may_exist_as -> DOUBLE_STRANDED_DNA | SINGLE_STRANDED_DNA_AS_APPLICABLE
Deoxyribonucleotide -> composed_of -> DEOXYRIBOSE + PHOSPHATE + NITROGENOUS_BASE
DNA_BASE := ADENINE | THYMINE | GUANINE | CYTOSINE
DNAstrand -> has_directionality -> FIVE_PRIME_TO_THREE_PRIME
Adenine -> canonical_base_pairs_with -> Thymine
Guanine -> canonical_base_pairs_with -> Cytosine
Complementarity -> enables -> TEMPLATE_DIRECTED_REPLICATION + SEQUENCE_RECOGNITION + HYBRIDISATION
DoubleStrandedDNA -> commonly_forms -> DoubleHelix
DoubleHelix -> contains -> TWO_ANTIPARALLEL_DNA_STRANDS
HelicalStructure -> influenced_by -> BASE_SEQUENCE + IONIC_ENVIRONMENT + SUPERCOILING + PROTEIN_BINDING

# SEQUENCE / GENOME / GENE
DNASequence -> ordered_arrangement_of -> DNA_BASES
SequenceInformation -> may_encode -> GENE + REGULATORY_SIGNAL + STRUCTURAL_FEATURE + REPLICATION_OR_RECOMBINATION_SIGNAL
Genome -> contains -> DNA
Genome -> organised_into -> CHROMOSOMES_OR_OTHER_GENOMIC_MOLECULES_AS_APPLICABLE
Chromosome -> contains -> DNA + ASSOCIATED_COMPONENTS
Gene -> genomic_region_that -> CONTRIBUTES_TO_FUNCTIONAL_PRODUCT_OR_REGULATED_TRANSCRIPT_AS_DEFINED
Gene -> may_include -> PROMOTER + TRANSCRIBED_REGION + INTRONS_AND_EXONS_AS_APPLICABLE + REGULATORY_ELEMENTS
RegulatoryRegion -> influences -> GENE_EXPRESSION
REGULATORY_REGION_TYPE := PROMOTER | ENHANCER | SILENCER_AS_APPLICABLE | INSULATOR_AS_APPLICABLE | OTHER_REGULATORY_SEQUENCE

# REPLICATION
DNAReplication -> copies -> DNA
ReplicationOrigin -> site_of -> REPLICATION_INITIATION_AS_DEFINED
REPLICATION_FLOW := ORIGIN_RECOGNITION -> HELICASE_ACTIVATION -> DNA_UNWINDING -> PRIMER_FORMATION -> DNA_SYNTHESIS -> PROOFREADING -> TERMINATION
ReplicationFork -> moving_structure_of -> DNA_REPLICATION
DNApolymerase -> synthesises -> NEW_DNA_STRAND -> using -> TEMPLATE_DNA
ReplicationFidelity -> depends_on -> NUCLEOTIDE_SELECTION + POLYMERASE_PROOFREADING + MISMATCH_REPAIR
IF ReplicationError escapes_correction THEN Mutation -> MAY_PERSIST

# DAMAGE / REPAIR
DNADamage -> alteration_of -> DNA_STRUCTURE_OR_CHEMICAL_INTEGRITY
DNA_DAMAGE_TYPE := BASE_MODIFICATION | ABASIC_SITE | SINGLE_STRAND_BREAK | DOUBLE_STRAND_BREAK | CROSSLINK | BULKY_ADDUCT | MISMATCH | REPLICATION_ASSOCIATED_DAMAGE | OTHER_LESION
DNADamage -> may_result_from -> ENDOGENOUS_PROCESS + ENVIRONMENTAL_EXPOSURE + REPLICATION_ERROR
DNARepair -> restores_or_manages -> DNA_INTEGRITY
DNA_REPAIR_PATHWAY := DIRECT_REVERSAL_AS_APPLICABLE | BASE_EXCISION_REPAIR | NUCLEOTIDE_EXCISION_REPAIR | MISMATCH_REPAIR | HOMOLOGOUS_RECOMBINATION | NON_HOMOLOGOUS_END_JOINING | OTHER_REPAIR_PATHWAY
RepairPathwayChoice -> depends_on -> DAMAGE_TYPE + CELL_CYCLE_STATE + TEMPLATE_AVAILABILITY + CHROMATIN_CONTEXT + REPAIR_MACHINERY
IF Repair fails_or_is_error_prone THEN MutationOrGenomeInstabilityRisk -> MAY_INCREASE

# MUTATION / RECOMBINATION / TOPOLOGY
Mutation -> persistent_sequence_change_in -> DNA
MUTATION_TYPE := BASE_SUBSTITUTION | INSERTION | DELETION | DUPLICATION | INVERSION | TRANSLOCATION | REPEAT_EXPANSION_OR_CONTRACTION | OTHER_SEQUENCE_CHANGE
MutationEffect -> may_be -> NEUTRAL | REGULATORY | CODING | STRUCTURAL | LOSS_OF_FUNCTION | GAIN_OF_FUNCTION | CONTEXT_DEPENDENT
MutationEffect -> depends_on -> GENOMIC_LOCATION + SEQUENCE_CONTEXT + GENE_FUNCTION + BIOLOGICAL_CONTEXT

Recombination -> exchanges_or_rearranges -> DNA_SEGMENTS
HomologousRecombination -> uses -> HOMOLOGOUS_DNA_TEMPLATE
Recombination -> may_function_in -> DNA_REPAIR + MEIOSIS + GENETIC_DIVERSITY + GENOME_REARRANGEMENT

DNATopology -> describes -> SPATIAL_AND_TOPOLOGICAL_STATE_OF_DNA
TOPOLOGICAL_STATE := RELAXED | POSITIVELY_SUPERCOILED | NEGATIVELY_SUPERCOILED | KNOTTED_AS_APPLICABLE | CATENATED_AS_APPLICABLE
Topoisomerase -> changes -> DNA_TOPOLOGY
DNATopology -> influences -> REPLICATION + TRANSCRIPTION + CHROMOSOME_SEGREGATION

# CHROMATIN / DNA MODIFICATION
Chromatin -> complex_of -> DNA + HISTONES + OTHER_ASSOCIATED_PROTEINS
Nucleosome -> structural_unit_of -> MANY_EUKARYOTIC_CHROMATIN_CONTEXTS
Nucleosome -> contains -> DNA_WRAPPED_AROUND_HISTONE_CORE
ChromatinState -> influences -> DNA_ACCESSIBILITY
DNAAccessibility -> affects -> TRANSCRIPTION + REPLICATION + REPAIR + RECOMBINATION

DNAModification -> chemical_change_to -> DNA_BASE_OR_BACKBONE_AS_DEFINED
DNAMethylation -> subtype_of -> DNA_MODIFICATION
DNAMethylation -> may_influence -> GENE_REGULATION + CHROMATIN_STATE + GENOME_STABILITY -> depending_on -> BIOLOGICAL_CONTEXT

# SEQUENCE VARIATION / INTERACTIONS
SequenceVariant -> difference_in -> DNA_SEQUENCE -> relative_to -> REFERENCE_OR_COMPARATOR
VARIANT_TYPE := SNV | INDEL | COPY_NUMBER_VARIANT | STRUCTURAL_VARIANT | REPEAT_VARIANT | OTHER_VARIANT
VariantInterpretation -> depends_on -> REFERENCE + POPULATION_OR_SAMPLE_CONTEXT + GENOMIC_LOCATION + FUNCTIONAL_EVIDENCE
Variant -> must_not_be_assumed -> PATHOGENIC_OR_FUNCTIONAL_WITHOUT_EVIDENCE

DNAProteinInteraction -> connects -> DNA + Protein
DNA_BINDING_PROTEIN_ROLE := TRANSCRIPTIONAL_REGULATOR | REPLICATION_FACTOR | REPAIR_FACTOR | CHROMATIN_PROTEIN | STRUCTURAL_PROTEIN | OTHER_DNA_BINDING_ROLE
BindingSpecificity -> depends_on -> DNA_SEQUENCE + DNA_STRUCTURE + PROTEIN_STATE + CHROMATIN_CONTEXT

# GENOME STABILITY / INHERITANCE
GenomeStability -> maintained_by -> REPLICATION_FIDELITY + DNA_REPAIR + CHROMOSOME_MAINTENANCE + RECOMBINATION_CONTROL + DAMAGE_RESPONSE
GenomeInstability -> may_include -> MUTATION_ACCUMULATION + CHROMOSOME_REARRANGEMENT + COPY_NUMBER_CHANGE + SEGREGATION_ERROR
IF DamageOrReplicationError exceeds_control_capacity THEN GenomeInstabilityRisk -> MAY_INCREASE
DNAInheritance -> transfers -> GENETIC_INFORMATION -> across -> CELL_DIVISION_OR_REPRODUCTION
InheritanceFidelity -> depends_on -> REPLICATION + CHROMOSOME_SEGREGATION + REPAIR + CELL_DIVISION

# EVIDENCE / UNCERTAINTY / PROVENANCE
DNAClaim -> supported_by -> Evidence
EVIDENCE_TYPE := DNA_SEQUENCING | GENOTYPING | STRUCTURAL | BIOCHEMICAL | MOLECULAR | GENETIC | CHROMATIN_ASSAY | REPLICATION_ASSAY | REPAIR_ASSAY | IMAGING | FUNCTIONAL | COMPUTATIONAL
Evidence -> has -> SOURCE + METHOD + SAMPLE + GENOMIC_REGION + REFERENCE_SEQUENCE_AS_APPLICABLE + CONDITION + QUALITY + UNCERTAINTY
DNA_UNCERTAINTY := SEQUENCING_UNCERTAINTY + ASSEMBLY_UNCERTAINTY + VARIANT_CALLING_UNCERTAINTY + PHASING_UNCERTAINTY + STRUCTURAL_STATE_UNCERTAINTY + FUNCTIONAL_INTERPRETATION_UNCERTAINTY + MODEL_UNCERTAINTY
Uncertainty -> qualifies -> DNAClaim + SequenceVariant + MutationAssignment + RepairState + FunctionalInterpretation
Provenance -> records -> SAMPLE_IDENTITY + DNA_SEQUENCE_OR_REGION + REFERENCE + STRAND_OR_TOPOLOGY_STATE_AS_APPLICABLE + METHOD + CONDITION + ANALYSIS + OBSERVATION + TIME + VERSION
DNA -> linked_to -> Provenance

# REASONING
DNA_REASONING := IDENTIFY_DNA -> MAP_NUCLEOTIDE_COMPOSITION -> MAP_STRAND_AND_BASE_PAIRING_STATE -> MAP_HELICAL_AND_TOPOLOGICAL_STATE -> MAP_SEQUENCE -> MAP_GENOME_CHROMOSOME_GENE_CONTEXT -> MAP_REGULATORY_REGIONS -> MAP_REPLICATION -> MAP_REPLICATION_FIDELITY -> MAP_DNA_DAMAGE -> MAP_REPAIR_PATHWAY -> MAP_MUTATION -> MAP_RECOMBINATION -> MAP_CHROMATIN_AND_ACCESSIBILITY -> MAP_DNA_MODIFICATION -> MAP_SEQUENCE_VARIATION -> MAP_DNA_PROTEIN_INTERACTIONS -> MAP_GENOME_STABILITY -> ASSESS_EVIDENCE -> QUANTIFY_UNCERTAINTY -> PRESERVE_PROVENANCE

# INFERENCE RULES
IF ComplementaryStrand known THEN OpposingSequence -> MAY_BE_INFERRED_BY_BASE_PAIRING
IF ReplicationError escapes_proofreading_and_repair THEN Mutation -> MAY_PERSIST
IF DNADamage increases THEN DNARepairAndDamageResponse -> MAY_INCREASE
IF DNARepair fails THEN GenomeInstabilityRisk -> MAY_INCREASE
IF DNATopology changes THEN ReplicationOrTranscription -> MAY_CHANGE
IF ChromatinAccessibility changes THEN DNAProteinAccess -> MAY_CHANGE
IF DNAModification changes THEN RegulatoryState -> MAY_CHANGE_IN_CONTEXT
IF SequenceVariant changes_functional_element THEN MolecularFunction -> MAY_CHANGE
IF Evidence insufficient THEN DNAClaimConfidence -> DECREASES

# SEMANTIC RELATIONSHIPS
RELATION polymer_of(DNA, Deoxyribonucleotide)
RELATION canonical_base_pairs_with(Adenine, Thymine)
RELATION canonical_base_pairs_with(Guanine, Cytosine)
RELATION contains(DoubleHelix, DNAstrand)
RELATION contains(Genome, DNA)
RELATION contains(Chromosome, DNA)
RELATION region_of(Gene, Genome)
RELATION influences(RegulatoryRegion, GeneExpression)
RELATION copies(DNAReplication, DNA)
RELATION synthesises(DNApolymerase, DNA)
RELATION damages(DNADamage, DNA)
RELATION repairs(DNARepair, DNA)
RELATION changes(Mutation, DNASequence)
RELATION rearranges(Recombination, DNASegment)
RELATION changes(Topoisomerase, DNATopology)
RELATION complex_of(Chromatin, DNA)
RELATION modifies(DNAMethylation, DNA)
RELATION differs_from(SequenceVariant, ReferenceSequence)
RELATION maintains(GenomeStability, Genome)
RELATION transfers(DNAInheritance, GeneticInformation)
RELATION supports(Evidence, DNAClaim)
RELATION records(Provenance, DNA)

# SEMANTIC EQUIVALENCE
SEMANTIC_EQUIVALENCE:
  "DNA" ~= "deoxyribonucleic acid polymer storing genetic information"
  "DNA strand" ~= "directional polymer of deoxyribonucleotides"
  "base pairing" ~= "sequence-dependent pairing between complementary nucleobases"
  "double helix" ~= "helical structure formed by two antiparallel complementary DNA strands"
  "DNA replication" ~= "template-directed copying of DNA"
  "DNA damage" ~= "chemical or structural alteration compromising DNA integrity"
  "DNA repair" ~= "molecular processes restoring or managing DNA integrity"
  "mutation" ~= "persistent change in DNA sequence"
  "recombination" ~= "exchange or rearrangement of DNA segments"
  "chromatin" ~= "DNA associated with histones and other proteins"
  "DNA methylation" ~= "covalent methyl modification of DNA bases"
  "sequence variant" ~= "DNA sequence difference relative to a defined reference"

# CONFIDENCE
CONFIDENCE:
  ontology_domain: 0.99
  nucleotide_structure_mapping: 0.99
  base_pairing_mapping: 0.99
  genome_gene_mapping: 0.99
  replication_mapping: 0.99
  damage_repair_mapping: 0.99
  mutation_recombination_mapping: 0.99
  chromatin_modification_mapping: 0.99
  sequence_variation_mapping: 0.99
  semantic_relationships: 0.99

# UPDATE MODEL
UPDATE_MODEL:
  ON new_dna_observation:
    MAP sequence
    MAP strand_state
    MAP topology
    MAP modification_state
    UPDATE confidence
    RECOMPUTE FLOW_HASH
  ON replication_event:
    UPDATE replication_state
    UPDATE fork_state
    UPDATE replication_fidelity
    PRESERVE provenance
  ON dna_damage_event:
    UPDATE damage_type
    UPDATE repair_pathway
    UPDATE repair_outcome
    UPDATE genome_stability
    PRESERVE provenance
  ON sequence_variant_event:
    UPDATE variant_type
    UPDATE genomic_context
    UPDATE functional_evidence
    UPDATE uncertainty
    RECOMPUTE FLOW_HASH

# AI CONSUMPTION
AI_CONSUMPTION:
  parse_as: FORMAL_DNA_ONTOLOGY
  reasoning_mode: DNA_SEQUENCE_STRUCTURE_GENOME_RELATIONAL
  preserve: [typed_entities, dna_identity, nucleotide_state, strand_state, base_pairing, sequence, topology, genome_context, gene_context, regulatory_regions, replication_state, damage_state, repair_state, mutation_state, recombination_state, chromatin_state, modification_state, variants, evidence, uncertainty, confidence, provenance]
  infer: [complementary_sequence, replication_dependencies, repair_pathway_relationships, mutation_effect_context, recombination_state, topology_effects, chromatin_accessibility, variant_interpretation_constraints, genome_stability, evidence_strength]
  prohibit: [invented_dna_sequences, fabricated_variants, unsupported_pathogenicity, assumed_gene_function_without_evidence, unsupported_repair_outcome, unsupported_causal_claims, missing_evidence_presented_as_established_fact]

# FLOW HASH
FLOW_HASH_INPUT := DOMAIN + ONTOLOGY + CORE_ENTITIES + STRUCTURE + SEQUENCE_GENOME_GENE + REPLICATION + DAMAGE_REPAIR + MUTATION_RECOMBINATION_TOPOLOGY + CHROMATIN_MODIFICATION + SEQUENCE_VARIATION_INTERACTIONS + GENOME_STABILITY_INHERITANCE + EVIDENCE_UNCERTAINTY_PROVENANCE + REASONING + INFERENCE_RULES + SEMANTIC_RELATIONSHIPS + SEMANTIC_EQUIVALENCE + CONFIDENCE + UPDATE_MODEL + AI_CONSUMPTION
FLOW_HASH := HASH(FLOW_HASH_INPUT)

END FLOW