mp_plus_schema.yaml

id: https://w3id.org/microgrow/mp-plus-recommendations
name: mp-plus-schema
title: MP_plus Recommendation Schema
description: >-
  LinkML schema for MP_plus ingredient recommendation outputs.
  Defines structure for additional ingredients, alternate forms,
  computational analyses (gap-filling, FBA, transporter, synergy),
  and evidence integration.

  Version 1.0 (2026-02-02): Initial schema for v6 recommendations.
  Version 1.1 (2026-02-02): v7 enhancements - mandatory similarity integration
    - Added cosine_similarity, reference_similarities, novelty_assessment to AdditionalIngredient
    - Added cosine_similarity_to_original, similarity_interpretation to AlternateForm
    - Added ReferenceSimilarity class
    - Added NoveltyEnum and SimilarityInterpretationEnum
  Version 1.2 (2026-02-03): v9 enhancements - toxicity flagging (not rejection)
    - Added toxicity_warning, toxicity_classification, safety_notes to AdditionalIngredient
    - Added ToxicityWarningEnum (SAFE, CAUTION, WARNING)
    - Added Category 11 (Literature-Based Discovery) to CategoryEnum
    - All compounds included with warning flags (no rejections)
  Version 1.2.1 (2026-02-03): v9 complete output specification
    - Documented required output files (TSV/CSV formats)
    - Added output file validation requirements
    - recommendations_additional.tsv: All ingredients in tabular format
    - recommendations_alternates.tsv: Alternate chemical forms (Category 6)
    - recommendations_summary_table.csv: Spreadsheet-friendly summary
    - analogy_discovery_details.tsv: Category 7 analogy-based discoveries
    - prioritization_ranking.tsv: Ranked by priority score
  Version 1.3 (2026-02-14): Provenance tracking (v11+, v13+)
    - Added ProvenanceMetadata, Decision, SkillUsage, DataSource classes
    - Added DataSourceTypeEnum for data source classification
    - Decision logging: timestamp, phase, decision_type, rationale, alternatives
    - Skills tracking: invocation count, parameters, success status, execution time
    - Compatible with v11/v12 agentic and v13 experimental workflows
    - Integrated into RecommendationMetadata.provenance field
    - Enables linkml-validate on decision logs and skills usage files
  Version 1.4 (2026-02-14): Optimization-driven recommendations (v14+)
    - Added OptimizationRecommendation class for factor range recommendations
    - Added AdjustmentTypeEnum (EXPAND_UPPER, EXPAND_LOWER, CONTRACT, SHIFT, MAINTAIN)
    - Added BoundaryEffectEnum (UPPER, LOWER, NONE, BOTH)
    - Integrated Pareto frontier, Sobol sensitivity, Bayesian optimization analyses
    - Added optimization_recommendations field to MPPlusRecommendationSet
    - Supports data-driven v14 design with automated range adjustments

  Output Files (Required for v9):
    Core Files:
      - recommendations_v9.yaml: Main structured data (YAML format)
      - recommendations_additional.tsv: All recommendations in tabular format
      - recommendations_summary_table.csv: Spreadsheet-friendly summary
    Category-Specific:
      - recommendations_alternates.tsv: Category 6 (Alternate Forms) if present
      - analogy_discovery_details.tsv: Category 7 (Analogy-Based) discoveries
    Toxicity & Safety:
      - tier_2d_toxicity_flagging_report.tsv: Complete toxicity assessment
      - recommendations_rejected_safety.tsv: REMOVED in v9 (all in main file)
    Analysis:
      - prioritization_ranking.tsv: Ranked by computed priority score
      - discovery_method_summary.tsv: Statistics by discovery method
    Literature:
      - recommendations_literature_discovered.tsv: Category 11 discoveries
      - literature_search_log.json: Literature query provenance
    Documentation:
      - README.md, GENERATION_SUMMARY.md, FILE_MANIFEST.md: Required docs

license: MIT

prefixes:
  linkml: https://w3id.org/linkml/
  microgrow: https://w3id.org/microgrow/
  schema: http://schema.org/
  CHEBI: http://purl.obolibrary.org/obo/CHEBI_

default_prefix: microgrow
default_range: string

imports:
  - linkml:types

classes:

  MPPlusRecommendationSet:
    tree_root: true
    description: >-
      Complete set of MP_plus recommendations including metadata,
      additional ingredients, alternate forms, and computational analyses.
    attributes:
      metadata:
        description: Generation metadata (version, prompt, organism, date)
        range: RecommendationMetadata
        required: true
      additional_ingredients:
        description: Additional ingredients to add to baseline medium
        range: AdditionalIngredient
        multivalued: true
        inlined_as_list: true
      alternate_forms:
        description: Alternate chemical forms of baseline ingredients
        range: AlternateForm
        multivalued: true
        inlined_as_list: true
      gap_analysis:
        description: GapMind pathway completeness analysis results
        range: GapAnalysisResult
        multivalued: true
        inlined_as_list: true
      fba_predictions:
        description: FBA-based growth predictions and flux analysis
        range: FBAPrediction
        multivalued: true
        inlined_as_list: true
      transporter_analysis:
        description: Transporter-based bioavailability validation
        range: TransporterAnalysis
        multivalued: true
        inlined_as_list: true
      synergy_analysis:
        description: Statistical synergy validation (TF-IDF co-occurrence)
        range: SynergyAnalysis
        multivalued: true
        inlined_as_list: true
      optimization_recommendations:
        description: v14+ optimization-driven factor range recommendations
        range: OptimizationRecommendation
        multivalued: true
        inlined_as_list: true
        required: false

  RecommendationMetadata:
    description: Metadata about recommendation generation
    attributes:
      version:
        description: MP_plus version (e.g., v6, v11_agentic, v13_experimental)
        range: string
        required: true
        pattern: "^v[0-9]+(_agentic|_experimental)?$"
      prompt_file:
        description: Prompt file used for generation
        range: string
        required: true
      organism:
        description: Target organism name
        range: string
        required: true
      genome_id:
        description: Genome assembly accession (e.g., GCA_000022685.1)
        range: string
        pattern: "^GCA_[0-9]{9}\\.[0-9]+$"
      base_medium:
        description: Base medium being enhanced (e.g., MP v2/v8)
        range: string
        required: true
      generation_date:
        description: Date recommendations generated (YYYY-MM-DD)
        range: date
        required: true
      agents_used:
        description: List of agents used in generation
        range: string
        multivalued: true
      evidence_tiers:
        description: Evidence framework tiers used (1, 2A, 2B, 3, 4)
        range: string
        multivalued: true
      total_additional:
        description: Number of additional ingredients recommended
        range: integer
        minimum_value: 0
      total_alternates:
        description: Number of alternate forms recommended
        range: integer
        minimum_value: 0
      provenance:
        description: Provenance tracking information (v11+)
        range: ProvenanceMetadata
        required: false

  AdditionalIngredient:
    description: Additional ingredient recommendation
    attributes:
      id:
        description: Unique identifier (e.g., ADD_001)
        range: string
        required: true
        identifier: true
        pattern: "^ADD_[0-9]{3}$"
      category:
        description: Recommendation category (1-10)
        range: CategoryEnum
        required: true
      ingredient:
        description: Ingredient name
        range: string
        required: true
      chebi_id:
        description: CHEBI identifier
        range: string
        pattern: "^CHEBI:[0-9]+$"
      chemical_formula:
        description: Chemical formula
        range: string
      molecular_weight:
        description: Molecular weight (g/mol)
        range: float
        minimum_value: 0.0
      concentration_min:
        description: Minimum recommended concentration
        range: float
        required: true
        minimum_value: 0.0
      concentration_max:
        description: Maximum recommended concentration
        range: float
        required: true
        minimum_value: 0.0
      concentration_unit:
        description: Concentration unit (µM, mM, nM, etc.)
        range: ConcentrationUnitEnum
        required: true
      priority:
        description: Experimental priority
        range: PriorityEnum
        required: true
      gap_type:
        description: Type of metabolic gap (if Category 9)
        range: GapTypeEnum
      gap_confidence:
        description: GapMind confidence (if Category 9)
        range: ConfidenceEnum
      fba_growth_improvement_pct:
        description: FBA-predicted growth improvement (%)
        range: float
        minimum_value: 0.0
        maximum_value: 1000.0
      fba_baseline_growth:
        description: FBA baseline growth rate (h⁻¹)
        range: float
        minimum_value: 0.0
      fba_predicted_growth:
        description: FBA predicted growth rate with ingredient (h⁻¹)
        range: float
        minimum_value: 0.0
      fba_shadow_price:
        description: FBA shadow price (h⁻¹/unit)
        range: float
      transporter_count:
        description: Number of transporters identified
        range: integer
        minimum_value: 0
      transporter_types:
        description: Transporter types (ABC, MFS, TonB, etc.)
        range: string
        multivalued: true
      bioavailability:
        description: Bioavailability assessment
        range: BioavailabilityEnum
      tfidf_top_synergy:
        description: Top synergy partner (ingredient name)
        range: string
      tfidf_score:
        description: TF-IDF score with top synergy partner
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      cosine_similarity:
        description: Maximum cosine similarity to reference compounds (0-1) (v7+)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      reference_similarities:
        description: List of reference compounds with similarity scores (v7+)
        range: ReferenceSimilarity
        multivalued: true
        inlined_as_list: true
      novelty_assessment:
        description: Novelty level based on similarity (v7+)
        range: NoveltyEnum
      analogy_score:
        description: Analogy-specific score for Category 7 (v7+)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      rationale:
        description: Rationale for recommendation
        range: string
        required: true
      toxicity_warning:
        description: Toxicity warning level from Tier 2D analysis (v9+)
        range: ToxicityWarningEnum
        required: false
      toxicity_classification:
        description: List of toxic ChEBI roles found (e.g., pesticide, herbicide) (v9+)
        range: string
        multivalued: true
        required: false
      safety_notes:
        description: Human-readable safety notes and recommendations (v9+)
        range: string
        required: false

  AlternateForm:
    description: Alternate chemical form recommendation
    attributes:
      id:
        description: Unique identifier (e.g., ALT_001)
        range: string
        required: true
        identifier: true
        pattern: "^ALT_[0-9]{3}$"
      category:
        description: Always 6 (Alternate Forms)
        range: integer
        required: true
        equals_number: 6
      current_form:
        description: Current form in baseline
        range: string
        required: true
      current_formula:
        description: Current chemical formula
        range: string
      current_concentration_min:
        description: Current concentration minimum
        range: float
      current_concentration_max:
        description: Current concentration maximum
        range: float
      current_unit:
        description: Current concentration unit
        range: ConcentrationUnitEnum
      alternate_form:
        description: Recommended alternate form
        range: string
        required: true
      alternate_formula:
        description: Alternate chemical formula
        range: string
      alternate_concentration_min:
        description: Alternate concentration minimum
        range: float
      alternate_concentration_max:
        description: Alternate concentration maximum
        range: float
      alternate_unit:
        description: Alternate concentration unit
        range: ConcentrationUnitEnum
      priority:
        description: Experimental priority
        range: PriorityEnum
        required: true
      advantages:
        description: Advantages of alternate form
        range: string
        multivalued: true
      disadvantages:
        description: Disadvantages of alternate form
        range: string
        multivalued: true
      transporter_compatibility:
        description: Transporter compatibility notes
        range: string
      cosine_similarity_to_original:
        description: Cosine similarity between alternate and original form (v7+)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      similarity_interpretation:
        description: Textual interpretation of similarity score (v7+)
        range: SimilarityInterpretationEnum
      reference_compounds:
        description: Reference compounds for context (v7+)
        range: ReferenceSimilarity
        multivalued: true
        inlined_as_list: true

  GapAnalysisResult:
    description: GapMind pathway completeness analysis result
    attributes:
      pathway_type:
        description: Type of pathway (amino_acid, vitamin, carbon_source)
        range: PathwayTypeEnum
        required: true
      compound:
        description: Compound name (e.g., L-alanine, thiamin)
        range: string
        required: true
      confidence:
        description: Pathway confidence (high, medium, low, gap)
        range: ConfidenceEnum
        required: true
      enzymes_present:
        description: Number of enzymes present
        range: integer
        minimum_value: 0
      enzymes_total:
        description: Total enzymes in pathway
        range: integer
        minimum_value: 0
      pathway_id:
        description: Pathway identifier (KEGG, MetaCyc)
        range: string
      missing_enzymes:
        description: EC numbers of missing enzymes
        range: string
        multivalued: true
      status:
        description: Status (prototroph, auxotroph, partial, in_baseline)
        range: string
      recommendation:
        description: Recommendation text
        range: string
        required: true
      concentration_range:
        description: Recommended concentration range if supplementation needed
        range: string

  FBAPrediction:
    description: FBA-based growth prediction
    attributes:
      rank:
        description: Rank by growth improvement (1 = highest)
        range: integer
        required: true
        minimum_value: 1
      ingredient:
        description: Ingredient name
        range: string
        required: true
      chebi_id:
        description: CHEBI identifier
        range: string
        pattern: "^CHEBI:[0-9]+$"
      test_concentration:
        description: Test concentration value
        range: float
        required: true
      test_unit:
        description: Test concentration unit
        range: ConcentrationUnitEnum
        required: true
      baseline_growth_rate:
        description: Baseline growth rate (h⁻¹)
        range: float
        required: true
        minimum_value: 0.0
      predicted_growth_rate:
        description: Predicted growth rate with ingredient (h⁻¹)
        range: float
        required: true
        minimum_value: 0.0
      growth_improvement_abs:
        description: Absolute growth improvement (h⁻¹)
        range: float
        minimum_value: 0.0
      growth_improvement_pct:
        description: Percent growth improvement
        range: float
        required: true
        minimum_value: 0.0
      shadow_price:
        description: Shadow price (h⁻¹/unit)
        range: float
      shadow_price_unit:
        description: Shadow price unit
        range: string
      essential:
        description: Essential for growth (true/false)
        range: boolean
      limiting_reactions_resolved:
        description: Limiting reactions resolved (reaction IDs and flux changes)
        range: string
        multivalued: true
      flux_distribution_changes:
        description: Flux distribution changes (pathways affected)
        range: string
        multivalued: true
      optimal_concentration_min:
        description: Optimal concentration minimum (from sweep)
        range: float
      optimal_concentration_max:
        description: Optimal concentration maximum (from sweep)
        range: float
      optimal_unit:
        description: Optimal concentration unit
        range: ConcentrationUnitEnum
      priority:
        description: Experimental priority
        range: PriorityEnum
        required: true

  TransporterAnalysis:
    description: Transporter-based bioavailability analysis
    attributes:
      ingredient:
        description: Ingredient name
        range: string
        required: true
      substrate:
        description: Substrate name (may differ from ingredient)
        range: string
        required: true
      transporter_count:
        description: Number of transporters identified
        range: integer
        required: true
        minimum_value: 0
      gene_ids:
        description: Transporter gene IDs
        range: string
        multivalued: true
      annotations:
        description: Transporter annotations
        range: string
        multivalued: true
      transporter_types:
        description: Transporter types (ABC, MFS, TonB, ECF, etc.)
        range: TransporterTypeEnum
        multivalued: true
      km_values_um:
        description: Km values in µM
        range: float
        multivalued: true
        minimum_value: 0.0
      affinity:
        description: Affinity classification
        range: AffinityEnum
        required: true
      bioavailability:
        description: Bioavailability assessment
        range: BioavailabilityEnum
        required: true
      recommended_concentration_min:
        description: Recommended concentration minimum
        range: float
      recommended_concentration_max:
        description: Recommended concentration maximum
        range: float
      recommended_unit:
        description: Recommended concentration unit
        range: ConcentrationUnitEnum
      uptake_expected:
        description: Uptake expected (true/false)
        range: boolean
        required: true
      notes:
        description: Additional notes
        range: string

  SynergyAnalysis:
    description: Statistical synergy analysis (TF-IDF co-occurrence)
    attributes:
      ingredient_a:
        description: First ingredient name
        range: string
        required: true
      ingredient_b:
        description: Second ingredient name
        range: string
        required: true
      chebi_a:
        description: CHEBI ID for ingredient A
        range: string
        pattern: "^CHEBI:[0-9]+$"
      chebi_b:
        description: CHEBI ID for ingredient B
        range: string
        pattern: "^CHEBI:[0-9]+$"
      media_with_a:
        description: Number of media containing ingredient A
        range: integer
        minimum_value: 0
      media_with_b:
        description: Number of media containing ingredient B
        range: integer
        minimum_value: 0
      media_with_both:
        description: Number of media containing both ingredients
        range: integer
        minimum_value: 0
      media_with_neither:
        description: Number of media containing neither ingredient
        range: integer
        minimum_value: 0
      tfidf_score:
        description: TF-IDF co-occurrence score
        range: float
        required: true
        minimum_value: 0.0
        maximum_value: 1.0
      fisher_p_value:
        description: Fisher's exact test p-value
        range: float
        required: true
        minimum_value: 0.0
        maximum_value: 1.0
      fisher_odds_ratio:
        description: Fisher's exact test odds ratio
        range: float
        minimum_value: 0.0
      statistical_significance:
        description: Statistical significance classification
        range: SignificanceEnum
        required: true
      embedding_similarity:
        description: Embedding similarity score (0-1)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      pathway_proximity:
        description: Pathway proximity score (0-1)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
      combined_score:
        description: Combined synergy score (weighted)
        range: float
        required: true
        minimum_value: 0.0
        maximum_value: 1.0
      synergy_type:
        description: Type of synergy
        range: SynergyTypeEnum
        required: true
      mechanism:
        description: Synergy mechanism description
        range: string
        required: true
      interpretation:
        description: Interpretation of synergy strength
        range: string
        required: true

  ReferenceSimilarity:
    description: Reference compound with similarity score (v7+)
    attributes:
      compound_name:
        description: Reference compound name
        range: string
        required: true
      chebi_id:
        description: CHEBI identifier for reference compound
        range: string
        pattern: "^CHEBI:[0-9]+$"
      cosine_similarity:
        description: Cosine similarity to this reference (0-1)
        range: float
        required: true
        minimum_value: 0.0
        maximum_value: 1.0
      context:
        description: Why this reference is relevant
        range: string
        required: true

  ProvenanceMetadata:
    description: Provenance tracking for agentic/experimental workflows (v11+)
    attributes:
      session_id:
        description: Claude Code session ID
        range: string
        required: false
      command:
        description: Command used to generate (e.g., /prompt path/to/prompt.md)
        range: string
        required: false
      user:
        description: User who ran the generation
        range: string
        required: false
      total_decisions:
        description: Total number of decisions logged
        range: integer
        minimum_value: 0
        required: false
      decisions:
        description: All decisions made during generation
        range: Decision
        multivalued: true
        inlined_as_list: true
        required: false
      skills_used:
        description: Skills/agents invoked during generation
        range: SkillUsage
        multivalued: true
        inlined_as_list: true
        required: false
      data_sources:
        description: Data sources used (experimental data, databases, etc.)
        range: DataSource
        multivalued: true
        inlined_as_list: true
        required: false
      runtime_seconds:
        description: Total runtime in seconds
        range: integer
        minimum_value: 0
        required: false

  Decision:
    description: Single decision made during agentic/experimental workflow
    attributes:
      timestamp:
        description: ISO 8601 timestamp of decision
        range: string
        required: true
        pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}"
      phase:
        description: Analysis phase (e.g., pareto_optimization, synergy_discovery)
        range: string
        required: true
      decision_type:
        description: Type of decision (e.g., weight_selection, threshold_selection)
        range: string
        required: true
      decision:
        description: The decision made (can be number, string, list, or object)
        range: string
        required: true
      rationale:
        description: Why this decision was made
        range: string
        required: true
      alternatives_considered:
        description: Alternative options that were evaluated
        range: string
        multivalued: true
        required: false
      data_driven:
        description: Whether decision was data-driven (vs. heuristic)
        range: boolean
        required: false
      evidence:
        description: Evidence supporting the decision
        range: string
        required: false
      experimental_context:
        description: Experimental context relevant to decision
        range: string
        required: false

  SkillUsage:
    description: Record of MicroGrowAgents skill/agent invocation
    attributes:
      skill_name:
        description: Name of skill/agent used
        range: string
        required: true
      invocation_count:
        description: Number of times invoked
        range: integer
        minimum_value: 1
        required: true
      parameters:
        description: Parameters passed to skill
        range: string
        required: false
      purpose:
        description: Purpose of invoking this skill
        range: string
        required: true
      output_used:
        description: Which output files used this skill's results
        range: string
        multivalued: true
        required: false
      success:
        description: Whether skill execution succeeded
        range: boolean
        required: true
      execution_time_seconds:
        description: Execution time in seconds
        range: float
        minimum_value: 0.0
        required: false
      error_message:
        description: Error message if failed
        range: string
        required: false

  DataSource:
    description: Data source used in generation
    attributes:
      source_type:
        description: Type of source (experimental, database, literature, etc.)
        range: DataSourceTypeEnum
        required: true
      path:
        description: File path or URL
        range: string
        required: true
      description:
        description: Description of data source
        range: string
        required: true
      loaded_timestamp:
        description: When data was loaded (ISO 8601)
        range: string
        pattern: "^[0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}"
        required: false
      record_count:
        description: Number of records loaded
        range: integer
        minimum_value: 0
        required: false
      data_quality:
        description: Data quality assessment
        range: string
        required: false

  OptimizationRecommendation:
    description: >-
      v14+ optimization-driven ingredient range recommendation.
      Based on Pareto frontier analysis, Sobol sensitivity, Bayesian optimization,
      and boundary effect detection from experimental data.
    attributes:
      ingredient:
        description: Ingredient name
        range: string
        required: true
      current_range_min:
        description: Current design space minimum
        range: float
        required: true
      current_range_max:
        description: Current design space maximum
        range: float
        required: true
      recommended_range_min:
        description: Recommended minimum for v14
        range: float
        required: true
      recommended_range_max:
        description: Recommended maximum for v14
        range: float
        required: true
      adjustment_type:
        description: Type of range adjustment recommended
        range: AdjustmentTypeEnum
        required: true
      sobol_index:
        description: Total-order Sobol sensitivity index (0-1)
        range: float
        minimum_value: 0.0
        maximum_value: 1.0
        required: false
      boundary_effect:
        description: Whether optima are at current boundaries
        range: BoundaryEffectEnum
        required: false
      pareto_optimal_value:
        description: Median value from Pareto frontier
        range: float
        required: false
      expected_improvement_rank:
        description: Rank in Bayesian optimization suggestions (1-20)
        range: integer
        minimum_value: 1
        maximum_value: 20
        required: false
      priority:
        description: Overall priority for v14 exploration
        range: PriorityEnum
        required: true
      rationale:
        description: Human-readable explanation of recommendation
        range: string
        required: true

enums:

  CategoryEnum:
    description: MP_plus recommendation categories
    permissible_values:
      1:
        description: XoxF-MDH Activity Enhancers
      2:
        description: Formaldehyde Assimilation Boosters
      3:
        description: Nd Solubility Maintainers
      4:
        description: Growth & Metabolic Enhancers
      5:
        description: Methylolanthanin Production Stimulators
      6:
        description: Alternate Chemical Forms
      7:
        description: Analogy-Based Discovery (v5+)
      8:
        description: Organism Transfer Reasoning (v5+)
      9:
        description: Gap-Filling Discovery (v6+)
      10:
        description: FBA-Based Optimization (v6+)
      11:
        description: Literature-Based Discovery (v8+)

  ConcentrationUnitEnum:
    description: Concentration units
    permissible_values:
      nM:
        description: Nanomolar
      µM:
        description: Micromolar
      mM:
        description: Millimolar
      M:
        description: Molar
      g/L:
        description: Grams per liter
      mg/L:
        description: Milligrams per liter

  PriorityEnum:
    description: Experimental testing priority
    permissible_values:
      VERY HIGH:
        description: Top priority for testing
      HIGH:
        description: High priority
      MEDIUM-HIGH:
        description: Medium-high priority
      MEDIUM:
        description: Medium priority
      MEDIUM-LOW:
        description: Medium-low priority
      LOW:
        description: Low priority

  ConfidenceEnum:
    description: Pathway confidence levels (GapMind)
    permissible_values:
      high:
        description: High confidence (>90% enzymes present)
      medium:
        description: Medium confidence (50-90% enzymes present)
      low:
        description: Low confidence (25-50% enzymes present)
      gap:
        description: Gap (<25% enzymes present)

  GapTypeEnum:
    description: Type of metabolic gap
    permissible_values:
      amino_acid:
        description: Amino acid biosynthesis gap
      vitamin:
        description: Vitamin biosynthesis gap
      cofactor:
        description: Cofactor biosynthesis gap
      carbon_source:
        description: Carbon source utilization gap

  PathwayTypeEnum:
    description: Type of pathway analyzed
    permissible_values:
      amino_acid:
        description: Amino acid biosynthesis pathway
      vitamin:
        description: Vitamin biosynthesis pathway
      carbon_source:
        description: Carbon source utilization pathway

  BioavailabilityEnum:
    description: Bioavailability assessment
    permissible_values:
      VERY HIGH:
        description: Very high bioavailability (ultra-high affinity transporters)
      HIGH:
        description: High bioavailability
      MODERATE:
        description: Moderate bioavailability
      LOW:
        description: Low bioavailability
      NA:
        description: Not applicable (e.g., extracellular buffer)

  TransporterTypeEnum:
    description: Transporter types
    permissible_values:
      ABC:
        description: ATP-binding cassette transporter
      MFS:
        description: Major facilitator superfamily
      TonB:
        description: TonB-dependent receptor
      ECF:
        description: Energy-coupling factor transporter
      Channel:
        description: Channel protein (facilitated diffusion)
      Symporter:
        description: Symporter (co-transport)
      Antiporter:
        description: Antiporter (exchange)
      GTP-dependent:
        description: GTP-dependent transporter

  AffinityEnum:
    description: Transporter affinity classification
    permissible_values:
      ultra_high:
        description: Ultra-high affinity (Km < 0.1 µM)
      very_high:
        description: Very high affinity (Km 0.1-1 µM)
      high:
        description: High affinity (Km 1-10 µM)
      moderate:
        description: Moderate affinity (Km 10-100 µM)
      low-moderate:
        description: Low-moderate affinity (Km 50-200 µM)
      low:
        description: Low affinity (Km > 100 µM)

  SignificanceEnum:
    description: Statistical significance classification
    permissible_values:
      highly_significant:
        description: Highly significant (p < 0.001)
      very_significant:
        description: Very significant (p < 0.01)
      significant:
        description: Significant (p < 0.05)
      not_significant:
        description: Not significant (p >= 0.05)

  SynergyTypeEnum:
    description: Type of synergy
    permissible_values:
      complementary:
        description: Complementary functions
      complementary_carbon_sources:
        description: Complementary carbon sources
      mechanistic_complementary:
        description: Mechanistic complementary (enzyme-substrate)
      sequential_pathway:
        description: Sequential pathway steps
      enzyme_substrate:
        description: Enzyme-substrate relationship
      essential_complementary:
        description: Essential complementary (both required)
      alternative:
        description: Alternative (not synergistic)

  NoveltyEnum:
    description: Novelty assessment based on similarity (v7+)
    permissible_values:
      HIGH:
        description: Similarity <0.60, truly novel direction
      MEDIUM:
        description: Similarity 0.60-0.80, related but distinct
      LOW:
        description: Similarity >0.80, incremental improvement

  SimilarityInterpretationEnum:
    description: Interpretation of cosine similarity scores (v7+)
    permissible_values:
      NEARLY_IDENTICAL:
        description: 0.95-1.00, nearly identical
      VERY_HIGH:
        description: 0.85-0.95, very similar
      HIGH:
        description: 0.70-0.85, functionally equivalent
      MEDIUM:
        description: 0.60-0.70, related compounds
      LOW:
        description: <0.60, distant relationship

  ToxicityWarningEnum:
    description: Toxicity warning level from Tier 2D safety analysis (v9+)
    permissible_values:
      SAFE:
        description: No toxicity concerns, safe for microbial growth media
      CAUTION:
        description: Minor concerns (no clear biological role, 1-2 toxicity papers)
      WARNING:
        description: Significant concerns (pesticide/herbicide/xenobiotic classification, ≥3 toxicity papers)

  DataSourceTypeEnum:
    description: Type of data source used in generation (v11+)
    permissible_values:
      experimental:
        description: Experimental data (OD600, Nd_uM, plate reader results)
      database:
        description: Database (MP ingredient DB, KG-Microbe, ChEBI)
      literature:
        description: Literature (PubMed, Semantic Scholar, local PDFs)
      computational:
        description: Computational prediction (GapMind, FBA, PCA, clustering)
      reference:
        description: Reference data (previous MP_plus versions)
      genome:
        description: Genome annotation data

  AdjustmentTypeEnum:
    description: Type of factor range adjustment for v14 design (v14+)
    permissible_values:
      EXPAND_UPPER:
        description: Increase upper bound (optima at current maximum)
      EXPAND_LOWER:
        description: Decrease lower bound (optima at current minimum)
      CONTRACT:
        description: Narrow range (low sensitivity, not impactful)
      SHIFT:
        description: Shift center without changing width (interior optimum)
      MAINTAIN:
        description: Keep current range (well-calibrated)

  BoundaryEffectEnum:
    description: Location of optima relative to design space boundaries (v14+)
    permissible_values:
      UPPER:
        description: Optimal values clustered at upper boundary
      LOWER:
        description: Optimal values clustered at lower boundary
      NONE:
        description: Optimal values in interior (not at boundaries)
      BOTH:
        description: Multiple optima at both boundaries