# Curated map from Arabidopsis thaliana pathways to repository modules.
#
# Hand-maintained input to scripts/arath_pathway_gaps.py, which checks every
# module id and gene folder named here against the repository and writes
# ARATH-pathway-gaps.yaml. Keep judgments here and computed facts in the output.
#
# Per pathway:
#   kegg:            KEGG ath maps the pathway falls under (several pathways can
#                    share a broad map, e.g. ath00500 starch and sucrose).
#   modules:         modules whose stated scope covers the pathway.
#   related_modules: modules that cover only one step, or the same chemistry in
#                    another lineage (e.g. a bacterial version). Informational;
#                    they do not count as coverage.
#   arath_genes:     reviewed folders under genes/ARATH/ that act in the pathway.
#   notes:           why the mapping is what it is.
#
# Pathway list: KEGG ath maps (https://rest.kegg.jp/list/pathway/ath, retrieved
# 2026-10-19) plus well-known plant processes that KEGG has no map for. It is
# not exhaustive; AraCyc/PMN has not been compared.

reference:
  kegg_list_url: https://rest.kegg.jp/list/pathway/ath
  kegg_retrieved: '2026-10-19'

# KEGG ath maps deliberately not mapped: global overviews, and maps that KEGG
# generates for Arabidopsis from shared orthologs but that describe animal or
# pathogen biology.
kegg_out_of_scope:
  overview: [ath01100, ath01110, ath01200, ath01210, ath01212, ath01230, ath01232,
    ath01240, ath01250, ath01310, ath01320]
  non_plant_biology: [ath00531, ath00540, ath00543, ath00601, ath00603, ath00604,
    ath00261, ath03250, ath03272, ath04082, ath04081, ath04517, ath04518, ath04519,
    ath04145, ath04148, ath04820, ath04620, ath04382, ath05100, ath04142]

pathways:
# ---------------------------------------------------------------- photosynthesis
- name: Photosynthetic light reactions and antenna complexes
  group: photosynthesis_and_carbon
  kegg: [ath00195, ath00196]
  modules: [photosynthesis]
- name: Calvin-Benson-Bassham cycle (carbon fixation)
  group: photosynthesis_and_carbon
  kegg: [ath00710]
  modules: [photosynthesis]
  notes: A part of the taxon-neutral photosynthesis module.
- name: Chlorophyll biosynthesis
  group: photosynthesis_and_carbon
  kegg: [ath00860]
  modules: [photosynthesis]
  related_modules: [heme_biosynthesis, siroheme_biosynthesis]
  notes: Included in the photosynthesis module only as a supporting part
    (magnesium chelatase onward). Chlorophyll degradation is not covered.
- name: Photorespiration (C2 cycle)
  group: photosynthesis_and_carbon
  kegg: [ath00630]
  modules: [photorespiration_c2_cycle]
  related_modules: [glycolate_glyoxylate_assimilation]
  notes: The photorespiration module includes glycine_cleavage_system by reference;
    the glycolate/glyoxylate module is bacterial.
- name: Starch synthesis and degradation
  group: photosynthesis_and_carbon
  kegg: [ath00500]
  modules: []
  related_modules: [tres_mak_glge_branched_alpha_glucan_biosynthesis, glycogen_biosynthesis]
  notes: Related modules are bacterial or animal alpha-glucan pathways.
- name: Sucrose synthesis and degradation
  group: photosynthesis_and_carbon
  kegg: [ath00500]
  modules: []
- name: Trehalose 6-phosphate metabolism
  group: photosynthesis_and_carbon
  kegg: [ath00500]
  modules: [trehalose_metabolism]
# ----------------------------------------------------------- central metabolism
- name: Glycolysis and gluconeogenesis
  group: central_metabolism
  kegg: [ath00010]
  modules: [emp_glycolysis, gluconeogenesis]
- name: Tricarboxylic acid cycle
  group: central_metabolism
  kegg: [ath00020]
  modules: [tca_cycle]
- name: Pentose phosphate pathway
  group: central_metabolism
  kegg: [ath00030]
  modules: [pentose_phosphate_pathway]
- name: Oxidative phosphorylation
  group: central_metabolism
  kegg: [ath00190]
  modules: [oxphos]
- name: Glyoxylate cycle
  group: central_metabolism
  kegg: [ath00630]
  modules: [glyoxylate_cycle]
- name: Alcoholic fermentation
  group: central_metabolism
  kegg: [ath00010]
  modules: [alcoholic_fermentation]
- name: Galactose metabolism (Leloir)
  group: central_metabolism
  kegg: [ath00052]
  modules: [galactose_leloir_pathway]
- name: Inositol phosphate metabolism
  group: central_metabolism
  kegg: [ath00562]
  modules: [myo_inositol_and_inositol_phosphate_biosynthesis]
- name: Nucleotide sugar interconversion
  group: central_metabolism
  kegg: [ath00520, ath00541]
  modules: []
  related_modules: [udp_glucose_and_udp_galactose_biosynthesis]
  notes: The UDP-glucose/UDP-galactose module is bacterial.
# ----------------------------------------------------- nitrogen and sulfur
- name: Nitrate assimilation (nitrate reductase, nitrite reductase)
  group: nitrogen_and_sulfur
  kegg: [ath00910]
  modules: []
  related_modules: [bacterial_assimilatory_nitrate_reduction, molybdenum_cofactor_biosynthesis]
  arath_genes: [CHL1]
  notes: CHL1 (NRT1.1) is the nitrate transporter/sensor, not an assimilation enzyme.
- name: Ammonium assimilation (GS/GOGAT)
  group: nitrogen_and_sulfur
  kegg: [ath00910, ath00250]
  modules: []
  related_modules: [nitrogen_assimilation_glutamate_glutamine, glutamate_glutamine_ammonia_hub]
  notes: Related modules are fungal and human.
- name: Sulfate assimilation
  group: nitrogen_and_sulfur
  kegg: [ath00920]
  modules: [aps_dependent_assimilatory_sulfate_reduction, paps_sulfate_activation]
- name: Ureide catabolism
  group: nitrogen_and_sulfur
  kegg: [ath00230]
  modules: [ureide_urea_catabolism]
# ------------------------------------------------------------ amino acids
- name: Shikimate and aromatic amino acid biosynthesis
  group: amino_acids
  kegg: [ath00400]
  modules: [bacterial_shikimate_chorismate_biosynthesis, phenylalanine_tyrosine_biosynthesis,
    tryptophan_biosynthesis]
- name: Branched-chain amino acid biosynthesis
  group: amino_acids
  kegg: [ath00290]
  modules: [branched_chain_amino_acid_biosynthesis]
- name: Aspartate-family amino acid biosynthesis (Lys, Thr, Met)
  group: amino_acids
  kegg: [ath00300, ath00260, ath00270]
  modules: [aspartate_family_threonine_biosynthesis, methionine_biosynthesis]
  related_modules: [lysine_biosynthesis]
  notes: The lysine module is the succinylated DAP route; plants use the
    LL-diaminopimelate aminotransferase variant.
- name: Histidine biosynthesis
  group: amino_acids
  kegg: [ath00340]
  modules: [histidine_biosynthesis]
- name: Proline and arginine metabolism
  group: amino_acids
  kegg: [ath00330, ath00220]
  modules: [proline_metabolism, arginine_catabolism_arginase_pathway]
  related_modules: [arginine_biosynthesis]
  notes: The arginine biosynthesis module is scoped to microbes and fungi.
- name: GABA shunt
  group: amino_acids
  kegg: [ath00250]
  modules: [gaba_shunt]
- name: Polyamine metabolism
  group: amino_acids
  kegg: [ath00330]
  modules: [polyamine_metabolism]
- name: Glutathione biosynthesis
  group: amino_acids
  kegg: [ath00480]
  modules: [glutathione_biosynthesis]
# ----------------------------------------------------- cofactors and vitamins
- name: Ascorbate biosynthesis (Smirnoff-Wheeler, L-galactose route)
  group: cofactors_and_vitamins
  kegg: [ath00053]
  modules: []
  related_modules: [erythroascorbate_biosynthesis]
  notes: The erythroascorbate module is the fungal analogue, not the plant pathway.
- name: Tocopherol, plastoquinone and phylloquinone biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00130]
  modules: []
  related_modules: [ubiquinone_biosynthesis]
- name: MEP and mevalonate isoprenoid precursor supply
  group: cofactors_and_vitamins
  kegg: [ath00900]
  modules: [mep_isoprenoid_precursor_biosynthesis, mevalonate_pathway, isoprenoid_diphosphate_biosynthesis]
- name: Thiamine biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00730]
  modules: [eukaryotic_thiamine_biosynthesis]
- name: Folate biosynthesis and one-carbon metabolism
  group: cofactors_and_vitamins
  kegg: [ath00790, ath00670]
  modules: [tetrahydrofolate_biosynthesis, folate_one_carbon_interconversion]
- name: Riboflavin biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00740]
  modules: [riboflavin_biosynthesis]
- name: Vitamin B6 metabolism
  group: cofactors_and_vitamins
  kegg: [ath00750]
  modules: [vitamin_b6_plp_metabolism]
- name: Biotin biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00780]
  modules: [biotin_biosynthesis]
- name: NAD biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00760]
  modules: [nad_biosynthesis_salvage]
- name: Coenzyme A biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00770]
  modules: [coenzyme_a_biosynthesis]
- name: Molybdenum cofactor biosynthesis
  group: cofactors_and_vitamins
  modules: []
  related_modules: [molybdenum_cofactor_biosynthesis]
  notes: The existing module is prokaryotic.
- name: Siroheme biosynthesis
  group: cofactors_and_vitamins
  kegg: [ath00860]
  modules: [siroheme_biosynthesis]
# ----------------------------------------------------------------- lipids
- name: Plastid de novo fatty acid synthesis (type II FAS)
  group: lipids
  kegg: [ath00061]
  modules: []
  related_modules: [fatty_acid_de_novo_synthesis]
  notes: The existing module is the cytosolic type I FAS.
- name: Fatty acid desaturation
  group: lipids
  kegg: [ath01040]
  modules: []
  arath_genes: [FAD2]
- name: Microsomal fatty acid elongation
  group: lipids
  kegg: [ath00062]
  modules: [fatty_acid_elongation_cycle]
- name: Cutin, suberin and cuticular wax biosynthesis
  group: lipids
  kegg: [ath00073]
  modules: []
  arath_genes: [CER1]
- name: Triacylglycerol (seed oil) biosynthesis
  group: lipids
  kegg: [ath00561]
  modules: [seed_triacylglycerol_biosynthesis, triacylglycerol_biosynthesis]
  arath_genes: [DGAT1, WRI1]
- name: Galactolipid (thylakoid membrane lipid) biosynthesis
  group: lipids
  kegg: [ath00561]
  modules: []
- name: Phospholipid biosynthesis
  group: lipids
  kegg: [ath00564]
  modules: [cdp_dag_phospholipid_synthesis]
- name: Sphingolipid biosynthesis
  group: lipids
  kegg: [ath00600]
  modules: [sphingolipid_de_novo_synthesis]
- name: Peroxisomal fatty acid beta-oxidation
  group: lipids
  kegg: [ath00071]
  modules: [peroxisomal_beta_oxidation]
- name: Phytosterol biosynthesis (cycloartenol route)
  group: lipids
  kegg: [ath00100]
  modules: []
  related_modules: [sterol_commitment_squalene_to_lanosterol, ergosterol_biosynthesis]
  notes: Related modules use the lanosterol route of animals and fungi.
# ------------------------------------------------------------- cell wall
- name: Cellulose biosynthesis
  group: cell_wall
  modules: [cellulose_biosynthesis]
- name: Xylan biosynthesis
  group: cell_wall
  modules: [xylan_biosynthesis]
- name: Pectin, xyloglucan and callose biosynthesis
  group: cell_wall
  kegg: [ath00040]
  modules: []
# ------------------------------------------------- specialised metabolism
- name: Aliphatic glucosinolate biosynthesis and myrosinase defence
  group: specialised_metabolism
  kegg: [ath00966]
  modules: [aliphatic_glucosinolate_myrosinase_defense]
- name: Indolic glucosinolate biosynthesis and its MYB regulation
  group: specialised_metabolism
  kegg: [ath00966]
  modules: []
  arath_genes: [MYB34, MYB51, MYB122]
  notes: CYP79B2/B3 sit in the camalexin module; the indole glucosinolate branch
    beyond indole-3-acetaldoxime has no module.
- name: Camalexin biosynthesis
  group: specialised_metabolism
  modules: [camalexin_biosynthesis]
- name: Monolignol (lignin) biosynthesis
  group: specialised_metabolism
  kegg: [ath00940]
  modules: [lignin_monolignol_biosynthesis]
- name: Flavonoid, flavonol and anthocyanin biosynthesis
  group: specialised_metabolism
  kegg: [ath00941, ath00944, ath00942]
  modules: []
  arath_genes: [TT8, TTG1]
  notes: TT8 and TTG1 are the bHLH and WD40 parts of the MBW complex that
    activates late flavonoid genes; TTG1 sits in the trichome module.
- name: Carotenoid biosynthesis
  group: specialised_metabolism
  kegg: [ath00906]
  modules: [carotene_backbone_biosynthesis]
  notes: Covers carotenes only; xanthophylls are not modelled.
- name: Mono-, sesqui- and triterpenoid biosynthesis
  group: specialised_metabolism
  kegg: [ath00902, ath00909]
  modules: []
# --------------------------------------------------- hormone biosynthesis
- name: Gibberellin biosynthesis
  group: hormone_biosynthesis
  kegg: [ath00904]
  modules: [gibberellin_biosynthesis]
- name: Abscisic acid biosynthesis
  group: hormone_biosynthesis
  kegg: [ath00906]
  modules: []
  arath_genes: [NCED3]
  notes: The ABA signaling module excludes biosynthesis from its boundary.
- name: Auxin biosynthesis (TAA/YUCCA indole-3-pyruvate route)
  group: hormone_biosynthesis
  kegg: [ath00380]
  modules: []
- name: Cytokinin biosynthesis
  group: hormone_biosynthesis
  kegg: [ath00908]
  modules: []
- name: Brassinosteroid biosynthesis
  group: hormone_biosynthesis
  kegg: [ath00905]
  modules: []
- name: Jasmonate biosynthesis (oxylipin pathway)
  group: hormone_biosynthesis
  kegg: [ath00592]
  modules: []
- name: Ethylene biosynthesis
  group: hormone_biosynthesis
  kegg: [ath00270]
  modules: []
  related_modules: [methionine_salvage_mta_cycle]
- name: Strigolactone biosynthesis
  group: hormone_biosynthesis
  modules: []
- name: Salicylic acid biosynthesis and NPR1 signaling
  group: hormone_biosynthesis
  modules: [salicylic_acid_biosynthesis_npr1_signaling]
  arath_genes: [ICS1, NPR1, WRKY70]
# -------------------------------------------- hormone and light signaling
- name: Auxin nuclear signaling
  group: signaling
  kegg: [ath04075]
  modules: [auxin_nuclear_signaling]
- name: Polar auxin transport
  group: signaling
  modules: [auxin_polar_transport]
- name: Cytokinin signaling
  group: signaling
  kegg: [ath04075]
  modules: [cytokinin_two_component_signaling]
- name: Gibberellin signaling
  group: signaling
  kegg: [ath04075]
  modules: [gibberellin_della_signaling]
- name: Abscisic acid signaling
  group: signaling
  kegg: [ath04075]
  modules: [abscisic_acid_signaling]
- name: Ethylene signaling
  group: signaling
  kegg: [ath04075]
  modules: [ethylene_signaling]
- name: Brassinosteroid signaling
  group: signaling
  kegg: [ath04075]
  modules: [brassinosteroid_signaling]
- name: Jasmonate signaling
  group: signaling
  kegg: [ath04075]
  modules: [jasmonate_coi1_jaz_signaling]
- name: Strigolactone signaling
  group: signaling
  modules: [strigolactone_signaling_shoot_branching]
- name: Karrikin (KAI2) signaling
  group: signaling
  modules: []
- name: Phytochrome signaling and photomorphogenesis
  group: signaling
  modules: [phytochrome_photomorphogenesis]
- name: Blue-light signaling (cryptochromes and phototropins)
  group: signaling
  modules: []
  arath_genes: [CRY1, CRY2]
  notes: CRY1 and CRY2 sit in the photomorphogenesis and photoperiod modules as
    inputs; there is no module for blue-light signaling or phototropism itself.
- name: UV-B signaling (UVR8)
  group: signaling
  modules: []
  arath_genes: [UVR8]
- name: Circadian clock
  group: signaling
  kegg: [ath04712]
  modules: [plant_circadian_clock_oscillator]
# ----------------------------------------------------------------- immunity
- name: Bacterial PAMP perception (FLS2/EFR)
  group: immunity
  kegg: [ath04626, ath04016]
  modules: [bacterial_pamp_lrr_receptor_signaling]
- name: Chitin perception
  group: immunity
  kegg: [ath04016]
  modules: [chitin_perception]
- name: NLR (effector-triggered) immunity
  group: immunity
  kegg: [ath04626]
  modules: [plant_nlr_resistosome_signaling]
  arath_genes: [RPM1, RPS2]
# ----------------------------------------------------------- abiotic stress
- name: Cold acclimation (ICE1-CBF)
  group: abiotic_stress
  modules: []
  arath_genes: [CBF1, ICE1]
  notes: ICE1 sits in the stomatal lineage module as SCRM.
- name: Drought and osmotic signaling (DREB2)
  group: abiotic_stress
  modules: []
  arath_genes: [DREB2A]
  notes: DREB2A sits in the heat stress module as an HSFA1 target.
- name: Salt tolerance (SOS pathway)
  group: abiotic_stress
  modules: [sos_salt_tolerance]
  arath_genes: [SOS1, CIPK24, HKT1]
- name: Heat stress response
  group: abiotic_stress
  modules: [plant_hsfa1_heat_stress_response]
- name: Phosphate starvation response
  group: abiotic_stress
  modules: []
- name: Iron deficiency response and uptake
  group: abiotic_stress
  modules: []
- name: Hypoxia sensing (N-degron pathway of ERF-VII factors)
  group: abiotic_stress
  modules: []
# -------------------------------------------------------------- development
- name: Flowering time (photoperiod, vernalization, autonomous pathways)
  group: development
  modules: [photoperiodic_flowering_co_ft, vernalization_flc_silencing, autonomous_flowering_pathway]
- name: Floral meristem and floral organ identity
  group: development
  modules: [floral_meristem_identity, floral_organ_identity_abce]
- name: Shoot apical meristem maintenance (CLV-WUS)
  group: development
  modules: [shoot_meristem_clv_wus_feedback]
- name: Root radial patterning (SHR-SCR)
  group: development
  modules: [root_radial_patterning_shr_scr]
- name: Stomatal development
  group: development
  modules: [stomatal_lineage_development]
- name: Trichome initiation and patterning
  group: development
  modules: [trichome_initiation_mbw]
# --------------------------------------------- small RNA and chromatin
- name: miRNA biogenesis and AGO1 loading
  group: small_rna_and_chromatin
  modules: [plant_mirna_biogenesis]
- name: siRNA, tasiRNA and RNA-directed DNA methylation
  group: small_rna_and_chromatin
  modules: []
  arath_genes: [RDR6]
  notes: RDR6 sits in the miRNA biogenesis module.
- name: Polycomb (PRC2) silencing
  group: small_rna_and_chromatin
  kegg: [ath03083]
  modules: [vernalization_flc_silencing]
  notes: Covered only as it acts at FLC.
# ------------------------------------------- organelles and cell biology
- name: Chloroplast protein import (TOC/TIC)
  group: organelles
  modules: []
- name: Peroxisome biogenesis and matrix protein import
  group: organelles
  kegg: [ath04146]
  modules: [peroxisome-lifecycle]
- name: Autophagy
  group: organelles
  kegg: [ath04136]
  modules: []
  related_modules: [metazoan_autophagosome_biogenesis]
- name: ER unfolded protein response
  group: organelles
  kegg: [ath04141]
  modules: [er_unfolded_protein_response]
- name: Nuclear envelope LINC complex
  group: organelles
  modules: [linc_complex]