# Failure-mode classification of the 76 ARBA rule reviews in rules/arba/.
#
# Each entry is a curator judgement made by reading the rule review's
# description, review_summary and action_rationale. `action` is copied from the
# review. `primary` is the failure that decides the verdict; `secondary` lists
# other defects the review documents. Modes are defined in `modes` below.
#
# Selection caveat: these rules were mostly chosen because GO curators had
# flagged them (several reviews cite geneontology/go-annotation issues), so the
# distribution here describes flagged rules, not ARBA as a whole.

modes:
  # --- consequent is wrong for some or all matched proteins ---
  HETEROGENEOUS_CONSEQUENT: >-
    Condition sets pool unrelated families under one term that fits only some
    of them; for the rest the term is wrong-branch (e.g. kinases annotated to
    phosphatidylinositol biosynthesis).
  SUBSTRATE_OR_CARGO: >-
    The protein is what the process acts on (cargo, substrate, degraded
    object), not what performs it.
  ACTIVITY_MISMATCH: >-
    A specific activity that the family does not have, or two distinct
    activities conflated under one term.
  NONCATALYTIC_HOMOLOG: >-
    Catalytic activity assigned to family members that have lost it
    (pseudoenzymes, cofactors).
  MECHANISM_OVEREXTENDED: >-
    A mechanism characterized in one lineage is applied to taxa where it is
    absent or unproven.
  SPURIOUS_SIGNATURE: >-
    The signature is not diagnostic of the function; the association looks
    data-mined (low containment, generic domains, zero matches).
  # --- consequent true but of little value ---
  TOO_GENERAL: >-
    The term is true for the matched proteins but so general it adds nothing
    (keyword-level classes such as Transferase, Hydrolase, Kinase).
  TOO_SPECIFIC: >-
    The term claims more than the evidence supports (direction, location, a
    precise sub-process).
  # --- rule construction ---
  MEGA_RULE: >-
    Tens to thousands of OR'd condition sets; impossible to audit, and the
    source of most HETEROGENEOUS_CONSEQUENT and TOO_GENERAL output.
  LOGIC_ERROR: >-
    AND over signatures that rarely co-occur, nested or identical conditions,
    or conditions that match no protein.
  ARBITRARY_TAXON: >-
    Taxon restrictions with no biological rationale (Primates, Mus, Homo) or
    inconsistent across condition sets of one rule.
  REDUNDANT_WITH_INTERPRO2GO: >-
    Every condition set is already covered by an InterPro2GO mapping to the
    same term.
  STALE: >-
    The consequent is obsolete, or the rule is withdrawn but still referenced.
  # --- not a failure ---
  SOUND: The rule, or its core, is correct; any defects are cosmetic.
  NOT_ASSESSED: The review could not assess the rule.

rules:
  - {id: ARBA00000900, action: DEPRECATE, consequent: "EC 2.3.2.27 ubiquitin-protein transferase", condition_sets: 298, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00001096, action: MODIFY, consequent: "EC 5.1.3.15 glucose-6-phosphate 1-epimerase", condition_sets: 1, primary: LOGIC_ERROR, secondary: [], note: "AND over three nested InterPro entries; effectively one condition"}
  - {id: ARBA00001712, action: MODIFY, consequent: "EC 5.1.3.3 aldose 1-epimerase", condition_sets: 2, primary: LOGIC_ERROR, secondary: [ARBITRARY_TAXON], note: "nested conditions; Metazoa vs Eukaryota inconsistency"}
  - {id: ARBA00004173, action: MODIFY, consequent: "SubCell Mitochondrion -> GO:0005739", condition_sets: 1490, primary: MEGA_RULE, secondary: [HETEROGENEOUS_CONSEQUENT], note: "large correct core (TOM40, MIC60, COX subunits); some branches wrong"}
  - {id: ARBA00004218, action: REMOVE, consequent: "SubCell acrosome", condition_sets: 35, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE], note: "ENaC, DLD, complement among 35 sets; 4 sets supported"}
  - {id: ARBA00004725, action: MODIFY, consequent: "Pathway: UMP biosynthesis via de novo pathway", condition_sets: 27, primary: MEGA_RULE, secondary: [], note: "biology sound; consolidation only"}
  - {id: ARBA00004841, action: MODIFY, consequent: "Pathway: heparan sulfate biosynthesis", condition_sets: 3, primary: SPURIOUS_SIGNATURE, secondary: [LOGIC_ERROR], note: "P-loop NTPase domain (40,360 proteins) as a condition"}
  - {id: ARBA00005098, action: DEPRECATE, consequent: "Pathway: urea cycle (arginase/agmatinase)", condition_sets: null, primary: ACTIVITY_MISMATCH, secondary: [ARBITRARY_TAXON], note: "arginase and agmatinase conflated"}
  - {id: ARBA00022438, action: MODIFY, consequent: "KW Aminopeptidase", condition_sets: 86, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00022487, action: REMOVE, consequent: "KW Serine esterase", condition_sets: 62, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00022603, action: UNDECIDED, consequent: null, condition_sets: null, primary: NOT_ASSESSED, secondary: []}
  - {id: ARBA00022670, action: REMOVE, consequent: "KW Protease", condition_sets: 1, primary: MEGA_RULE, secondary: [TOO_GENERAL, NONCATALYTIC_HOMOLOG], note: "one condition set OR-ing 502 InterPro entries"}
  - {id: ARBA00022679, action: REMOVE, consequent: "KW Transferase", condition_sets: 4473, primary: MEGA_RULE, secondary: [TOO_GENERAL], note: "14 million proteins"}
  - {id: ARBA00022722, action: REMOVE, consequent: "KW Nuclease", condition_sets: 532, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00022759, action: REMOVE, consequent: "KW Endonuclease", condition_sets: 318, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00022777, action: REMOVE, consequent: "KW Kinase", condition_sets: 1358, primary: MEGA_RULE, secondary: [TOO_GENERAL, NONCATALYTIC_HOMOLOG], note: "pseudokinases"}
  - {id: ARBA00022801, action: REMOVE, consequent: "KW Hydrolase", condition_sets: 4070, primary: MEGA_RULE, secondary: [TOO_GENERAL, HETEROGENEOUS_CONSEQUENT], note: "includes kinase and GTPase domains"}
  - {id: ARBA00022806, action: MODIFY, consequent: "KW Helicase", condition_sets: 355, primary: MEGA_RULE, secondary: [], note: "biology sound"}
  - {id: ARBA00022825, action: REMOVE, consequent: "KW Serine protease", condition_sets: 240, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00022912, action: MODIFY, consequent: "KW Protein phosphatase", condition_sets: 210, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00023002, action: MODIFY, consequent: "KW Oxidoreductase", condition_sets: 2105, primary: MEGA_RULE, secondary: [HETEROGENEOUS_CONSEQUENT], note: "kinases and phosphatases among the sets"}
  - {id: ARBA00023137, action: DEPRECATE, consequent: "KW Tyrosine-protein kinase", condition_sets: 98, primary: MEGA_RULE, secondary: [HETEROGENEOUS_CONSEQUENT]}
  - {id: ARBA00023239, action: DEPRECATE, consequent: "KW Lyase", condition_sets: 894, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00026249, action: DEPRECATE, consequent: "GO:0004791 thioredoxin-disulfide reductase (NADPH) activity", condition_sets: 3, primary: REDUNDANT_WITH_INTERPRO2GO, secondary: [LOGIC_ERROR]}
  - {id: ARBA00026302, action: DEPRECATE, consequent: "GO:1901137 carbohydrate derivative biosynthetic process", condition_sets: 185, primary: MEGA_RULE, secondary: [TOO_GENERAL, HETEROGENEOUS_CONSEQUENT]}
  - {id: ARBA00026372, action: DEPRECATE, consequent: "GO:0051998 protein carboxyl O-methyltransferase activity", condition_sets: 5, primary: ACTIVITY_MISMATCH, secondary: [], note: "ICMT and PIMT conflated"}
  - {id: ARBA00026480, action: DEPRECATE, consequent: "GO:0010605 negative regulation of macromolecule metabolic process", condition_sets: 343, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE]}
  - {id: ARBA00026572, action: DEPRECATE, consequent: "GO:0006139 nucleobase-containing compound metabolic process", condition_sets: 781, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00026647, action: DEPRECATE, consequent: "GO:0010629 negative regulation of gene expression", condition_sets: 131, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE], note: "ESA1 acetyltransferase annotated as a negative regulator"}
  - {id: ARBA00026698, action: DEPRECATE, consequent: "GO:0007034 vacuolar transport", condition_sets: 26, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE, ARBITRARY_TAXON]}
  - {id: ARBA00026708, action: MODIFY, consequent: "GO:0007031 peroxisome organization", condition_sets: 10, primary: MECHANISM_OVEREXTENDED, secondary: [TOO_GENERAL]}
  - {id: ARBA00026799, action: ACCEPT, consequent: "GO:0003951 NAD+ kinase activity", condition_sets: 6, primary: SOUND, secondary: []}
  - {id: ARBA00026991, action: DEPRECATE, consequent: "GO:0015980 energy derivation by oxidation of organic compounds", condition_sets: 83, primary: MEGA_RULE, secondary: [TOO_GENERAL, ARBITRARY_TAXON]}
  - {id: ARBA00027164, action: DEPRECATE, consequent: "GO:0006401 RNA catabolic process", condition_sets: 51, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE], note: "helicases and terminal transferases called catabolic"}
  - {id: ARBA00027169, action: DEPRECATE, consequent: "GO:0120114 Sm-like protein family complex", condition_sets: 28, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE, ARBITRARY_TAXON], note: "translation elongation factors included"}
  - {id: ARBA00027389, action: DEPRECATE, consequent: "GO:0042546 cell wall biogenesis", condition_sets: 29, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE], note: "polyketide synthases, LRR kinases, Rho GTPases"}
  - {id: ARBA00027399, action: MODIFY, consequent: "GO:0008236 serine-type peptidase activity", condition_sets: 36, primary: MEGA_RULE, secondary: [NONCATALYTIC_HOMOLOG], note: "Protein S cofactor"}
  - {id: ARBA00027430, action: DEPRECATE, consequent: "GO:0006066 alcohol metabolic process", condition_sets: 89, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE, ARBITRARY_TAXON]}
  - {id: ARBA00027624, action: DEPRECATE, consequent: "GO:0031090 organelle membrane", condition_sets: 304, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00027651, action: DEPRECATE, consequent: "GO:0004721 phosphoprotein phosphatase activity", condition_sets: 74, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00027723, action: DEPRECATE, consequent: "GO:0016740 transferase activity", condition_sets: 1094, primary: MEGA_RULE, secondary: [TOO_GENERAL, HETEROGENEOUS_CONSEQUENT], note: "PAS domain included"}
  - {id: ARBA00027853, action: MODIFY, consequent: "GO:0006720 isoprenoid metabolic process", condition_sets: 94, primary: MEGA_RULE, secondary: [HETEROGENEOUS_CONSEQUENT], note: "64 of 94 sets sound; human subset 100% correct"}
  - {id: ARBA00027994, action: SPLIT, consequent: "GO:0006338 chromatin remodeling", condition_sets: 134, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE], note: "UBR7 via PHD-like zinc finger (go-annotation#5899)"}
  - {id: ARBA00028131, action: MODIFY, consequent: "GO:0004175 endopeptidase activity", condition_sets: 41, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00028334, action: DEPRECATE, consequent: "GO:0010468 regulation of gene expression", condition_sets: 930, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00028538, action: DEPRECATE, consequent: "GO:0046467 membrane lipid biosynthetic process (obsolete)", condition_sets: 51, primary: STALE, secondary: [HETEROGENEOUS_CONSEQUENT], note: "obsoleted 2025-12-09; rule modified 2025-12-15 without noticing"}
  - {id: ARBA00028584, action: MODIFY, consequent: "GO:0005778 peroxisomal membrane", condition_sets: 9, primary: SOUND, secondary: [HETEROGENEOUS_CONSEQUENT], note: "7 of 9 sets correct; NBR1 set wrong"}
  - {id: ARBA00028655, action: SPLIT, consequent: "GO:0006661 phosphatidylinositol biosynthetic process", condition_sets: 25, primary: HETEROGENEOUS_CONSEQUENT, secondary: [], note: "2 of 25 sets are PI synthase; rest kinases, phosphatases, GPI enzymes"}
  - {id: ARBA00028665, action: DEPRECATE, consequent: "GO:0048468 cell development", condition_sets: 174, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00028985, action: DEPRECATE, consequent: "GO:0016070 RNA metabolic process", condition_sets: 357, primary: MEGA_RULE, secondary: [TOO_GENERAL]}
  - {id: ARBA00029057, action: DEPRECATE, consequent: "GO:0065003 protein-containing complex assembly", condition_sets: 89, primary: HETEROGENEOUS_CONSEQUENT, secondary: [MEGA_RULE, TOO_GENERAL]}
  - {id: ARBA00035048, action: MODIFY, consequent: "spliceosomal complex", condition_sets: 17, primary: MEGA_RULE, secondary: [ARBITRARY_TAXON], note: "biology sound"}
  - {id: ARBA00035068, action: MODIFY, consequent: "GO:0004438 phosphatidylinositol-3-phosphate phosphatase activity", condition_sets: 2, primary: NONCATALYTIC_HOMOLOG, secondary: [ARBITRARY_TAXON], note: "no exclusion of pseudophosphatase MTMRs; MTM1 set restricted to Primates"}
  - {id: ARBA00043370, action: DEPRECATE, consequent: "GO:0140115 export across plasma membrane", condition_sets: 12, primary: TOO_SPECIFIC, secondary: [HETEROGENEOUS_CONSEQUENT], note: "direction and membrane cannot be inferred (go-annotation#6140)"}
  - {id: ARBA00045851, action: MODIFY, consequent: "MORN3 p53/SIRT1/MDM2 function", condition_sets: null, primary: MECHANISM_OVEREXTENDED, secondary: [], note: "fly ortholog flagged (go-annotation#6179)"}
  - {id: ARBA00047230, action: MODIFY, consequent: "PtdIns(3,5)P2 3-phosphatase activity", condition_sets: 3, primary: NONCATALYTIC_HOMOLOG, secondary: [ARBITRARY_TAXON, LOGIC_ERROR]}
  - {id: ARBA00047239, action: MODIFY, consequent: "GO:0032206 positive regulation of telomere maintenance", condition_sets: 9, primary: HETEROGENEOUS_CONSEQUENT, secondary: [ARBITRARY_TAXON, LOGIC_ERROR], note: "ATM, MAPK, RUVBL families; Homo, Mus, Haplorrhini restrictions"}
  - {id: ARBA00047244, action: DEPRECATE, consequent: "GO:0043605 amide catabolic process", condition_sets: 4, primary: LOGIC_ERROR, secondary: [TOO_GENERAL], note: "AND over urease subunits: <=10 of 851 proteins match"}
  - {id: ARBA00049204, action: MODIFY, consequent: "EC 1.15.1.1 superoxide dismutase", condition_sets: 24, primary: MEGA_RULE, secondary: [], note: "biology sound"}
  - {id: ARBA00085337, action: MODIFY, consequent: "GO:0045454 cell redox homeostasis", condition_sets: 9, primary: HETEROGENEOUS_CONSEQUENT, secondary: [LOGIC_ERROR], note: "NOS, KRIT1, VDAC, SCO1 wrong; 5 of 9 sets correct"}
  - {id: ARBA00085883, action: MODIFY, consequent: "GO:0030167 proteoglycan catabolic process", condition_sets: 4, primary: HETEROGENEOUS_CONSEQUENT, secondary: [ARBITRARY_TAXON], note: "GLB1 and HEXB primarily ganglioside catabolism; Mus restriction"}
  - {id: ARBA00086620, action: DEPRECATE, consequent: "sexual sporulation resulting in cellular spore formation", condition_sets: 5, primary: SPURIOUS_SIGNATURE, secondary: [MECHANISM_OVEREXTENDED, LOGIC_ERROR], note: "matches 0 proteins"}
  - {id: ARBA00087037, action: DEPRECATE, consequent: "GO:0005608 laminin-1 complex", condition_sets: 1, primary: SPURIOUS_SIGNATURE, secondary: [LOGIC_ERROR], note: "cadherin, laminin beta and netrin FunFams ANDed; 0 proteins"}
  - {id: ARBA00088058, action: ACCEPT, consequent: "GO:0051010 microtubule plus-end binding", condition_sets: 5, primary: SOUND, secondary: [LOGIC_ERROR], note: "redundant FunFams to remove"}
  - {id: ARBA00088072, action: DEPRECATE, consequent: "GO:0160103 tRNA G26/G27 dimethyltransferase activity", condition_sets: null, primary: ACTIVITY_MISMATCH, secondary: [STALE], note: "TRM1 is G26-specific; rule no longer in UniProt"}
  - {id: ARBA00089174, action: MODIFY, consequent: "GO:1990845 adaptive thermogenesis", condition_sets: 2, primary: MECHANISM_OVEREXTENDED, secondary: [ARBITRARY_TAXON, LOGIC_ERROR], note: "PM20D1 across Eukaryota; mammalian process"}
  - {id: ARBA00089175, action: ACCEPT, consequent: "GO:1990849 vacuolar localization", condition_sets: 1, primary: SOUND, secondary: [LOGIC_ERROR], note: "two identical FunFam conditions"}
  - {id: ARBA00089176, action: DEPRECATE, consequent: "GO:1990840 response to lectin", condition_sets: 2, primary: SPURIOUS_SIGNATURE, secondary: [ARBITRARY_TAXON, LOGIC_ERROR]}
  - {id: ARBA00089180, action: DEPRECATE, consequent: "GO:1990858 cellular response to lectin", condition_sets: 2, primary: SPURIOUS_SIGNATURE, secondary: [ARBITRARY_TAXON, LOGIC_ERROR]}
  - {id: ARBA00089391, action: DEPRECATE, consequent: "GO:1903711 spermidine transmembrane transport", condition_sets: 2, primary: SPURIOUS_SIGNATURE, secondary: [], note: "21.8% containment"}
  - {id: ARBA00089395, action: DEPRECATE, consequent: "spermine transmembrane transport", condition_sets: 1, primary: SPURIOUS_SIGNATURE, secondary: [LOGIC_ERROR], note: "matches 0 proteins"}
  - {id: ARBA00090047, action: MODIFY, consequent: "GO:1904498 protein localization to mitotic actomyosin contractile ring", condition_sets: 1, primary: TOO_SPECIFIC, secondary: []}
  - {id: ARBA00090252, action: DEPRECATE, consequent: "ribosomal large subunit export from nucleus", condition_sets: 2, primary: SUBSTRATE_OR_CARGO, secondary: [REDUNDANT_WITH_INTERPRO2GO], note: "ribosomal proteins are the cargo"}
  - {id: ARBA00090718, action: DEPRECATE, consequent: "GO:0047545 (S)-2-hydroxyglutarate dehydrogenase activity", condition_sets: 1, primary: ACTIVITY_MISMATCH, secondary: [], note: "same FunFam (3.40.50.720:FF:000041) as the serine-biosynthesis rule ARBA00093701; SerA makes (R)-2-hydroxyglutarate"}
  - {id: ARBA00092121, action: DEPRECATE, consequent: "GO:1903833 positive regulation of cellular response to amino acid starvation", condition_sets: 1, primary: SPURIOUS_SIGNATURE, secondary: [LOGIC_ERROR], note: "DRG1 FunFam; 0 proteins"}
  - {id: ARBA00095398, action: DEPRECATE, consequent: "ribophagy", condition_sets: null, primary: SUBSTRATE_OR_CARGO, secondary: [STALE], note: "ribosomal L12 is degraded by ribophagy; rule already withdrawn"}