Fold every spelling of a registry the census already counts

_fleet/README.md

@@ -187,11 +187,30 @@ ontologies, because they are how NaturalProductMech cites its corpus. MIBiG is a
 seeded grounding source; NPAtlas is a cross-reference target only, since its
 licence bars ingestion into a CC BY 4.0 corpus.
 
-`prefix_census.py`'s prefix alternation is a hand-maintained list and is known to
-be incomplete: TOGO, UTEX and CCAP are absent although comparable registries
-(MediaDive, DSMZ, ATCC, GOLD) are present. TOGO is CultureMech's second-largest
-structured namespace at 2,833 occurrences, so the heatmap currently understates
-it. Adding a prefix changes the heatmap's columns, so it needs a full rescan.
+`prefix_census.py`'s prefix alternation is a hand-maintained list. Its `norm`
+table folds every namespace named for or qualified by a counted registry into
+that registry: case and alternate names (`gold:` and `GOLD:`, `SwissProt:` and
+`UniProt:`, `TAXON:` and `NCBITaxon:`, `CAS-RN:` and `CAS:`, `TC:` and `TCDB:`), and entity-qualified
+namespaces (`kegg.compound:`, `mediadive.medium:`, `gtdb.genome:`,
+`uniprot.location:`, `RHEA-COMP:`), as `gold.ecosystem` and `pubchem.compound`
+always did (#271). Reference and curator collections named for a registry are
+not its terms and stay out: `GO_REF:` and `PO_REF:` are literature-like (#84
+lists GO_REF as a CITATION candidate), and `GOC:` is curator attribution, which
+#84 proposes never to count (#282). Mechs mix lowercase bioregistry spellings with upper-case ones,
+TaxonMech most heavily (#279). The list was measured by scanning every record at the
+#120 pins with a pattern allowing dots, underscores and hyphens; a spelling a
+Mech adopts later is missed until someone scans again. Until #84's fold (#244,
+#255, #270) those spellings went uncounted, 1.49 million GOLD and 556,160 BacDive
+identifiers in TaxonMech among them. `build_subsets.py` folds the same spellings
+for heatmap columns. Rhea compounds, whose ids share values with Rhea reactions,
+and PDB ligand codes, a different kind of identifier from entries, keep their own
+term keys, so an overlap never pairs a compound with a reaction or shows a
+ligand as an entry. Which
+namespaces to count at all is still open on #84, which has the measured
+inventory: CATH, CDD, PROSITE, StrainInfo, LPSN, TOGO, UNII and about a hundred
+more are cited but not counted. Adding a prefix to the census does not add a
+heatmap column (`build_data.VOC` decides those, and `PrefixListTests` keeps the
+lists consistent), but it changes the vocabulary tile and needs a full rescan.
 
 ## Published-site refresh (September 24, 2026)
 

_fleet/data/prefix_census.json

@@ -59,13 +59,13 @@
    "GO": 11688,
    "DOI": 6636,
    "NCBITaxon": 1438,
+   "UniProt": 993,
    "PMID": 698,
-   "UniProt": 337,
-   "PDB": 277,
+   "PDB": 280,
    "InterPro": 206,
    "ECO": 145,
    "SO": 69,
-   "CHEBI": 65,
+   "CHEBI": 66,
    "Pfam": 22,
    "ComplexPortal": 16,
    "METPO": 14,
@@ -79,32 +79,33 @@
  "ProteinTraitsMech": {
   "files": 429293,
   "prefixes": {
-   "InterPro": 1480044,
-   "UniProt": 658574,
-   "PMID": 657527,
-   "RHEA": 613456,
+   "InterPro": 1480046,
+   "UniProt": 659208,
+   "PMID": 657552,
+   "RHEA": 624625,
    "Pfam": 521966,
    "GO": 421586,
    "ARO": 397717,
-   "CHEBI": 374424,
-   "NCBITaxon": 358320,
+   "CHEBI": 374596,
+   "NCBITaxon": 358325,
    "RO": 278407,
-   "PDB": 235957,
+   "PDB": 250830,
    "DOI": 193845,
    "NCBIfam": 139525,
-   "EC": 119999,
+   "EC": 120213,
    "BFO": 74488,
    "ComplexPortal": 20753,
    "SO": 19302,
-   "TCDB": 4705,
+   "TCDB": 4899,
+   "KEGG": 2018,
    "CL": 260,
-   "KEGG": 245,
    "METPO": 244,
    "PATO": 124,
    "PO": 53,
    "UBERON": 43,
+   "MESH": 14,
    "ECO": 4,
-   "MESH": 1
+   "PubChem": 1
   }
  },
  "NaturalProductMech": {
@@ -114,9 +115,11 @@
    "MIBiG": 10133,
    "DOI": 8437,
    "PMID": 5703,
+   "PubChem": 3290,
    "NPAtlas": 1756,
    "CHEBI": 1659,
    "UniProt": 613,
+   "ChEMBL": 41,
    "RHEA": 14
   }
  },
@@ -126,30 +129,32 @@
    "CHEBI": 22104,
    "ARO": 16653,
    "CAS": 1823,
+   "KEGG": 1461,
    "PMID": 1207,
    "NCBITaxon": 1085,
    "PubChem": 592,
    "DrugBank": 508,
+   "ChEMBL": 415,
+   "PDB": 339,
    "UniProt": 278,
    "PHIPO": 217,
    "DOI": 216,
-   "PDB": 6,
    "GO": 3
   }
  },
  "MediaIngredientMech": {
   "files": 2953,
   "prefixes": {
-   "CHEBI": 8220,
-   "CAS": 727,
+   "CHEBI": 8224,
+   "CAS": 1463,
+   "MediaDive": 538,
    "MICRO": 351,
-   "MESH": 326,
+   "MESH": 328,
    "NCIT": 306,
    "FOODON": 273,
    "ENVO": 110,
    "KEGG": 61,
    "PMID": 29,
-   "MediaDive": 24,
    "UBERON": 23,
    "DOI": 9,
    "BTO": 3,
@@ -160,6 +165,8 @@
   "files": 6288,
   "prefixes": {
    "CHEBI": 160678,
+   "MediaDive": 4843,
+   "KOMODO": 3262,
    "KEGG": 1406,
    "MICRO": 356,
    "FOODON": 223,
@@ -168,7 +175,6 @@
    "PMID": 68,
    "NCBITaxon": 63,
    "ENVO": 13,
-   "MediaDive": 10,
    "DSMZ": 9,
    "BacDive": 1,
    "NCIT": 1,
@@ -179,13 +185,17 @@
   "files": 625960,
   "prefixes": {
    "NCBITaxon": 9250364,
-   "GTDB": 648112,
+   "GOLD": 1492983,
+   "GTDB": 783276,
+   "BacDive": 556160,
    "DOI": 402247,
+   "IMG": 68303,
+   "DSMZ": 31553,
    "PMID": 20558,
    "ATCC": 8870
   }
  },
- "_as_of": "2026-09-24",
+ "_as_of": "2026-09-25",
  "_revisions": {
   "HabitatMech": "b16e3099478a7ea55b82142836e9a118ae062cf6",
   "CommunityMech": "8505a56d644b02fe87f776be9d667db4cf3f5c5d",

_fleet/data/subsets_summary.json

@@ -251,10 +251,10 @@
    ]
   },
   "CommunityMech|ProteinTraitsMech": {
-   "n": 689,
+   "n": 690,
    "by": {
     "CHEBI": 276,
-    "NCBITaxon": 226,
+    "NCBITaxon": 227,
     "GO": 186,
     "UBERON": 1
    },
@@ -316,9 +316,9 @@
    ]
   },
   "CommunityMech|MediaIngredientMech": {
-   "n": 240,
+   "n": 241,
    "by": {
-    "CHEBI": 238,
+    "CHEBI": 239,
     "ENVO": 2
    },
    "ex": [
@@ -533,11 +533,11 @@
    ]
   },
   "CellStructureMech|ProteinTraitsMech": {
-   "n": 1058,
+   "n": 1059,
    "by": {
     "GO": 737,
     "UniProt": 155,
-    "NCBITaxon": 77,
+    "NCBITaxon": 78,
     "InterPro": 64,
     "CHEBI": 15,
     "Pfam": 10
@@ -660,9 +660,9 @@
    ]
   },
   "ProteinTraitsMech|NaturalProductMech": {
-   "n": 794,
+   "n": 795,
    "by": {
-    "NCBITaxon": 487,
+    "NCBITaxon": 488,
     "UniProt": 156,
     "CHEBI": 148,
     "RHEA": 3
@@ -683,10 +683,11 @@
    ]
   },
   "ProteinTraitsMech|AntibioticMech": {
-   "n": 2435,
+   "n": 2575,
    "by": {
     "ARO": 1740,
     "CHEBI": 594,
+    "PDB": 140,
     "NCBITaxon": 79,
     "UniProt": 20,
     "GO": 2
@@ -707,9 +708,9 @@
    ]
   },
   "ProteinTraitsMech|MediaIngredientMech": {
-   "n": 798,
+   "n": 803,
    "by": {
-    "CHEBI": 797,
+    "CHEBI": 802,
     "UBERON": 1
    },
    "ex": [
@@ -728,9 +729,9 @@
    ]
   },
   "ProteinTraitsMech|CultureMech": {
-   "n": 233,
+   "n": 234,
    "by": {
-    "CHEBI": 221,
+    "CHEBI": 222,
     "NCBITaxon": 10,
     "UBERON": 2
    },
@@ -750,9 +751,9 @@
    ]
   },
   "ProteinTraitsMech|TaxonMech": {
-   "n": 7444,
+   "n": 7445,
    "by": {
-    "NCBITaxon": 7444
+    "NCBITaxon": 7445
    },
    "ex": [
     {
@@ -853,9 +854,10 @@
    ]
   },
   "AntibioticMech|MediaIngredientMech": {
-   "n": 324,
+   "n": 345,
    "by": {
-    "CHEBI": 324
+    "CHEBI": 324,
+    "CAS": 21
    },
    "ex": [
     {
@@ -986,22 +988,22 @@
   "CellStructureMech|InterPro": 33,
   "CellStructureMech|METPO": 5,
   "CellStructureMech|NCBITaxon": 531,
-  "CellStructureMech|PDB": 19,
+  "CellStructureMech|PDB": 20,
   "CellStructureMech|Pfam": 8,
-  "CellStructureMech|UniProt": 65,
+  "CellStructureMech|UniProt": 184,
   "ProteinTraitsMech|ARO": 7452,
-  "ProteinTraitsMech|CHEBI": 30122,
+  "ProteinTraitsMech|CHEBI": 30290,
   "ProteinTraitsMech|GO": 110744,
   "ProteinTraitsMech|InterPro": 120090,
-  "ProteinTraitsMech|KEGG": 231,
+  "ProteinTraitsMech|KEGG": 1967,
   "ProteinTraitsMech|METPO": 119,
-  "ProteinTraitsMech|NCBITaxon": 98697,
+  "ProteinTraitsMech|NCBITaxon": 98699,
   "ProteinTraitsMech|PATO": 81,
-  "ProteinTraitsMech|PDB": 51718,
+  "ProteinTraitsMech|PDB": 52174,
   "ProteinTraitsMech|Pfam": 107455,
   "ProteinTraitsMech|RHEA": 29550,
   "ProteinTraitsMech|UBERON": 43,
-  "ProteinTraitsMech|UniProt": 159595,
+  "ProteinTraitsMech|UniProt": 160190,
   "NaturalProductMech|CHEBI": 405,
   "NaturalProductMech|MIBiG": 3115,
   "NaturalProductMech|NCBITaxon": 3115,
@@ -1012,11 +1014,12 @@
   "AntibioticMech|CAS": 1797,
   "AntibioticMech|CHEBI": 2814,
   "AntibioticMech|GO": 3,
+  "AntibioticMech|KEGG": 1154,
   "AntibioticMech|NCBITaxon": 163,
-  "AntibioticMech|PDB": 5,
+  "AntibioticMech|PDB": 331,
   "AntibioticMech|UniProt": 47,
   "MediaIngredientMech|BTO": 1,
-  "MediaIngredientMech|CAS": 287,
+  "MediaIngredientMech|CAS": 739,
   "MediaIngredientMech|CHEBI": 2232,
   "MediaIngredientMech|ENVO": 26,
   "MediaIngredientMech|FOODON": 99,
@@ -1030,7 +1033,7 @@
   "CultureMech|KEGG": 329,
   "CultureMech|NCBITaxon": 30,
   "CultureMech|UBERON": 72,
-  "TaxonMech|GTDB": 118801,
+  "TaxonMech|GTDB": 119248,
   "TaxonMech|NCBITaxon": 625960
  }
 }

_fleet/fleet_fragment.html

@@ -824,9 +824,16 @@ <h2 id="shared-vocabulary">Shared vocabulary</h2>
     if (more > refs.length) out += ' <em>+' + fmt(more - refs.length) + ' more</em>';
     return out;
   }
+  // Term keys that count toward another column (build_subsets TERM_SPACE): a
+  // column filter such as "PDB:" must still find PDB-CCD ligand codes (#284).
+  var TERM_COLUMN = { "PDB-CCD": "PDB", "RHEA-COMP": "RHEA" };
+  function termText(t) {
+    var column = TERM_COLUMN[t.id.split(":")[0]];
+    return (t.id + " " + t.l + (column ? " " + column + ":" : "")).toLowerCase();
+  }
   function renderTermList(box, doc) {
     var q = (box.querySelector("input") || {}).value || "", shown = parseInt(box.dataset.shown || "40", 10);
-    var terms = doc.terms.filter(function (t) { return !q || (t.id + " " + t.l).toLowerCase().indexOf(q.toLowerCase()) >= 0; });
+    var terms = doc.terms.filter(function (t) { return !q || termText(t).indexOf(q.toLowerCase()) >= 0; });
     box.querySelector("ol").innerHTML = terms.slice(0, shown).map(function (t) {
       return '<li><b>' + esc(t.l || t.id) + '</b> <code>' + esc(t.id) + '</code><div class="in"><span>' + esc(doc.a) + ' (' + fmt(t.na) + '):</span> ' + recLinks(doc.base[doc.a], t.a, t.na) + '</div><div class="in"><span>' + esc(doc.b) + ' (' + fmt(t.nb) + '):</span> ' + recLinks(doc.base[doc.b], t.b, t.nb) + '</div></li>';
     }).join("") || '<li><em>No terms match.</em></li>';

assets/fleet/cells/CellStructureMech--PDB.json

@@ -1 +1 @@
-{"mech":"CellStructureMech","prefix":"PDB","base":"https://culturebotai.github.io/CellStructureMech/pages/structures/","total":19,"records":[["appendage/omce_cytochrome_nanowire.html","OmcE cytochrome nanowire"],["appendage/omcs_cytochrome_nanowire.html","OmcS cytochrome nanowire"],["appendage/omcz_cytochrome_nanowire.html","OmcZ cytochrome nanowire"],["cytoskeleton/mamk_filament.html","MamK filament"],["energy_complex/cytochrome_bd_i_ubiquinol_oxidase_complex.html","cytochrome bd-I ubiquinol oxidase complex"],["energy_complex/cytochrome_o_ubiquinol_oxidase_complex.html","cytochrome o ubiquinol oxidase complex"],["energy_complex/fumarate_reductase_complex.html","fumarate reductase complex"],["energy_complex/methyl_coenzyme_m_reductase_complex.html","methyl coenzyme M reductase complex"],["energy_complex/nitrogenase_complex.html","nitrogenase complex"],["energy_complex/proton_transporting_atp_synthase_complex.html","proton-transporting ATP synthase complex"],["energy_complex/respiratory_chain_complex_i.html","respiratory chain complex I"],["energy_complex/respiratory_chain_complex_ii_succinate_dehydrogenase.html","respiratory chain complex II (succinate dehydrogenase)"],["energy_complex/respiratory_chain_complex_iii.html","respiratory chain complex III"],["energy_complex/respiratory_chain_complex_iv.html","respiratory chain complex IV"],["energy_complex/sodium_translocating_nadh_quinone_reductase_complex.html","sodium-translocating NADH:quinone reductase complex"],["other/dna_gyrase_complex.html","DNA gyrase complex"],["other/exodeoxyribonuclease_v_complex.html","exodeoxyribonuclease V complex"],["other/single_stranded_dna_binding_protein_complex.html","single-stranded DNA-binding protein complex"],["secretion_system/esx_3_type_vii_secretion_system_membrane_complex.html","ESX-3 type VII secretion system membrane complex"]]}
+{"mech":"CellStructureMech","prefix":"PDB","base":"https://culturebotai.github.io/CellStructureMech/pages/structures/","total":20,"records":[["appendage/omce_cytochrome_nanowire.html","OmcE cytochrome nanowire"],["appendage/omcs_cytochrome_nanowire.html","OmcS cytochrome nanowire"],["appendage/omcz_cytochrome_nanowire.html","OmcZ cytochrome nanowire"],["cytoskeleton/mamk_filament.html","MamK filament"],["energy_complex/cytochrome_bd_i_ubiquinol_oxidase_complex.html","cytochrome bd-I ubiquinol oxidase complex"],["energy_complex/cytochrome_o_ubiquinol_oxidase_complex.html","cytochrome o ubiquinol oxidase complex"],["energy_complex/fumarate_reductase_complex.html","fumarate reductase complex"],["energy_complex/methyl_coenzyme_m_reductase_complex.html","methyl coenzyme M reductase complex"],["energy_complex/nitrogenase_complex.html","nitrogenase complex"],["energy_complex/proton_transporting_atp_synthase_complex.html","proton-transporting ATP synthase complex"],["energy_complex/respiratory_chain_complex_i.html","respiratory chain complex I"],["energy_complex/respiratory_chain_complex_ii_succinate_dehydrogenase.html","respiratory chain complex II (succinate dehydrogenase)"],["energy_complex/respiratory_chain_complex_iii.html","respiratory chain complex III"],["energy_complex/respiratory_chain_complex_iv.html","respiratory chain complex IV"],["energy_complex/sodium_translocating_nadh_quinone_reductase_complex.html","sodium-translocating NADH:quinone reductase complex"],["other/dna_gyrase_complex.html","DNA gyrase complex"],["other/exodeoxyribonuclease_v_complex.html","exodeoxyribonuclease V complex"],["other/single_stranded_dna_binding_protein_complex.html","single-stranded DNA-binding protein complex"],["ribonucleoprotein/exosome_rnase_complex.html","exosome (RNase complex)"],["secretion_system/esx_3_type_vii_secretion_system_membrane_complex.html","ESX-3 type VII secretion system membrane complex"]]}