diff --git a/src/mol-model-formats/structure/mmcif/parser.ts b/src/mol-model-formats/structure/mmcif/parser.ts
index 29a3c2e3ad5b573d009157cdd73bfcb2474db535..7a35b55203149878a443912a8c3c12e9b744f885 100644
--- a/src/mol-model-formats/structure/mmcif/parser.ts
+++ b/src/mol-model-formats/structure/mmcif/parser.ts
@@ -144,10 +144,13 @@ function getChemicalComponentMap(format: mmCIF_Format): Model['properties']['che
function getSaccharideComponentMap(format: mmCIF_Format): SaccharideComponentMap {
const map = new Map<string, SaccharideComponent>();
- const { pdbx_chem_comp_identifier } = format.data
- if (pdbx_chem_comp_identifier._rowCount > 0) {
- const { comp_id, type, identifier } = pdbx_chem_comp_identifier
- for (let i = 0, il = pdbx_chem_comp_identifier._rowCount; i < il; ++i) {
+
+ if (format.data.pdbx_chem_comp_identifier._rowCount > 0) {
+ // note that `pdbx_chem_comp_identifier` does not contain
+ // a 'SNFG CARB SYMBOL' entry for 'Unknown' saccharide components
+ // so we always need to check `chem_comp` for those
+ const { comp_id, type, identifier } = format.data.pdbx_chem_comp_identifier
+ for (let i = 0, il = comp_id.rowCount; i < il; ++i) {
if (type.value(i) === 'SNFG CARB SYMBOL') {
const snfgName = identifier.value(i)
const saccharideComp = SaccharidesSnfgMap.get(snfgName)
@@ -158,21 +161,24 @@ function getSaccharideComponentMap(format: mmCIF_Format): SaccharideComponentMap
}
}
}
- } else if (format.data.chem_comp._rowCount > 0) {
+ }
+
+ if (format.data.chem_comp._rowCount > 0) {
const { id, type } = format.data.chem_comp
for (let i = 0, il = id.rowCount; i < il; ++i) {
const _id = id.value(i)
+ if (map.has(_id)) continue
const _type = type.value(i)
if (SaccharideCompIdMap.has(_id)) {
map.set(_id, SaccharideCompIdMap.get(_id)!)
- } else if (!map.has(_id) && getMoleculeType(_type, _id) === MoleculeType.saccharide) {
+ } else if (getMoleculeType(_type, _id) === MoleculeType.saccharide) {
map.set(_id, UnknownSaccharideComponent)
}
}
} else {
const uniqueNames = getUniqueComponentNames(format)
SaccharideCompIdMap.forEach((v, k) => {
- if (uniqueNames.has(k)) map.set(k, v)
+ if (!map.has(k) && uniqueNames.has(k)) map.set(k, v)
})
}
return map
diff --git a/src/mol-model/structure/model/types.ts b/src/mol-model/structure/model/types.ts
index 64863fcf0610b7ac75f9a7456e65db462bcc0a8d..1302c2fe162aab2725f6c6d8de932312db602389 100644
--- a/src/mol-model/structure/model/types.ts
+++ b/src/mol-model/structure/model/types.ts
@@ -224,7 +224,12 @@ export function getMoleculeType(compType: string, compId: string) {
} else if (IonNames.has(compId)) {
return MoleculeType.ion
} else if (OtherComponentTypeNames.has(compType)) {
- return MoleculeType.other
+ if (SaccharideCompIdMap.has(compId)) {
+ // trust our saccharide table more than given 'non-polymer' or 'other' component type
+ return MoleculeType.saccharide
+ } else {
+ return MoleculeType.other
+ }
} else {
return MoleculeType.unknown
}
@@ -679,5 +684,5 @@ export const ResidueHydrophobicity = {
'TRP': [ -1.85, -2.09, -0.24 ],
'TYR': [ -0.94, -0.71, 0.23 ],
'VAL': [ 0.07, -0.46, -0.53 ]
- }
- export const DefaultResidueHydrophobicity = [ 0.00, 0.00, 0.00 ]
\ No newline at end of file
+}
+export const DefaultResidueHydrophobicity = [ 0.00, 0.00, 0.00 ]
\ No newline at end of file
diff --git a/src/mol-model/structure/structure/carbohydrates/constants.ts b/src/mol-model/structure/structure/carbohydrates/constants.ts
index 75d23bb9ab999885943b4b3bf97352732f5415f5..7dcb8b51ad3d98cf012da8b64d85098817915ec3 100644
--- a/src/mol-model/structure/structure/carbohydrates/constants.ts
+++ b/src/mol-model/structure/structure/carbohydrates/constants.ts
@@ -172,6 +172,19 @@ const Monosaccharides: SaccharideComponent[] = [
{ abbr: 'Tag', name: 'Tagatose', color: SaccharideColors.Yellow, type: SaccharideType.Assigned },
{ abbr: 'Sor', name: 'Sorbose', color: SaccharideColors.Orange, type: SaccharideType.Assigned },
{ abbr: 'Psi', name: 'Psicose', color: SaccharideColors.Pink, type: SaccharideType.Assigned },
+
+ { abbr: 'Hexose', name: 'Hexose', color: SaccharideColors.Secondary, type: SaccharideType.Hexose },
+ { abbr: 'HexNAc', name: 'HexNAc', color: SaccharideColors.Secondary, type: SaccharideType.HexNAc },
+ { abbr: 'Hexosamine', name: 'Hexosamine', color: SaccharideColors.Secondary, type: SaccharideType.Hexosamine },
+ { abbr: 'Hexuronate', name: 'Hexuronate', color: SaccharideColors.Secondary, type: SaccharideType.Hexuronate },
+ { abbr: 'Deoxyhexose', name: 'Deoxyhexose', color: SaccharideColors.Secondary, type: SaccharideType.Deoxyhexose },
+ { abbr: 'DeoxyhexNAc', name: 'DeoxyhexNAc', color: SaccharideColors.Secondary, type: SaccharideType.DeoxyhexNAc },
+ { abbr: 'Di-deoxyhexose', name: 'Di-deoxyhexose', color: SaccharideColors.Secondary, type: SaccharideType.DiDeoxyhexose },
+ { abbr: 'Pentose', name: 'Pentose', color: SaccharideColors.Secondary, type: SaccharideType.Pentose },
+ { abbr: 'Deoxynonulosonate', name: 'Deoxynonulosonate', color: SaccharideColors.Secondary, type: SaccharideType.Deoxynonulosonate },
+ { abbr: 'Di-deoxynonulosonate', name: 'Di-deoxynonulosonate', color: SaccharideColors.Secondary, type: SaccharideType.DiDeoxynonulosonate },
+ { abbr: 'Unknown', name: 'Unknown', color: SaccharideColors.Secondary, type: SaccharideType.Unknown },
+ { abbr: 'Assigned', name: 'Assigned', color: SaccharideColors.Secondary, type: SaccharideType.Assigned },
]
export const SaccharidesSnfgMap = (function () {
@@ -200,33 +213,27 @@ const CommonSaccharideNames: { [k: string]: string[] } = {
// Hexose
Glc: [
'GLC', 'BGC',
- 'BOG', // via GlyFinder
- 'TRE', // via GlyFinder, di-saccharide but homomer
- 'MLR', // via GlyFinder, tri-saccharide but homomer
+ 'TRE', // di-saccharide but homomer
+ 'MLR', // tri-saccharide but homomer
],
Man: ['MAN', 'BMA'],
- Gal: [
- 'GAL', 'GLA',
- 'GXL' // via PubChem
- ],
- Gul: ['GUP', 'GL0'],
- Alt: ['ALT'],
- All: ['ALL', 'AFD'],
- Tal: ['TAL'],
- Ido: ['4N2'],
+ Gal: ['GLA', 'GAL', 'GZL'],
+ Gul: ['4GL', 'GL0'],
+ Alt: ['Z6H', '3MK'],
+ All: ['AFD', 'ALL'],
+ Tal: [],
+ Ido: ['Z0F', '4N2'],
// HexNAc
- GlcNAc: ['NAG', 'NDG'],
- ManNAc: ['NGA', 'A2G'],
- GulNAc: [],
+ GlcNAc: ['NDG', 'NAG'],
+ ManNAc: ['BM3', 'BM7'],
+ GalNAc: ['A2G', 'NGA'],
+ GulNAc: ['LXB'],
AltNAc: [],
AllNAc: ['NAA'],
TalNAc: [],
- IdoNAc: ['HSQ'],
+ IdoNAc: [],
// Hexosamine
- GlcN: [
- 'GCS', 'PA1',
- 'IDU', 'SGN', 'SUS', // via GlyFinder
- ],
+ GlcN: ['PA1', 'GCS'],
ManN: ['95Z'],
GalN: ['X6X', '1GN'],
GulN: [],
@@ -237,66 +244,76 @@ const CommonSaccharideNames: { [k: string]: string[] } = {
// Hexuronate
GlcA: ['GCU', 'BDP'],
ManA: ['MAV', 'BEM'],
- GalA: ['ADA', 'GTR'],
- GulA: ['LGU'],
+ GalA: ['ADA', 'GTR', 'GTK'],
+ GulA: [],
AltA: [],
AllA: [],
- TalA: ['X0X', 'X1X'],
- IdoA: [
- 'IDR',
- 'IDS', // via GlyFinder
- ],
+ TalA: ['X1X', 'X0X'],
+ IdoA: ['IDR'],
// Deoxyhexose
- Qui: ['G6D'],
+ Qui: ['G6D', 'YYK'],
Rha: ['RAM', 'RM4'],
- '6dGul': [],
+ '6dGul': ['66O'],
'6dAlt': [],
'6dTal': [],
Fuc: ['FUC', 'FUL'],
// DeoxyhexNAc
- QuiNAc: [],
+ QuiNAc: ['Z9W'],
RhaNAc: [],
'6dAltNAc': [],
'6dTalNAc': [],
FucNAc: [],
// Di-deoxyhexose
- Oli: ['DDA'],
+ Oli: ['DDA', 'RAE', 'Z5J'],
Tyv: ['TYV'],
Abe: ['ABE'],
Par: ['PZU'],
- Dig: [],
+ Dig: ['Z3U'],
Col: [],
// Pentose
- Ara: ['ARA', 'ARB'],
- Lyx: ['LDY'],
- Xyl: ['XYS', 'XYP'],
- Rib: ['RIP', '0MK'],
+ Ara: ['ARA', 'ARB', 'AHR', 'FUB'],
+ Lyx: ['LDY', 'Z4W'],
+ Xyl: ['XZS', 'XYP', 'XYZ'],
+ Rib: ['YYM', 'RIP', 'RIB', 'BDR'],
// Deoxynonulosonate
- Kdn: ['KDN', 'KDM'],
+ Kdn: ['KDM', 'KDN'],
Neu5Ac: ['SIA', 'SLB'],
Neu5Gc: ['NGC', 'NGE'],
Neu: [],
Sia: [],
// Di-deoxynonulosonate
- Pse: ['6PZ'],
+ Pse: [],
Leg: [],
Aci: [],
'4eLeg': [],
// Unknown
- Bac: ['B6D'],
+ Bac: [],
LDManHep: ['GMH'],
Kdo: ['KDO'],
Dha: [],
- DDManHep: [],
- MurNAc: ['AMU'],
+ DDManHep: ['289'],
+ MurNAc: ['MUB', 'AMU'],
MurNGc: [],
- Mur: ['MUR'],
+ Mur: ['1S4', 'MUR'],
// Assigned
Api: ['XXM'],
- Fru: ['BDF'],
+ Fru: ['BDF', 'Z9N', 'FRU'],
Tag: ['T6T'],
Sor: ['SOE'],
- Psi: [],
+ Psi: ['PSV'],
+ // Generic
+ Hexose: [],
+ HexNAc: [],
+ Hexosamine: [],
+ Hexuronate: [],
+ Deoxyhexose: [],
+ DeoxyhexNAc: [],
+ 'Di-deoxyhexose': [],
+ Pentose: [],
+ Deoxynonulosonate: [],
+ 'Di-deoxynonulosonate': [],
+ Unknown: [],
+ Assigned: ['PUF'],
}
const UnknownSaccharideNames = [
diff --git a/src/mol-plugin/util/structure-selection-helper.ts b/src/mol-plugin/util/structure-selection-helper.ts
index a3416b0e4b812902e75d52d3f77586c7516018f4..1a221e6b715086f4098b0bad5f891df4eefff036 100644
--- a/src/mol-plugin/util/structure-selection-helper.ts
+++ b/src/mol-plugin/util/structure-selection-helper.ts
@@ -114,8 +114,11 @@ const branchedConnectedOnly = MS.struct.modifier.union([
const ligand = MS.struct.modifier.union([
MS.struct.generator.atomGroups({
'entity-test': MS.core.logic.and([
- MS.core.rel.neq([MS.ammp('entityType'), 'branched']),
- MS.core.rel.eq([MS.ammp('entityType'), 'non-polymer'])
+ MS.core.rel.eq([MS.ammp('entityType'), 'non-polymer']),
+ MS.core.logic.not([MS.core.str.match([
+ MS.re('oligosaccharide', 'i'),
+ MS.ammp('entitySubtype')
+ ])])
]),
'chain-test': MS.core.rel.eq([MS.ammp('objectPrimitive'), 'atomistic']),
'residue-test': MS.core.logic.not([