Merge pull request #606 from jpattle/remove-caps-from-ligand-query

Remove common protein caps from ligand query

CHANGELOG.md

@@ -5,6 +5,7 @@ Note that since we don't clearly distinguish between a public and private interf
 
 
 ## [Unreleased]
+- Excluded common protein caps `NME` and `ACE` from the ligand selection query
 
 ## [v3.25.1] - 2022-11-20
 

package.json

@@ -92,7 +92,8 @@
     "Panagiotis Tourlas <panagiot_tourlov@hotmail.com>",
     "Adam Midlik <midlik@gmail.com>",
     "Koya Sakuma <koya.sakuma.work@gmail.com>",
-    "Gianluca Tomasello <giagitom@gmail.com>"
+    "Gianluca Tomasello <giagitom@gmail.com>",
+    "Jason Pattle <jpattle@exscientia.co.uk>"
   ],
   "license": "MIT",
   "devDependencies": {

src/mol-model/structure/model/types.ts

@@ -285,6 +285,10 @@ export const AminoAcidNamesD = new Set([
 ]);
 export const AminoAcidNames = SetUtils.unionMany(AminoAcidNamesL, AminoAcidNamesD);
 
+export const CommonProteinCaps = new Set([
+    'NME', 'ACE'
+]);
+
 export const RnaBaseNames = new Set([
     'A', 'C', 'T', 'G', 'I', 'U',
     'N' // unknown RNA base from CCD

src/mol-plugin-state/helpers/structure-selection-query.ts

@@ -7,7 +7,7 @@
 
 import { CustomProperty } from '../../mol-model-props/common/custom-property';
 import { QueryContext, Structure, StructureQuery, StructureSelection, StructureProperties, StructureElement } from '../../mol-model/structure';
-import { BondType, NucleicBackboneAtoms, ProteinBackboneAtoms, SecondaryStructureType, AminoAcidNamesL, RnaBaseNames, DnaBaseNames, WaterNames, ElementSymbol, PolymerNames } from '../../mol-model/structure/model/types';
+import { BondType, NucleicBackboneAtoms, ProteinBackboneAtoms, SecondaryStructureType, AminoAcidNamesL, RnaBaseNames, DnaBaseNames, WaterNames, ElementSymbol, PolymerNames, CommonProteinCaps } from '../../mol-model/structure/model/types';
 import { PluginContext } from '../../mol-plugin/context';
 import { MolScriptBuilder as MS } from '../../mol-script/language/builder';
 import { Expression } from '../../mol-script/language/expression';
@@ -350,14 +350,23 @@ const ligand = StructureSelectionQuery('Ligand', MS.struct.modifier.union([
                 ])
             ]),
         ]),
-        by: MS.struct.modifier.union([
+        by: MS.struct.combinator.merge([
+            MS.struct.modifier.union([
+                MS.struct.generator.atomGroups({
+                    'entity-test': MS.core.rel.eq([MS.ammp('entityType'), 'polymer']),
+                    'chain-test': MS.core.rel.eq([MS.ammp('objectPrimitive'), 'atomistic']),
+                    'residue-test': MS.core.set.has([
+                        MS.set(...SetUtils.toArray(PolymerNames)), MS.ammp('label_comp_id')
+                    ])
+                }),
+            ]),
             MS.struct.generator.atomGroups({
-                'entity-test': MS.core.rel.eq([MS.ammp('entityType'), 'polymer']),
                 'chain-test': MS.core.rel.eq([MS.ammp('objectPrimitive'), 'atomistic']),
                 'residue-test': MS.core.set.has([
-                    MS.set(...SetUtils.toArray(PolymerNames)), MS.ammp('label_comp_id')
-                ])
-            })
+                    MS.set(...SetUtils.toArray(CommonProteinCaps)),
+                    MS.ammp('label_comp_id'),
+                ]),
+            }),
         ])
     })
 ]), { category: StructureSelectionCategory.Type });