avoid standard polymers misqualified as ligands

- overrule erroneous chem comp type in some files

docs/interesting-pdb-entries.md

@@ -29,6 +29,11 @@
 * Long linear sugar chain (4HG6)
 * Anisotropic B-factors/Ellipsoids (1EJG)
 * NOS bridges (LYS-CSO in 7B0L, 6ZWJ, 6ZWH)
+* Non-polymer components in polymer entities
+    * PN2 in 1F80
+    * ACE (many, e.g. 5AGU, 1E1X)
+    * ACY in 7ABY
+    * NH2 (many, e.g. 6Y13)
 
 Assembly symmetries
 * 5M30 (Assembly 1, C3 local and pseudo)

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

@@ -321,6 +321,12 @@ export function getMoleculeType(compType: string, compId: string): MoleculeType
         if (SaccharideCompIdMap.has(compId)) {
             // trust our saccharide table more than given 'non-polymer' or 'other' component type
             return MoleculeType.Saccharide;
+        } else if (AminoAcidNames.has(compId)) {
+            return MoleculeType.Protein;
+        } else if (RnaBaseNames.has(compId)) {
+            return MoleculeType.RNA;
+        } else if (DnaBaseNames.has(compId)) {
+            return MoleculeType.DNA;
         } else {
             return MoleculeType.Other;
         }

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 } from '../../mol-model/structure/model/types';
+import { BondType, NucleicBackboneAtoms, ProteinBackboneAtoms, SecondaryStructureType, AminoAcidNamesL, RnaBaseNames, DnaBaseNames, WaterNames, ElementSymbol, PolymerNames } 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';
@@ -320,33 +320,46 @@ const branchedConnectedOnly = StructureSelectionQuery('Connected to Carbohydrate
 ]), { category: StructureSelectionCategory.Internal, isHidden: true });
 
 const ligand = StructureSelectionQuery('Ligand', MS.struct.modifier.union([
-    MS.struct.combinator.merge([
-        MS.struct.modifier.union([
-            MS.struct.generator.atomGroups({
-                'entity-test': MS.core.logic.and([
-                    MS.core.logic.or([
-                        MS.core.rel.eq([MS.ammp('entityType'), 'non-polymer']),
-                        MS.core.rel.neq([MS.ammp('entityPrdId'), ''])
-                    ]),
-                    MS.core.logic.not([MS.core.str.match([
-                        MS.re('(oligosaccharide|lipid|ion)', 'i'),
-                        MS.ammp('entitySubtype')
-                    ])])
+    MS.struct.modifier.exceptBy({
+        0: MS.struct.modifier.union([
+            MS.struct.combinator.merge([
+                MS.struct.modifier.union([
+                    MS.struct.generator.atomGroups({
+                        'entity-test': MS.core.logic.and([
+                            MS.core.logic.or([
+                                MS.core.rel.eq([MS.ammp('entityType'), 'non-polymer']),
+                                MS.core.rel.neq([MS.ammp('entityPrdId'), ''])
+                            ]),
+                            MS.core.logic.not([MS.core.str.match([
+                                MS.re('(oligosaccharide|lipid|ion)', 'i'),
+                                MS.ammp('entitySubtype')
+                            ])])
+                        ]),
+                        'chain-test': MS.core.rel.eq([MS.ammp('objectPrimitive'), 'atomistic']),
+                        'residue-test': MS.core.logic.not([
+                            MS.core.str.match([MS.re('saccharide', 'i'), MS.ammp('chemCompType')])
+                        ])
+                    })
                 ]),
-                'chain-test': MS.core.rel.eq([MS.ammp('objectPrimitive'), 'atomistic']),
-                'residue-test': MS.core.logic.not([
-                    MS.core.str.match([MS.re('saccharide', 'i'), MS.ammp('chemCompType')])
+                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': _nonPolymerResidueTest
+                    })
                 ])
-            })
+            ]),
         ]),
-        MS.struct.modifier.union([
+        by: 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': _nonPolymerResidueTest
+                'residue-test': MS.core.set.has([
+                    MS.set(...SetUtils.toArray(PolymerNames)), MS.ammp('label_comp_id')
+                ])
             })
         ])
-    ]),
+    })
 ]), { category: StructureSelectionCategory.Type });
 
 // don't include branched entities as they have their own link representation