Merge branch 'master' of https://github.com/molstar/molstar

src/mol-io/reader/cif/schema/bird.ts

@@ -1,7 +1,7 @@
 /**
  * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.318, IHM 1.04, CARB draft.
+ * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.320, IHM 1.05, CARB draft.
  *
  * @author molstar/ciftools package
  */

src/mol-io/reader/cif/schema/ccd.ts

@@ -1,7 +1,7 @@
 /**
  * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.318, IHM 1.04, CARB draft.
+ * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.320, IHM 1.05, CARB draft.
  *
  * @author molstar/ciftools package
  */
@@ -103,7 +103,7 @@ export const CCD_Schema = {
          * linking monomers, monomers with some type of N-terminal (or 5')
          * cap and monomers with some type of C-terminal (or 3') cap.
          */
-        type: Aliased<'D-peptide linking' | 'L-peptide linking' | 'D-peptide NH3 amino terminus' | 'L-peptide NH3 amino terminus' | 'D-peptide COOH carboxy terminus' | 'L-peptide COOH carboxy terminus' | 'DNA linking' | 'RNA linking' | 'L-RNA linking' | 'L-DNA linking' | 'DNA OH 5 prime terminus' | 'RNA OH 5 prime terminus' | 'DNA OH 3 prime terminus' | 'RNA OH 3 prime terminus' | 'D-saccharide 1,4 and 1,4 linking' | 'L-saccharide 1,4 and 1,4 linking' | 'D-saccharide 1,4 and 1,6 linking' | 'L-saccharide 1,4 and 1,6 linking' | 'L-saccharide' | 'D-saccharide' | 'saccharide' | 'non-polymer' | 'peptide linking' | 'peptide-like' | 'L-gamma-peptide, C-delta linking' | 'D-gamma-peptide, C-delta linking' | 'L-beta-peptide, C-gamma linking' | 'D-beta-peptide, C-gamma linking' | 'other'>(str),
+        type: Aliased<'D-peptide linking' | 'L-peptide linking' | 'D-peptide NH3 amino terminus' | 'L-peptide NH3 amino terminus' | 'D-peptide COOH carboxy terminus' | 'L-peptide COOH carboxy terminus' | 'DNA linking' | 'RNA linking' | 'L-RNA linking' | 'L-DNA linking' | 'DNA OH 5 prime terminus' | 'RNA OH 5 prime terminus' | 'DNA OH 3 prime terminus' | 'RNA OH 3 prime terminus' | 'D-saccharide 1,4 and 1,4 linking' | 'L-saccharide 1,4 and 1,4 linking' | 'D-saccharide 1,4 and 1,6 linking' | 'L-saccharide 1,4 and 1,6 linking' | 'D-saccharide, beta linking' | 'D-saccharide, alpha linking' | 'L-saccharide, beta linking' | 'L-saccharide, alpha linking' | 'L-saccharide' | 'D-saccharide' | 'saccharide' | 'non-polymer' | 'peptide linking' | 'peptide-like' | 'L-gamma-peptide, C-delta linking' | 'D-gamma-peptide, C-delta linking' | 'L-beta-peptide, C-gamma linking' | 'D-beta-peptide, C-gamma linking' | 'other'>(str),
         /**
          * Synonym list for the component.
          */
@@ -382,7 +382,7 @@ export const CCD_Schema = {
         /**
          * This data item contains the identifier type.
          */
-        type: Aliased<'COMMON NAME' | 'SYSTEMATIC NAME' | 'CAS REGISTRY NUMBER' | 'PUBCHEM Identifier' | 'MDL Identifier' | 'SYNONYM' | 'CONDENSED IUPAC CARB SYMBOL' | 'IUPAC CARB SYMBOL' | 'SNFG CARB SYMBOL'>(str),
+        type: Aliased<'COMMON NAME' | 'SYSTEMATIC NAME' | 'CAS REGISTRY NUMBER' | 'PUBCHEM Identifier' | 'MDL Identifier' | 'SYNONYM' | 'CONDENSED IUPAC CARB SYMBOL' | 'IUPAC CARB SYMBOL' | 'SNFG CARB SYMBOL' | 'CONDENSED IUPAC CARBOHYDRATE SYMBOL' | 'IUPAC CARBOHYDRATE SYMBOL' | 'SNFG CARBOHYDRATE SYMBOL'>(str),
         /**
          * This data item contains the name of the program
          * or library used to compute the identifier.

src/mol-io/reader/cif/schema/mmcif.ts

@@ -1,7 +1,7 @@
 /**
  * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.318, IHM 1.04, CARB draft.
+ * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.320, IHM 1.05, CARB draft.
  *
  * @author molstar/ciftools package
  */
@@ -492,7 +492,7 @@ export const mmCIF_Schema = {
          * linking monomers, monomers with some type of N-terminal (or 5')
          * cap and monomers with some type of C-terminal (or 3') cap.
          */
-        type: Aliased<'D-peptide linking' | 'L-peptide linking' | 'D-peptide NH3 amino terminus' | 'L-peptide NH3 amino terminus' | 'D-peptide COOH carboxy terminus' | 'L-peptide COOH carboxy terminus' | 'DNA linking' | 'RNA linking' | 'L-RNA linking' | 'L-DNA linking' | 'DNA OH 5 prime terminus' | 'RNA OH 5 prime terminus' | 'DNA OH 3 prime terminus' | 'RNA OH 3 prime terminus' | 'D-saccharide 1,4 and 1,4 linking' | 'L-saccharide 1,4 and 1,4 linking' | 'D-saccharide 1,4 and 1,6 linking' | 'L-saccharide 1,4 and 1,6 linking' | 'L-saccharide' | 'D-saccharide' | 'saccharide' | 'non-polymer' | 'peptide linking' | 'peptide-like' | 'L-gamma-peptide, C-delta linking' | 'D-gamma-peptide, C-delta linking' | 'L-beta-peptide, C-gamma linking' | 'D-beta-peptide, C-gamma linking' | 'other'>(str),
+        type: Aliased<'D-peptide linking' | 'L-peptide linking' | 'D-peptide NH3 amino terminus' | 'L-peptide NH3 amino terminus' | 'D-peptide COOH carboxy terminus' | 'L-peptide COOH carboxy terminus' | 'DNA linking' | 'RNA linking' | 'L-RNA linking' | 'L-DNA linking' | 'DNA OH 5 prime terminus' | 'RNA OH 5 prime terminus' | 'DNA OH 3 prime terminus' | 'RNA OH 3 prime terminus' | 'D-saccharide 1,4 and 1,4 linking' | 'L-saccharide 1,4 and 1,4 linking' | 'D-saccharide 1,4 and 1,6 linking' | 'L-saccharide 1,4 and 1,6 linking' | 'D-saccharide, beta linking' | 'D-saccharide, alpha linking' | 'L-saccharide, beta linking' | 'L-saccharide, alpha linking' | 'L-saccharide' | 'D-saccharide' | 'saccharide' | 'non-polymer' | 'peptide linking' | 'peptide-like' | 'L-gamma-peptide, C-delta linking' | 'D-gamma-peptide, C-delta linking' | 'L-beta-peptide, C-gamma linking' | 'D-beta-peptide, C-gamma linking' | 'other'>(str),
         /**
          * Synonym list for the component.
          */
@@ -1898,7 +1898,7 @@ export const mmCIF_Schema = {
         /**
          * This data item contains the identifier type.
          */
-        type: Aliased<'COMMON NAME' | 'SYSTEMATIC NAME' | 'CAS REGISTRY NUMBER' | 'PUBCHEM Identifier' | 'MDL Identifier' | 'SYNONYM' | 'CONDENSED IUPAC CARB SYMBOL' | 'IUPAC CARB SYMBOL' | 'SNFG CARB SYMBOL'>(str),
+        type: Aliased<'COMMON NAME' | 'SYSTEMATIC NAME' | 'CAS REGISTRY NUMBER' | 'PUBCHEM Identifier' | 'MDL Identifier' | 'SYNONYM' | 'CONDENSED IUPAC CARB SYMBOL' | 'IUPAC CARB SYMBOL' | 'SNFG CARB SYMBOL' | 'CONDENSED IUPAC CARBOHYDRATE SYMBOL' | 'IUPAC CARBOHYDRATE SYMBOL' | 'SNFG CARBOHYDRATE SYMBOL'>(str),
         /**
          * This data item contains the name of the program
          * or library used to compute the identifier.
@@ -3665,7 +3665,7 @@ export const mmCIF_Schema = {
         /**
          * The type of crosslinker used.
          */
-        linker_type: Aliased<'EDC' | 'DSS' | 'EGS' | 'BS3' | 'BS2G' | 'DST' | 'sulfo-SDA' | 'sulfo-SMCC' | 'DSSO' | 'DSG' | 'BSP' | 'Other'>(str),
+        linker_type: Aliased<'EDC' | 'DSS' | 'EGS' | 'BS3' | 'BS2G' | 'DST' | 'sulfo-SDA' | 'sulfo-SMCC' | 'DSSO' | 'DSG' | 'BSP' | 'BMSO' | 'DHSO' | 'Other'>(str),
         /**
          * Identifier to the crosslinking dataset.
          * This data item is a pointer to the _ihm_dataset_list.id in the

src/mol-model-formats/structure/mmcif/parser.ts

@@ -156,11 +156,13 @@ function getSaccharideComponentMap(format: mmCIF_Format): SaccharideComponentMap
 
     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
+        // a 'SNFG CARBOHYDRATE 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') {
+            if (type.value(i) === 'SNFG CARBOHYDRATE SYMBOL' ||
+                type.value(i) === 'SNFG CARB SYMBOL' // legacy, to be removed from mmCIF dictionary
+            ) {
                 const snfgName = identifier.value(i)
                 const saccharideComp = SaccharidesSnfgMap.get(snfgName)
                 if (saccharideComp) {

src/mol-model/loci.ts

@@ -12,7 +12,7 @@ import { CentroidHelper } from '../mol-math/geometry/centroid-helper';
 import { Vec3 } from '../mol-math/linear-algebra';
 import { OrderedSet } from '../mol-data/int';
 import { Structure } from './structure/structure';
-import { capitalize } from '../mol-util/string';
+import { stringToWords } from '../mol-util/string';
 import { PrincipalAxes } from '../mol-math/linear-algebra/matrix/principal-axes';
 
 /** A Loci that includes every loci */
@@ -194,6 +194,21 @@ namespace Loci {
                 ? StructureElement.Loci.extendToWholeChains(loci)
                 : loci
         },
+        'elementInstances': (loci: Loci) => {
+            return StructureElement.Loci.is(loci)
+                ? StructureElement.Loci.extendToAllInstances(loci)
+                : loci
+        },
+        'residueInstances': (loci: Loci) => {
+            return StructureElement.Loci.is(loci)
+                ? StructureElement.Loci.extendToAllInstances(StructureElement.Loci.extendToWholeResidues(loci, true))
+                : loci
+        },
+        'chainInstances': (loci: Loci) => {
+            return StructureElement.Loci.is(loci)
+                ? StructureElement.Loci.extendToAllInstances(StructureElement.Loci.extendToWholeChains(loci))
+                : loci
+        },
         'entity': (loci: Loci) => {
             return StructureElement.Loci.is(loci)
                 ? StructureElement.Loci.extendToWholeEntities(loci)
@@ -211,7 +226,7 @@ namespace Loci {
         }
     }
     export type Granularity = keyof typeof Granularity
-    export const GranularityOptions = Object.keys(Granularity).map(n => [n, capitalize(n)]) as [Granularity, string][]
+    export const GranularityOptions = Object.keys(Granularity).map(n => [n, stringToWords(n)]) as [Granularity, string][]
 
     export function applyGranularity(loci: Loci, granularity: Granularity) {
         return Granularity[granularity](loci)

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

@@ -200,9 +200,12 @@ export const RNAComponentTypeNames = new Set([
 
 /** Chemical component type names for saccharide */
 export const SaccharideComponentTypeNames = new Set([
+    'D-SACCHARIDE, BETA LINKING', 'L-SACCHARIDE, BETA LINKING',
+    'D-SACCHARIDE, ALPHA LINKING', 'L-SACCHARIDE, ALPHA LINKING',
+    'L-SACCHARIDE', 'D-SACCHARIDE', 'SACCHARIDE',
+    // the following four are marked to be deprecated in the mmCIF dictionary
     'D-SACCHARIDE 1,4 AND 1,4 LINKING', 'L-SACCHARIDE 1,4 AND 1,4 LINKING',
-    'D-SACCHARIDE 1,4 AND 1,6 LINKING', 'L-SACCHARIDE 1,4 AND 1,6 LINKING', 'L-SACCHARIDE',
-    'D-SACCHARIDE', 'SACCHARIDE',
+    'D-SACCHARIDE 1,4 AND 1,6 LINKING', 'L-SACCHARIDE 1,4 AND 1,6 LINKING',
 ])
 
 /** Chemical component type names for other */

src/mol-model/structure/structure/element/loci.ts

@@ -410,6 +410,31 @@ export namespace Loci {
         return Loci(loci.structure, elements)
     }
 
+    export function extendToAllInstances(loci: Loci): Loci {
+        const elements: Loci['elements'][0][] = [];
+        const byInvariantId = new Map<number, OrderedSet<UnitIndex>>()
+        const { unitSymmetryGroups, unitSymmetryGroupsIndexMap } = loci.structure
+
+        for (let i = 0, len = loci.elements.length; i < len; i++) {
+            const e = loci.elements[i]
+            const { invariantId } = e.unit
+            if (byInvariantId.has(invariantId)) {
+                byInvariantId.set(invariantId, OrderedSet.union(e.indices, byInvariantId.get(invariantId)!))
+            } else {
+                byInvariantId.set(invariantId, e.indices)
+            }
+        }
+
+        byInvariantId.forEach((indices, invariantId) => {
+            const { units } = unitSymmetryGroups[unitSymmetryGroupsIndexMap.get(invariantId)]
+            for (let i = 0, il = units.length; i < il; ++i) {
+                elements[elements.length] = { unit: units[i], indices }
+            }
+        })
+
+        return Loci(loci.structure, elements);
+    }
+
     //
 
     const boundaryHelper = new BoundaryHelper();

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

@@ -43,6 +43,7 @@ class Structure {
         links?: InterUnitBonds,
         crossLinkRestraints?: PairRestraints<CrossLinkRestraint>,
         unitSymmetryGroups?: ReadonlyArray<Unit.SymmetryGroup>,
+        unitSymmetryGroupsIndexMap?: IntMap<number>,
         carbohydrates?: Carbohydrates,
         models?: ReadonlyArray<Model>,
         model?: Model,
@@ -217,6 +218,13 @@ class Structure {
         return this._props.unitSymmetryGroups;
     }
 
+    /** Maps unit.invariantId to index of SymmetryGroup in unitSymmetryGroups array */
+    get unitSymmetryGroupsIndexMap(): IntMap<number> {
+        if (this._props.unitSymmetryGroupsIndexMap) return this._props.unitSymmetryGroupsIndexMap;
+        this._props.unitSymmetryGroupsIndexMap = Unit.SymmetryGroup.getUnitSymmetryGroupsIndexMap(this.unitSymmetryGroups);
+        return this._props.unitSymmetryGroupsIndexMap;
+    }
+
     get carbohydrates(): Carbohydrates {
         if (this._props.carbohydrates) return this._props.carbohydrates;
         this._props.carbohydrates = computeCarbohydrates(this);

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

@@ -86,6 +86,14 @@ namespace Unit {
             if (a.hashCode !== b.hashCode) return false;
             return SortedArray.areEqual(a.elements, b.elements);
         }
+
+        export function getUnitSymmetryGroupsIndexMap(symmetryGroups: ReadonlyArray<Unit.SymmetryGroup>): IntMap<number> {
+            const unitSymmetryGroupsIndexMap = IntMap.Mutable<number>();
+            for (let i = 0, _i = symmetryGroups.length; i < _i; i++) {
+                unitSymmetryGroupsIndexMap.set(symmetryGroups[i].units[0].invariantId, i);
+            }
+            return unitSymmetryGroupsIndexMap
+        }
     }
 
     export function conformationId (unit: Unit) {