Merge pull request #414 from molstar/lowercase-str-column

lowercase column schema

CHANGELOG.md

@@ -13,6 +13,7 @@ Note that since we don't clearly distinguish between a public and private interf
 - Improve pdb parsing: handle non unique atom and chain names (fixes #156)
 - Fix volume streaming for entries with multiple contour lists
 - Add ``allowTransparentBackfaces`` parameter to support double-sided rendering of transparent geometries
+- Fix handling of case insensitive mmCIF enumeration fields (including entity.type)
 - Fix ``disable-wboit`` Viewer GET param
 
 ## [v3.5.0] - 2022-03-25

src/cli/cifschema/util/cif-dic.ts

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
  */
@@ -13,15 +13,17 @@ export function getFieldType(type: string, description: string, values?: string[
     switch (type) {
         // mmCIF
         case 'code':
-        case 'ucode':
         case 'line':
-        case 'uline':
         case 'text':
         case 'char':
-        case 'uchar3':
-        case 'uchar1':
         case 'boolean':
             return values && values.length ? EnumCol(values, 'str', description) : StrCol(description);
+        case 'ucode':
+        case 'uline':
+        case 'uchar3':
+        case 'uchar1':
+            // only force lower-case for enums
+            return values && values.length ? EnumCol(values.map(x => x.toLowerCase()), 'lstr', description) : StrCol(description);
         case 'aliasname':
         case 'name':
         case 'idname':

src/cli/cifschema/util/generate.ts

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
  */
@@ -10,7 +10,7 @@ import { FieldPath } from '../../../mol-io/reader/cif/schema';
 
 function header(name: string, info: string, moldataImportPath: string) {
     return `/**
- * Copyright (c) 2017-2020 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * Code-generated '${name}' schema file. ${info}
  *
@@ -35,13 +35,17 @@ function getTypeShorthands(schema: Database, fields?: Filter) {
         const { columns } = schema.tables[table];
         Object.keys(columns).forEach(columnName => {
             if (fields && !fields[table][columnName]) return;
-            types.add(schema.tables[table].columns[columnName].type);
+            const col = schema.tables[table].columns[columnName];
+            if (col.type === 'enum') types.add(col.subType);
+            types.add(col.type);
         });
     });
     const shorthands: string[] = [];
     types.forEach(type => {
         switch (type) {
             case 'str': shorthands.push('const str = Schema.str;'); break;
+            case 'ustr': shorthands.push('const ustr = Schema.ustr;'); break;
+            case 'lstr': shorthands.push('const lstr = Schema.lstr;'); break;
             case 'int': shorthands.push('const int = Schema.int;'); break;
             case 'float': shorthands.push('const float = Schema.float;'); break;
             case 'coord': shorthands.push('const coord = Schema.coord;'); break;

src/cli/cifschema/util/schema.ts

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
  */
@@ -29,8 +29,8 @@ export function FloatCol(description: string): FloatCol { return { type: 'float'
 export type CoordCol = { type: 'coord' } & BaseCol
 export function CoordCol(description: string): CoordCol { return { type: 'coord', description }; }
 
-export type EnumCol = { type: 'enum', subType: 'int' | 'str', values: string[] } & BaseCol
-export function EnumCol(values: string[], subType: 'int' | 'str', description: string): EnumCol {
+export type EnumCol = { type: 'enum', subType: 'int' | 'str' | 'ustr' | 'lstr', values: string[] } & BaseCol
+export function EnumCol(values: string[], subType: 'int' | 'str' | 'ustr' | 'lstr', description: string): EnumCol {
     return { type: 'enum', description, values, subType };
 }
 

src/mol-data/db/_spec/table.spec.ts

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author David Sehnal <david.sehnal@gmail.com>
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -61,6 +61,29 @@ describe('column', () => {
     });
 });
 
+describe('string column', () => {
+    const xs = ['A', 'b', null, undefined];
+    const xsArr = xs.map(x => x ?? '');
+    const xsLC = xs.map(x => (x ?? '').toLowerCase());
+    const arr = Column.ofArray({ array: xs as any, schema: Column.Schema.str });
+    const arrLC = Column.ofArray({ array: xs as any, schema: Column.Schema.Str({ transform: 'lowercase' }) });
+    const aliasedLC = Column.ofArray({ array: xs as any, schema: Column.Schema.Aliased<'a' | 'b'>(Column.Schema.lstr) });
+
+    it('value', () => {
+        for (let i = 0; i < xs.length; i++) {
+            expect(arr.value(i)).toBe(xs[i] ?? '');
+            expect(arrLC.value(i)).toBe(xsLC[i] ?? '');
+            expect(aliasedLC.value(i)).toBe(xsLC[i]);
+        }
+    });
+
+    it('array', () => {
+        expect(arr.toArray()).toEqual(xsArr);
+        expect(arrLC.toArray()).toEqual(xsLC);
+        expect(aliasedLC.toArray()).toEqual(xsLC);
+    });
+});
+
 describe('table', () => {
     const schema = {
         x: Column.Schema.int,

src/mol-data/db/column.ts

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author David Sehnal <david.sehnal@gmail.com>
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -25,38 +25,39 @@ interface Column<T> {
 namespace Column {
     export type ArrayCtor<T> = { new(size: number): ArrayLike<T> }
 
-    export type Schema<T = any> = Schema.Str | Schema.Int | Schema.Float | Schema.Coordinate | Schema.Aliased<T> | Schema.Tensor | Schema.List<number|string>
+    export type Schema<T = any> = Schema.Str | Schema.Int | Schema.Float | Schema.Coordinate | Schema.Aliased<T> | Schema.Tensor | Schema.List<number | string>
 
     export namespace Schema {
         // T also serves as a default value for undefined columns
 
         type Base<T extends string> = { valueType: T }
-        export type Str = { '@type': 'str', T: string } & Base<'str'>
+        export type Str = { '@type': 'str', T: string, transform?: 'uppercase' | 'lowercase' } & Base<'str'>
         export type Int = { '@type': 'int', T: number } & Base<'int'>
         export type Float = { '@type': 'float', T: number } & Base<'float'>
         export type Coordinate = { '@type': 'coord', T: number } & Base<'float'>
 
         export type Tensor = { '@type': 'tensor', T: Tensors.Data, space: Tensors.Space, baseType: Int | Float } & Base<'tensor'>
-        export type Aliased<T> = { '@type': 'aliased', T: T } & Base<T extends string ? 'str' : 'int'>
-        export type List<T extends number|string> = { '@type': 'list', T: T[], separator: string, itemParse: (x: string) => T } & Base<'list'>
+        export type Aliased<T> = { '@type': 'aliased', T: T, transform?: T extends string ? 'uppercase' | 'lowercase' : never } & Base<T extends string ? 'str' : 'int'>
+        export type List<T extends number | string> = { '@type': 'list', T: T[], separator: string, itemParse: (x: string) => T } & Base<'list'>
 
         export const str: Str = { '@type': 'str', T: '', valueType: 'str' };
+        export const ustr: Str = { '@type': 'str', T: '', valueType: 'str', transform: 'uppercase' };
+        export const lstr: Str = { '@type': 'str', T: '', valueType: 'str', transform: 'lowercase' };
         export const int: Int = { '@type': 'int', T: 0, valueType: 'int' };
         export const coord: Coordinate = { '@type': 'coord', T: 0, valueType: 'float' };
         export const float: Float = { '@type': 'float', T: 0, valueType: 'float' };
 
-        export function Str(defaultValue = ''): Str { return { '@type': 'str', T: defaultValue, valueType: 'str' }; };
+        export function Str(options?: { defaultValue?: string, transform?: 'uppercase' | 'lowercase' }): Str { return { '@type': 'str', T: options?.defaultValue ?? '', transform: options?.transform, valueType: 'str' }; };
         export function Int(defaultValue = 0): Int { return { '@type': 'int', T: defaultValue, valueType: 'int' }; };
         export function Float(defaultValue = 0): Float { return { '@type': 'float', T: defaultValue, valueType: 'float' }; };
         export function Tensor(space: Tensors.Space, baseType: Int | Float = float): Tensor { return { '@type': 'tensor', T: space.create(), space, valueType: 'tensor', baseType }; }
         export function Vector(dim: number, baseType: Int | Float = float): Tensor { return Tensor(Tensors.Vector(dim, baseType['@type'] === 'int' ? Int32Array : Float64Array), baseType); }
         export function Matrix(rows: number, cols: number, baseType: Int | Float = float): Tensor { return Tensor(Tensors.ColumnMajorMatrix(rows, cols, baseType['@type'] === 'int' ? Int32Array : Float64Array), baseType); }
 
-        export function Aliased<T>(t: Str | Int, defaultValue?: T): Aliased<T> {
-            if (typeof defaultValue !== 'undefined') return { ...t, T: defaultValue } as any as Aliased<T>;
+        export function Aliased<T>(t: Str | Int): Aliased<T> {
             return t as any as Aliased<T>;
         }
-        export function List<T extends number|string>(separator: string, itemParse: (x: string) => T, defaultValue: T[] = []): List<T> {
+        export function List<T extends number | string>(separator: string, itemParse: (x: string) => T, defaultValue: T[] = []): List<T> {
             return { '@type': 'list', T: defaultValue, separator, itemParse, valueType: 'list' };
         }
     }
@@ -287,8 +288,13 @@ function lambdaColumn<T extends Column.Schema>({ value, valueKind, areValuesEqua
 
 function arrayColumn<T extends Column.Schema>({ array, schema, valueKind }: Column.ArraySpec<T>): Column<T['T']> {
     const rowCount = array.length;
+    const defaultValue = schema.T;
     const value: Column<T['T']>['value'] = schema.valueType === 'str'
-        ? row => { const v = array[row]; return typeof v === 'string' ? v : '' + v; }
+        ? (schema as Column.Schema.Str).transform === 'lowercase'
+            ? row => { const v = array[row]; return typeof v === 'string' ? v.toLowerCase() : `${v ?? defaultValue}`.toLowerCase(); }
+            : (schema as Column.Schema.Str).transform === 'uppercase'
+                ? row => { const v = array[row]; return typeof v === 'string' ? v.toUpperCase() : `${v ?? defaultValue}`.toUpperCase(); }
+                : row => { const v = array[row]; return typeof v === 'string' ? v : `${v ?? defaultValue}`; }
         : row => array[row];
 
     const isTyped = ColumnHelpers.isTypedArray(array);
@@ -300,15 +306,35 @@ function arrayColumn<T extends Column.Schema>({ array, schema, valueKind }: Colu
         value,
         valueKind: valueKind ? valueKind : row => Column.ValueKind.Present,
         toArray: schema.valueType === 'str'
-            ? params => {
-                const { start, end } = ColumnHelpers.getArrayBounds(rowCount, params);
-                const ret = new (params && typeof params.array !== 'undefined' ? params.array : (array as any).constructor)(end - start) as any;
-                for (let i = 0, _i = end - start; i < _i; i++) {
-                    const v = array[start + i];
-                    ret[i] = typeof v === 'string' ? v : '' + v;
+            ? (schema as Column.Schema.Str).transform === 'lowercase'
+                ? params => {
+                    const { start, end } = ColumnHelpers.getArrayBounds(rowCount, params);
+                    const ret = new (params && typeof params.array !== 'undefined' ? params.array : (array as any).constructor)(end - start) as any;
+                    for (let i = 0, _i = end - start; i < _i; i++) {
+                        const v = array[start + i];
+                        ret[i] = typeof v === 'string' ? v.toLowerCase() : `${v ?? defaultValue}`.toLowerCase();
+                    }
+                    return ret;
                 }
-                return ret;
-            }
+                : (schema as Column.Schema.Str).transform === 'uppercase'
+                    ? params => {
+                        const { start, end } = ColumnHelpers.getArrayBounds(rowCount, params);
+                        const ret = new (params && typeof params.array !== 'undefined' ? params.array : (array as any).constructor)(end - start) as any;
+                        for (let i = 0, _i = end - start; i < _i; i++) {
+                            const v = array[start + i];
+                            ret[i] = typeof v === 'string' ? v.toUpperCase() : `${v ?? defaultValue}`.toUpperCase();
+                        }
+                        return ret;
+                    }
+                    : params => {
+                        const { start, end } = ColumnHelpers.getArrayBounds(rowCount, params);
+                        const ret = new (params && typeof params.array !== 'undefined' ? params.array : (array as any).constructor)(end - start) as any;
+                        for (let i = 0, _i = end - start; i < _i; i++) {
+                            const v = array[start + i];
+                            ret[i] = typeof v === 'string' ? v : `${v ?? defaultValue}`;
+                        }
+                        return ret;
+                    }
             : isTyped
                 ? params => ColumnHelpers.typedArrayWindow(array, params) as any as ReadonlyArray<T>
                 : params => {

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

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2019 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author David Sehnal <david.sehnal@gmail.com>
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -45,7 +45,7 @@ type ColumnCtor = (field: Data.CifField, category: Data.CifCategory, key: string
 
 function getColumnCtor(t: Column.Schema): ColumnCtor {
     switch (t.valueType) {
-        case 'str': return (f, c, k) => createColumn(t, f, f.str, f.toStringArray);
+        case 'str': return (f, c, k) => createStringColumn(t, f, f.str, f.toStringArray);
         case 'int': return (f, c, k) => createColumn(t, f, f.int, f.toIntArray);
         case 'float': return (f, c, k) => createColumn(t, f, f.float, f.toFloatArray);
         case 'list': throw new Error('Use createListColumn instead.');
@@ -53,6 +53,27 @@ function getColumnCtor(t: Column.Schema): ColumnCtor {
     }
 }
 
+function createStringColumn<T extends string>(schema: Column.Schema.Str | Column.Schema.Aliased<T>, field: Data.CifField, value: (row: number) => T, toArray: Column<T>['toArray']): Column<T> {
+    return {
+        schema,
+        __array: field.__array,
+        isDefined: field.isDefined,
+        rowCount: field.rowCount,
+        value: schema.transform === 'lowercase'
+            ? row => value(row).toLowerCase() as T
+            : schema.transform === 'uppercase'
+                ? row => value(row).toUpperCase() as T
+                : value,
+        valueKind: field.valueKind,
+        areValuesEqual: field.areValuesEqual,
+        toArray: schema.transform === 'lowercase'
+            ? p => Array.from(toArray(p)).map(x => x.toLowerCase() as T)
+            : schema.transform === 'uppercase'
+                ? p => Array.from(toArray(p)).map(x => x.toUpperCase() as T)
+                : toArray,
+    };
+}
+
 function createColumn<T>(schema: Column.Schema, field: Data.CifField, value: (row: number) => T, toArray: Column<T>['toArray']): Column<T> {
     return {
         schema,

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

@@ -1,7 +1,7 @@
 /**
- * Copyright (c) 2017-2020 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.356, IHM 1.17, MA 1.3.5.
+ * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.357, IHM 1.17, MA 1.3.6.
  *
  * @author molstar/ciftools package
  */
@@ -12,6 +12,7 @@ import Schema = Column.Schema;
 
 const str = Schema.str;
 const float = Schema.float;
+const lstr = Schema.lstr;
 const Aliased = Schema.Aliased;
 const int = Schema.int;
 
@@ -58,7 +59,7 @@ export const BIRD_Schema = {
         /**
          * Defines the structural classification of the entity.
          */
-        type: Aliased<'Amino acid' | 'Aminoglycoside' | 'Anthracycline' | 'Anthraquinone' | 'Ansamycin' | 'Chalkophore' | 'Chromophore' | 'Glycopeptide' | 'Cyclic depsipeptide' | 'Cyclic lipopeptide' | 'Cyclic peptide' | 'Heterocyclic' | 'Imino sugar' | 'Keto acid' | 'Lipoglycopeptide' | 'Lipopeptide' | 'Macrolide' | 'Non-polymer' | 'Nucleoside' | 'Oligopeptide' | 'Oligosaccharide' | 'Peptaibol' | 'Peptide-like' | 'Polycyclic' | 'Polypeptide' | 'Polysaccharide' | 'Quinolone' | 'Thiolactone' | 'Thiopeptide' | 'Siderophore' | 'Unknown' | 'Chalkophore, Polypeptide'>(str),
+        type: Aliased<'amino acid' | 'aminoglycoside' | 'anthracycline' | 'anthraquinone' | 'ansamycin' | 'chalkophore' | 'chromophore' | 'glycopeptide' | 'cyclic depsipeptide' | 'cyclic lipopeptide' | 'cyclic peptide' | 'heterocyclic' | 'imino sugar' | 'keto acid' | 'lipoglycopeptide' | 'lipopeptide' | 'macrolide' | 'non-polymer' | 'nucleoside' | 'oligopeptide' | 'oligosaccharide' | 'peptaibol' | 'peptide-like' | 'polycyclic' | 'polypeptide' | 'polysaccharide' | 'quinolone' | 'thiolactone' | 'thiopeptide' | 'siderophore' | 'unknown' | 'chalkophore, polypeptide'>(lstr),
         /**
          * Evidence for the assignment of _pdbx_reference_molecule.type
          */
@@ -66,7 +67,7 @@ export const BIRD_Schema = {
         /**
          * Broadly defines the function of the entity.
          */
-        class: Aliased<'Antagonist' | 'Antibiotic' | 'Anticancer' | 'Anticoagulant' | 'Antifungal' | 'Antigen' | 'Antiinflammatory' | 'Antimicrobial' | 'Antineoplastic' | 'Antiparasitic' | 'Antiretroviral' | 'Anthelmintic' | 'Antithrombotic' | 'Antitumor' | 'Antiviral' | 'CASPASE inhibitor' | 'Chaperone binding' | 'Enzyme inhibitor' | 'Drug delivery' | 'Glycan component' | 'Growth factor' | 'Immunosuppressant' | 'Inducer' | 'Inhibitor' | 'Lantibiotic' | 'Metabolism' | 'Metal transport' | 'Nutrient' | 'Oxidation-reduction' | 'Protein binding' | 'Receptor' | 'Substrate analog' | 'Synthetic opioid' | 'Thrombin inhibitor' | 'Transition state mimetic' | 'Transport activator' | 'Trypsin inhibitor' | 'Toxin' | 'Unknown' | 'Water retention' | 'Anticoagulant, Antithrombotic' | 'Antibiotic, Antimicrobial' | 'Antibiotic, Anthelmintic' | 'Antibiotic, Antineoplastic' | 'Antimicrobial, Antiretroviral' | 'Antimicrobial, Antitumor' | 'Antimicrobial, Antiparasitic, Antibiotic' | 'Thrombin inhibitor, Trypsin inhibitor'>(str),
+        class: Aliased<'antagonist' | 'antibiotic' | 'anticancer' | 'anticoagulant' | 'antifungal' | 'antigen' | 'antiinflammatory' | 'antimicrobial' | 'antineoplastic' | 'antiparasitic' | 'antiretroviral' | 'anthelmintic' | 'antithrombotic' | 'antitumor' | 'antiviral' | 'caspase inhibitor' | 'chaperone binding' | 'enzyme inhibitor' | 'drug delivery' | 'glycan component' | 'growth factor' | 'immunosuppressant' | 'inducer' | 'inhibitor' | 'lantibiotic' | 'metabolism' | 'metal transport' | 'nutrient' | 'oxidation-reduction' | 'protein binding' | 'receptor' | 'substrate analog' | 'synthetic opioid' | 'thrombin inhibitor' | 'transition state mimetic' | 'transport activator' | 'trypsin inhibitor' | 'toxin' | 'unknown' | 'water retention' | 'anticoagulant, antithrombotic' | 'antibiotic, antimicrobial' | 'antibiotic, anthelmintic' | 'antibiotic, antineoplastic' | 'antimicrobial, antiretroviral' | 'antimicrobial, antitumor' | 'antimicrobial, antiparasitic, antibiotic' | 'thrombin inhibitor, trypsin inhibitor'>(lstr),
         /**
          * Evidence for the assignment of _pdbx_reference_molecule.class
          */
@@ -78,7 +79,7 @@ export const BIRD_Schema = {
         /**
          * Defines how this entity is represented in PDB data files.
          */
-        represent_as: Aliased<'polymer' | 'single molecule' | 'branched'>(str),
+        represent_as: Aliased<'polymer' | 'single molecule' | 'branched'>(lstr),
         /**
          * For entities represented as single molecules, the identifier
          * corresponding to the chemical definition for the molecule.
@@ -99,7 +100,7 @@ export const BIRD_Schema = {
         /**
          * Defines the current PDB release status for this molecule definition.
          */
-        release_status: Aliased<'REL' | 'HOLD' | 'OBS' | 'WAIT'>(str),
+        release_status: Aliased<'rel' | 'hold' | 'obs' | 'wait'>(lstr),
         /**
          * Assigns the identifier for the reference molecule which have been replaced
          * by this reference molecule.
@@ -129,7 +130,7 @@ export const BIRD_Schema = {
         /**
          * Defines the polymer characteristic of the entity.
          */
-        type: Aliased<'polymer' | 'polymer-like' | 'non-polymer' | 'branched'>(str),
+        type: Aliased<'polymer' | 'polymer-like' | 'non-polymer' | 'branched'>(lstr),
         /**
          * Additional details about this entity.
          */
@@ -249,7 +250,7 @@ export const BIRD_Schema = {
         /**
          * The bond order target for the chemical linkage.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
         /**
          * The entity component identifier for the first of two entities containing the linkage.
          */
@@ -335,7 +336,7 @@ export const BIRD_Schema = {
         /**
          * The bond order target for the non-standard linkage.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
     },
     /**
      * Data items in the PDBX_REFERENCE_ENTITY_POLY category record details about
@@ -400,11 +401,11 @@ export const BIRD_Schema = {
         /**
          * A flag to indicate that this monomer is observed in the instance example.
          */
-        observed: Aliased<'Y' | 'N'>(str),
+        observed: Aliased<'y' | 'n'>(lstr),
         /**
          * A flag to indicate that sequence heterogeneity at this monomer position.
          */
-        hetero: Aliased<'Y' | 'N'>(str),
+        hetero: Aliased<'y' | 'n'>(lstr),
     },
     /**
      * Additional features associated with the reference entity.

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

@@ -1,7 +1,7 @@
 /**
- * Copyright (c) 2017-2020 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.356, IHM 1.17, MA 1.3.5.
+ * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.357, IHM 1.17, MA 1.3.6.
  *
  * @author molstar/ciftools package
  */
@@ -13,6 +13,7 @@ import Schema = Column.Schema;
 const str = Schema.str;
 const float = Schema.float;
 const List = Schema.List;
+const lstr = Schema.lstr;
 const Aliased = Schema.Aliased;
 const int = Schema.int;
 const coord = Schema.coord;
@@ -103,7 +104,7 @@ 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, 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),
+        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, 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'>(lstr),
         /**
          * Synonym list for the component.
          */
@@ -154,11 +155,11 @@ export const CCD_Schema = {
         /**
          * This data item identifies if ideal coordinates are missing in this definition.
          */
-        pdbx_ideal_coordinates_missing_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_ideal_coordinates_missing_flag: Aliased<'y' | 'n'>(lstr),
         /**
          * This data item identifies if model coordinates are missing in this definition.
          */
-        pdbx_model_coordinates_missing_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_model_coordinates_missing_flag: Aliased<'y' | 'n'>(lstr),
         /**
          * Date component was added to database.
          */
@@ -279,15 +280,15 @@ export const CCD_Schema = {
         /**
          * The chiral configuration of the atom that is a chiral center.
          */
-        pdbx_stereo_config: Aliased<'R' | 'S' | 'N'>(str),
+        pdbx_stereo_config: Aliased<'r' | 's' | 'n'>(lstr),
         /**
          * A flag indicating an aromatic atom.
          */
-        pdbx_aromatic_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_aromatic_flag: Aliased<'y' | 'n'>(lstr),
         /**
          * A flag indicating a leaving atom.
          */
-        pdbx_leaving_atom_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_leaving_atom_flag: Aliased<'y' | 'n'>(lstr),
     },
     /**
      * Data items in the CHEM_COMP_BOND category record details about
@@ -320,7 +321,7 @@ export const CCD_Schema = {
          * bond associated with the specified atoms, expressed as a bond
          * order.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
         /**
          * Ordinal index for the component bond list.
          */
@@ -328,11 +329,11 @@ export const CCD_Schema = {
         /**
          * Stereochemical configuration across a double bond.
          */
-        pdbx_stereo_config: Aliased<'E' | 'Z' | 'N'>(str),
+        pdbx_stereo_config: Aliased<'e' | 'z' | 'n'>(lstr),
         /**
          * A flag indicating an aromatic bond.
          */
-        pdbx_aromatic_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_aromatic_flag: Aliased<'y' | 'n'>(lstr),
     },
     /**
      * Data items in the CHEM_COMP_DESCRIPTOR category provide
@@ -352,7 +353,7 @@ export const CCD_Schema = {
         /**
          * This data item contains the descriptor type.
          */
-        type: Aliased<'SMILES_CANNONICAL' | 'SMILES_CANONICAL' | 'SMILES' | 'InChI' | 'InChI_MAIN' | 'InChI_MAIN_FORMULA' | 'InChI_MAIN_CONNECT' | 'InChI_MAIN_HATOM' | 'InChI_CHARGE' | 'InChI_STEREO' | 'InChI_ISOTOPE' | 'InChI_FIXEDH' | 'InChI_RECONNECT' | 'InChIKey'>(str),
+        type: Aliased<'smiles_cannonical' | 'smiles_canonical' | 'smiles' | 'inchi' | 'inchi_main' | 'inchi_main_formula' | 'inchi_main_connect' | 'inchi_main_hatom' | 'inchi_charge' | 'inchi_stereo' | 'inchi_isotope' | 'inchi_fixedh' | 'inchi_reconnect' | 'inchikey'>(lstr),
         /**
          * This data item contains the name of the program
          * or library used to compute the descriptor.

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

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2018-2020 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2018-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author David Sehnal <david.sehnal@gmail.com>
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
@@ -25,9 +25,9 @@ export const mmCIF_chemCompBond_schema = {
     molstar_protonation_variant: Column.Schema.Str()
 };
 
-/** Has `type` extended with 'Ion' and 'Lipid' */
+/** Has `type` extended with 'ION' and 'LIPID' */
 export const mmCIF_chemComp_schema = {
     ...mmCIF_Schema.chem_comp,
-    type: Column.Schema.Aliased<mmCIF_Schema['chem_comp']['type']['T'] | 'Ion' | 'Lipid'>(Column.Schema.str)
+    type: Column.Schema.Aliased<mmCIF_Schema['chem_comp']['type']['T'] | 'ion' | 'lipid'>(Column.Schema.str)
 };
 export type mmCIF_chemComp_schema = typeof mmCIF_chemComp_schema;

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

@@ -1,7 +1,7 @@
 /**
- * Copyright (c) 2017-2020 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
- * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.356, IHM 1.17, MA 1.3.5.
+ * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.357, IHM 1.17, MA 1.3.6.
  *
  * @author molstar/ciftools package
  */
@@ -17,6 +17,7 @@ const coord = Schema.coord;
 const Aliased = Schema.Aliased;
 const Matrix = Schema.Matrix;
 const Vector = Schema.Vector;
+const lstr = Schema.lstr;
 const List = Schema.List;
 
 export const mmCIF_Schema = {
@@ -512,7 +513,7 @@ export const mmCIF_Schema = {
          * _chem_comp.mon_nstd_parent, _chem_comp.mon_nstd_class and
          * _chem_comp.mon_nstd_details data items.
          */
-        mon_nstd_flag: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        mon_nstd_flag: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * The full name of the component.
          */
@@ -523,7 +524,7 @@ 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, 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),
+        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, 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'>(lstr),
         /**
          * Synonym list for the component.
          */
@@ -560,7 +561,7 @@ export const mmCIF_Schema = {
          * bond associated with the specified atoms, expressed as a bond
          * order.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
         /**
          * Ordinal index for the component bond list.
          */
@@ -568,11 +569,11 @@ export const mmCIF_Schema = {
         /**
          * Stereochemical configuration across a double bond.
          */
-        pdbx_stereo_config: Aliased<'E' | 'Z' | 'N'>(str),
+        pdbx_stereo_config: Aliased<'e' | 'z' | 'n'>(lstr),
         /**
          * A flag indicating an aromatic bond.
          */
-        pdbx_aromatic_flag: Aliased<'Y' | 'N'>(str),
+        pdbx_aromatic_flag: Aliased<'y' | 'n'>(lstr),
     },
     /**
      * Data items in the CITATION category record details about the
@@ -704,7 +705,7 @@ export const mmCIF_Schema = {
         /**
          * An abbreviation that identifies the database.
          */
-        database_id: Aliased<'AlphaFoldDB' | 'CAS' | 'CSD' | 'EMDB' | 'ICSD' | 'ModelArchive' | 'MDF' | 'MODBASE' | 'NDB' | 'NBS' | 'PDB' | 'PDF' | 'RCSB' | 'SWISS-MODEL_REPOSITORY' | 'EBI' | 'PDBE' | 'BMRB' | 'WWPDB' | 'PDB_ACC'>(str),
+        database_id: Aliased<'alphafolddb' | 'cas' | 'csd' | 'emdb' | 'icsd' | 'modelarchive' | 'mdf' | 'modbase' | 'ndb' | 'nbs' | 'pdb' | 'pdf' | 'rcsb' | 'swiss-model_repository' | 'ebi' | 'pdbe' | 'bmrb' | 'wwpdb' | 'pdb_acc'>(lstr),
         /**
          * The code assigned by the database identified in
          * _database_2.database_id.
@@ -767,7 +768,7 @@ export const mmCIF_Schema = {
          * manipulated sources are expected to have further information in
          * the ENTITY_SRC_GEN category.
          */
-        src_method: Aliased<'nat' | 'man' | 'syn'>(str),
+        src_method: Aliased<'nat' | 'man' | 'syn'>(lstr),
         /**
          * Defines the type of the entity.
          *
@@ -780,7 +781,7 @@ export const mmCIF_Schema = {
          * Water entities are not expected to have corresponding
          * entries in the ENTITY category.
          */
-        type: Aliased<'polymer' | 'non-polymer' | 'macrolide' | 'water' | 'branched'>(str),
+        type: Aliased<'polymer' | 'non-polymer' | 'macrolide' | 'water' | 'branched'>(lstr),
         /**
          * A description of the entity.
          *
@@ -820,12 +821,12 @@ export const mmCIF_Schema = {
          * one monomer-to-monomer link different from that implied by
          * _entity_poly.type.
          */
-        nstd_linkage: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        nstd_linkage: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * A flag to indicate whether the polymer contains at least
          * one monomer that is not considered standard.
          */
-        nstd_monomer: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        nstd_monomer: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * The type of the polymer.
          */
@@ -894,6 +895,10 @@ export const mmCIF_Schema = {
          * parent is not specified. Deoxynucleotides are
          * represented by their canonical one-letter codes of A,
          * C, G, or T.
+         *
+         * For modifications with several parent amino acids,
+         * all corresponding parent amino acid codes will be listed
+         * (ex. chromophores).
          */
         pdbx_seq_one_letter_code_can: str,
         /**
@@ -919,7 +924,7 @@ export const mmCIF_Schema = {
          * A flag to indicate whether this monomer in the polymer is
          * heterogeneous in sequence.
          */
-        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * This data item is a pointer to _chem_comp.id in the CHEM_COMP
          * category.
@@ -996,7 +1001,7 @@ export const mmCIF_Schema = {
          * The classification of the software according to the most
          * common types.
          */
-        type: Aliased<'program' | 'library' | 'package' | 'filter' | 'jiffy' | 'other'>(str),
+        type: Aliased<'program' | 'library' | 'package' | 'filter' | 'jiffy' | 'other'>(lstr),
         /**
          * The version of the software.
          */
@@ -1119,7 +1124,7 @@ export const mmCIF_Schema = {
          * This data item is a pointer to _struct_conf_type.id in the
          * STRUCT_CONF_TYPE category.
          */
-        conf_type_id: Aliased<'BEND' | 'HELX_P' | 'HELX_OT_P' | 'HELX_RH_P' | 'HELX_RH_OT_P' | 'HELX_RH_AL_P' | 'HELX_RH_GA_P' | 'HELX_RH_OM_P' | 'HELX_RH_PI_P' | 'HELX_RH_27_P' | 'HELX_RH_3T_P' | 'HELX_RH_PP_P' | 'HELX_LH_P' | 'HELX_LH_OT_P' | 'HELX_LH_AL_P' | 'HELX_LH_GA_P' | 'HELX_LH_OM_P' | 'HELX_LH_PI_P' | 'HELX_LH_27_P' | 'HELX_LH_3T_P' | 'HELX_LH_PP_P' | 'HELX_N' | 'HELX_OT_N' | 'HELX_RH_N' | 'HELX_RH_OT_N' | 'HELX_RH_A_N' | 'HELX_RH_B_N' | 'HELX_RH_Z_N' | 'HELX_LH_N' | 'HELX_LH_OT_N' | 'HELX_LH_A_N' | 'HELX_LH_B_N' | 'HELX_LH_Z_N' | 'TURN_P' | 'TURN_OT_P' | 'TURN_TY1_P' | 'TURN_TY1P_P' | 'TURN_TY2_P' | 'TURN_TY2P_P' | 'TURN_TY3_P' | 'TURN_TY3P_P' | 'STRN' | 'OTHER'>(str),
+        conf_type_id: Aliased<'bend' | 'helx_p' | 'helx_ot_p' | 'helx_rh_p' | 'helx_rh_ot_p' | 'helx_rh_al_p' | 'helx_rh_ga_p' | 'helx_rh_om_p' | 'helx_rh_pi_p' | 'helx_rh_27_p' | 'helx_rh_3t_p' | 'helx_rh_pp_p' | 'helx_lh_p' | 'helx_lh_ot_p' | 'helx_lh_al_p' | 'helx_lh_ga_p' | 'helx_lh_om_p' | 'helx_lh_pi_p' | 'helx_lh_27_p' | 'helx_lh_3t_p' | 'helx_lh_pp_p' | 'helx_n' | 'helx_ot_n' | 'helx_rh_n' | 'helx_rh_ot_n' | 'helx_rh_a_n' | 'helx_rh_b_n' | 'helx_rh_z_n' | 'helx_lh_n' | 'helx_lh_ot_n' | 'helx_lh_a_n' | 'helx_lh_b_n' | 'helx_lh_z_n' | 'turn_p' | 'turn_ot_p' | 'turn_ty1_p' | 'turn_ty1p_p' | 'turn_ty2_p' | 'turn_ty2p_p' | 'turn_ty3_p' | 'turn_ty3p_p' | 'strn' | 'other'>(lstr),
         /**
          * A description of special aspects of the conformation assignment.
          */
@@ -1219,7 +1224,7 @@ export const mmCIF_Schema = {
          * This data item is a pointer to _struct_conn_type.id in the
          * STRUCT_CONN_TYPE category.
          */
-        conn_type_id: Aliased<'covale' | 'disulf' | 'metalc' | 'hydrog'>(str),
+        conn_type_id: Aliased<'covale' | 'disulf' | 'metalc' | 'hydrog'>(lstr),
         /**
          * A description of special aspects of the connection.
          */
@@ -1439,7 +1444,7 @@ export const mmCIF_Schema = {
          * The chemical bond order associated with the specified atoms in
          * this contact.
          */
-        pdbx_value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad'>(str),
+        pdbx_value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad'>(lstr),
     },
     /**
      * Data items in the STRUCT_CONN_TYPE category record details
@@ -1454,7 +1459,7 @@ export const mmCIF_Schema = {
         /**
          * The chemical or structural type of the interaction.
          */
-        id: Aliased<'covale' | 'disulf' | 'hydrog' | 'metalc' | 'mismat' | 'saltbr' | 'modres' | 'covale_base' | 'covale_sugar' | 'covale_phosphate'>(str),
+        id: Aliased<'covale' | 'disulf' | 'hydrog' | 'metalc' | 'mismat' | 'saltbr' | 'modres' | 'covale_base' | 'covale_sugar' | 'covale_phosphate'>(lstr),
         /**
          * A reference that specifies the criteria used to define the
          * interaction.
@@ -1808,7 +1813,7 @@ export const mmCIF_Schema = {
         /**
          * The cell settings for this space-group symmetry.
          */
-        cell_setting: Aliased<'triclinic' | 'monoclinic' | 'orthorhombic' | 'tetragonal' | 'rhombohedral' | 'trigonal' | 'hexagonal' | 'cubic'>(str),
+        cell_setting: Aliased<'triclinic' | 'monoclinic' | 'orthorhombic' | 'tetragonal' | 'rhombohedral' | 'trigonal' | 'hexagonal' | 'cubic'>(lstr),
         /**
          * Space-group number from International Tables for Crystallography
          * Vol. A (2002).
@@ -1868,7 +1873,7 @@ export const mmCIF_Schema = {
          * This code indicates whether the entry belongs to
          * Structural Genomics Project.
          */
-        SG_entry: Aliased<'Y' | 'N'>(str),
+        SG_entry: Aliased<'y' | 'n'>(lstr),
         /**
          * The site where the file was deposited.
          */
@@ -1892,7 +1897,7 @@ export const mmCIF_Schema = {
          * A value of 'N' indicates that the no PDB format data file is
          * corresponding to this entry is available in the PDB archive.
          */
-        pdb_format_compatible: Aliased<'Y' | 'N'>(str),
+        pdb_format_compatible: Aliased<'y' | 'n'>(lstr),
     },
     /**
      * The PDBX_NONPOLY_SCHEME category provides residue level nomenclature
@@ -2045,7 +2050,7 @@ export const mmCIF_Schema = {
          * The value of polymer flag indicates whether the unobserved or
          * zero occupancy residue is part of a polymer chain or not
          */
-        polymer_flag: Aliased<'Y' | 'N'>(str),
+        polymer_flag: Aliased<'y' | 'n'>(lstr),
         /**
          * The value of occupancy flag indicates whether the residue
          * is unobserved (= 1) or the coordinates have an occupancy of zero (=0)
@@ -2298,7 +2303,7 @@ export const mmCIF_Schema = {
         /**
          * Defines the polymer characteristic of the entity.
          */
-        type: Aliased<'polymer' | 'polymer-like' | 'non-polymer' | 'branched'>(str),
+        type: Aliased<'polymer' | 'polymer-like' | 'non-polymer' | 'branched'>(lstr),
         /**
          * Additional details about this entity.
          */
@@ -2393,7 +2398,7 @@ export const mmCIF_Schema = {
         /**
          * The bond order target for the chemical linkage.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
         /**
          * The entity component identifier for the first of two entities containing the linkage.
          */
@@ -2479,7 +2484,7 @@ export const mmCIF_Schema = {
         /**
          * The bond order target for the non-standard linkage.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
     },
     /**
      * Data items in the PDBX_MOLECULE category identify reference molecules
@@ -2514,11 +2519,11 @@ export const mmCIF_Schema = {
         /**
          * Broadly defines the function of the molecule.
          */
-        class: Aliased<'Antagonist' | 'Antibiotic' | 'Anticancer' | 'Anticoagulant' | 'Antifungal' | 'Antigen' | 'Antiinflammatory' | 'Antimicrobial' | 'Antineoplastic' | 'Antiparasitic' | 'Antiretroviral' | 'Anthelmintic' | 'Antithrombotic' | 'Antitumor' | 'Antiviral' | 'CASPASE inhibitor' | 'Chaperone binding' | 'Enzyme inhibitor' | 'Drug delivery' | 'Glycan component' | 'Growth factor' | 'Immunosuppressant' | 'Inducer' | 'Inhibitor' | 'Lantibiotic' | 'Metabolism' | 'Metal transport' | 'Nutrient' | 'Oxidation-reduction' | 'Protein binding' | 'Receptor' | 'Substrate analog' | 'Synthetic opioid' | 'Thrombin inhibitor' | 'Transition state mimetic' | 'Transport activator' | 'Trypsin inhibitor' | 'Toxin' | 'Unknown' | 'Water retention' | 'Anticoagulant, Antithrombotic' | 'Antibiotic, Antimicrobial' | 'Antibiotic, Anthelmintic' | 'Antibiotic, Antineoplastic' | 'Antimicrobial, Antiretroviral' | 'Antimicrobial, Antitumor' | 'Antimicrobial, Antiparasitic, Antibiotic' | 'Thrombin inhibitor, Trypsin inhibitor'>(str),
+        class: Aliased<'antagonist' | 'antibiotic' | 'anticancer' | 'anticoagulant' | 'antifungal' | 'antigen' | 'antiinflammatory' | 'antimicrobial' | 'antineoplastic' | 'antiparasitic' | 'antiretroviral' | 'anthelmintic' | 'antithrombotic' | 'antitumor' | 'antiviral' | 'caspase inhibitor' | 'chaperone binding' | 'enzyme inhibitor' | 'drug delivery' | 'glycan component' | 'growth factor' | 'immunosuppressant' | 'inducer' | 'inhibitor' | 'lantibiotic' | 'metabolism' | 'metal transport' | 'nutrient' | 'oxidation-reduction' | 'protein binding' | 'receptor' | 'substrate analog' | 'synthetic opioid' | 'thrombin inhibitor' | 'transition state mimetic' | 'transport activator' | 'trypsin inhibitor' | 'toxin' | 'unknown' | 'water retention' | 'anticoagulant, antithrombotic' | 'antibiotic, antimicrobial' | 'antibiotic, anthelmintic' | 'antibiotic, antineoplastic' | 'antimicrobial, antiretroviral' | 'antimicrobial, antitumor' | 'antimicrobial, antiparasitic, antibiotic' | 'thrombin inhibitor, trypsin inhibitor'>(lstr),
         /**
          * Defines the structural classification of the molecule.
          */
-        type: Aliased<'Amino acid' | 'Aminoglycoside' | 'Anthracycline' | 'Anthraquinone' | 'Ansamycin' | 'Chalkophore' | 'Chromophore' | 'Glycopeptide' | 'Cyclic depsipeptide' | 'Cyclic lipopeptide' | 'Cyclic peptide' | 'Heterocyclic' | 'Imino sugar' | 'Keto acid' | 'Lipoglycopeptide' | 'Lipopeptide' | 'Macrolide' | 'Non-polymer' | 'Nucleoside' | 'Oligopeptide' | 'Oligosaccharide' | 'Peptaibol' | 'Peptide-like' | 'Polycyclic' | 'Polypeptide' | 'Polysaccharide' | 'Quinolone' | 'Thiolactone' | 'Thiopeptide' | 'Siderophore' | 'Unknown' | 'Chalkophore, Polypeptide'>(str),
+        type: Aliased<'amino acid' | 'aminoglycoside' | 'anthracycline' | 'anthraquinone' | 'ansamycin' | 'chalkophore' | 'chromophore' | 'glycopeptide' | 'cyclic depsipeptide' | 'cyclic lipopeptide' | 'cyclic peptide' | 'heterocyclic' | 'imino sugar' | 'keto acid' | 'lipoglycopeptide' | 'lipopeptide' | 'macrolide' | 'non-polymer' | 'nucleoside' | 'oligopeptide' | 'oligosaccharide' | 'peptaibol' | 'peptide-like' | 'polycyclic' | 'polypeptide' | 'polysaccharide' | 'quinolone' | 'thiolactone' | 'thiopeptide' | 'siderophore' | 'unknown' | 'chalkophore, polypeptide'>(lstr),
         /**
          * A name of the molecule.
          */
@@ -2665,7 +2670,7 @@ export const mmCIF_Schema = {
         /**
          * This data item contains the descriptor type.
          */
-        type: Aliased<'LINUCS' | 'Glycam Condensed Sequence' | 'Glycam Condensed Core Sequence' | 'WURCS'>(str),
+        type: Aliased<'linucs' | 'glycam condensed sequence' | 'glycam condensed core sequence' | 'wurcs'>(lstr),
         /**
          * This data item contains the name of the program
          * or library used to compute the descriptor.
@@ -2740,7 +2745,7 @@ export const mmCIF_Schema = {
          * A flag to indicate whether this monomer in the entity is
          * heterogeneous in sequence.
          */
-        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * This data item is a pointer to _chem_comp.id in the CHEM_COMP
          * category.
@@ -2812,7 +2817,7 @@ export const mmCIF_Schema = {
         /**
          * The chiral configuration of the first atom making the linkage.
          */
-        atom_stereo_config_1: Aliased<'R' | 'S' | 'N'>(str),
+        atom_stereo_config_1: Aliased<'r' | 's' | 'n'>(lstr),
         /**
          * The atom identifier/name for the second atom making the linkage.
          */
@@ -2824,11 +2829,11 @@ export const mmCIF_Schema = {
         /**
          * The chiral configuration of the second atom making the linkage.
          */
-        atom_stereo_config_2: Aliased<'R' | 'S' | 'N'>(str),
+        atom_stereo_config_2: Aliased<'r' | 's' | 'n'>(lstr),
         /**
          * The bond order target for the chemical linkage.
          */
-        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+        value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(lstr),
     },
     /**
      * Data items in the PDBX_ENTITY_BRANCH category specify the list
@@ -2859,7 +2864,7 @@ export const mmCIF_Schema = {
          * A flag to indicate whether this monomer in the entity is
          * heterogeneous in sequence.
          */
-        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+        hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(lstr),
         /**
          * Pointer to _atom_site.label_asym_id.
          */
@@ -3332,15 +3337,15 @@ export const mmCIF_Schema = {
         /**
          * A flag to indicate if the modeling is multi scale.
          */
-        multi_scale_flag: Aliased<'YES' | 'NO'>(str),
+        multi_scale_flag: Aliased<'yes' | 'no'>(lstr),
         /**
          * A flag to indicate if the modeling is multi state.
          */
-        multi_state_flag: Aliased<'YES' | 'NO'>(str),
+        multi_state_flag: Aliased<'yes' | 'no'>(lstr),
         /**
          * A flag to indicate if the modeling involves an ensemble ordered by time or other order.
          */
-        ordered_flag: Aliased<'YES' | 'NO'>(str),
+        ordered_flag: Aliased<'yes' | 'no'>(lstr),
         /**
          * The file id corresponding to the script used in the modeling protocol step.
          * This data item is a pointer to _ihm_external_files.id in the IHM_EXTERNAL_FILES category.
@@ -3629,7 +3634,7 @@ export const mmCIF_Schema = {
          * A flag that indicates whether the dataset is archived in
          * an IHM related database or elsewhere.
          */
-        database_hosted: Aliased<'YES' | 'NO'>(str),
+        database_hosted: Aliased<'yes' | 'no'>(lstr),
     },
     /**
      * Category to define groups or collections of input datasets.
@@ -4236,7 +4241,7 @@ export const mmCIF_Schema = {
          * whether the whole image is used or only a portion of it is used (by masking
          * or by other means) as restraint in the modeling.
          */
-        image_segment_flag: Aliased<'YES' | 'NO'>(str),
+        image_segment_flag: Aliased<'yes' | 'no'>(lstr),
         /**
          * Number of 2D projections of the model used in the fitting.
          */
@@ -4389,7 +4394,7 @@ export const mmCIF_Schema = {
          * whether the whole SAS profile is used or only a portion of it is used
          * (by masking or by other means) as restraint in the modeling.
          */
-        profile_segment_flag: Aliased<'YES' | 'NO'>(str),
+        profile_segment_flag: Aliased<'yes' | 'no'>(lstr),
         /**
          * The type of atoms in the model fit to the SAS data.
          */
@@ -4983,7 +4988,7 @@ export const mmCIF_Schema = {
         /**
          * The type of QA metric.
          */
-        type: Aliased<'zscore' | 'energy' | 'distance' | 'normalized score' | 'pLDDT' | 'PAE' | 'contact probability' | 'other'>(str),
+        type: Aliased<'zscore' | 'energy' | 'distance' | 'normalized score' | 'pLDDT' | 'pLDDT in [0,1]' | 'pLDDT all-atom' | 'pLDDT all-atom in [0,1]' | 'PAE' | 'pTM' | 'ipTM' | 'contact probability' | 'other'>(str),
         /**
          * The mode of calculation of the QA metric.
          */

src/mol-io/writer/mol/encoder.ts

@@ -42,7 +42,7 @@ export class MolEncoder extends LigandEncoder {
             StringBuilder.writeSafe(ctab, '  0');
             StringBuilder.writeIntegerPadLeft(ctab, this.mapCharge(charge), 3);
             StringBuilder.writeSafe(ctab, '  0  0  0  0  0  0  0  0  0  0\n');
-            if (stereo_config !== 'N') chiral = true;
+            if (stereo_config !== 'n') chiral = true;
 
             // no data for metal ions
             if (!bondMap?.map) return;

src/mol-model-formats/structure/basic/entities.ts

@@ -10,6 +10,9 @@ import { Entities, EntitySubtype } from '../../../mol-model/structure/model/prop
 import { getEntityType, getEntitySubtype } from '../../../mol-model/structure/model/types';
 import { ElementIndex, EntityIndex, Model } from '../../../mol-model/structure/model';
 import { BasicData, BasicSchema, Entity } from './schema';
+import { mmCIF_chemComp_schema } from '../../../mol-io/reader/cif/schema/mmcif-extras';
+
+type ChemCompType = mmCIF_chemComp_schema['type']['T'];
 
 export function getEntityData(data: BasicData): Entities {
     let entityData: Entity;
@@ -96,7 +99,7 @@ export function getEntityData(data: BasicData): Entities {
     }
 
     if (assignSubtype) {
-        const chemCompType = new Map<string, string>();
+        const chemCompType = new Map<string, ChemCompType>();
         if (data.chem_comp) {
             const { id, type } = data.chem_comp;
             for (let i = 0, il = data.chem_comp._rowCount; i < il; i++) {
@@ -110,7 +113,7 @@ export function getEntityData(data: BasicData): Entities {
                 const entityId = label_entity_id.value(i);
                 if (!entityIds.has(entityId)) {
                     const compId = label_comp_id.value(i);
-                    const compType = chemCompType.get(compId) || '';
+                    const compType = chemCompType.get(compId) || 'other';
                     subtypes[getEntityIndex(entityId)] = getEntitySubtype(compId, compType);
                     entityIds.add(entityId);
                 }

src/mol-model-formats/structure/common/component.ts

@@ -37,48 +37,48 @@ const NonPolymerNames = new Set([
 const StandardComponents = (function () {
     const map = new Map<string, Component>();
     const components: Component[] = [
-        { id: 'HIS', name: 'HISTIDINE', type: 'L-peptide linking' },
-        { id: 'ARG', name: 'ARGININE', type: 'L-peptide linking' },
-        { id: 'LYS', name: 'LYSINE', type: 'L-peptide linking' },
-        { id: 'ILE', name: 'ISOLEUCINE', type: 'L-peptide linking' },
-        { id: 'PHE', name: 'PHENYLALANINE', type: 'L-peptide linking' },
-        { id: 'LEU', name: 'LEUCINE', type: 'L-peptide linking' },
-        { id: 'TRP', name: 'TRYPTOPHAN', type: 'L-peptide linking' },
-        { id: 'ALA', name: 'ALANINE', type: 'L-peptide linking' },
-        { id: 'MET', name: 'METHIONINE', type: 'L-peptide linking' },
-        { id: 'CYS', name: 'CYSTEINE', type: 'L-peptide linking' },
-        { id: 'ASN', name: 'ASPARAGINE', type: 'L-peptide linking' },
-        { id: 'VAL', name: 'VALINE', type: 'L-peptide linking' },
+        { id: 'HIS', name: 'HISTIDINE', type: 'l-peptide linking' },
+        { id: 'ARG', name: 'ARGININE', type: 'l-peptide linking' },
+        { id: 'LYS', name: 'LYSINE', type: 'l-peptide linking' },
+        { id: 'ILE', name: 'ISOLEUCINE', type: 'l-peptide linking' },
+        { id: 'PHE', name: 'PHENYLALANINE', type: 'l-peptide linking' },
+        { id: 'LEU', name: 'LEUCINE', type: 'l-peptide linking' },
+        { id: 'TRP', name: 'TRYPTOPHAN', type: 'l-peptide linking' },
+        { id: 'ALA', name: 'ALANINE', type: 'l-peptide linking' },
+        { id: 'MET', name: 'METHIONINE', type: 'l-peptide linking' },
+        { id: 'CYS', name: 'CYSTEINE', type: 'l-peptide linking' },
+        { id: 'ASN', name: 'ASPARAGINE', type: 'l-peptide linking' },
+        { id: 'VAL', name: 'VALINE', type: 'l-peptide linking' },
         { id: 'GLY', name: 'GLYCINE', type: 'peptide linking' },
-        { id: 'SER', name: 'SERINE', type: 'L-peptide linking' },
-        { id: 'GLN', name: 'GLUTAMINE', type: 'L-peptide linking' },
-        { id: 'TYR', name: 'TYROSINE', type: 'L-peptide linking' },
-        { id: 'ASP', name: 'ASPARTIC ACID', type: 'L-peptide linking' },
-        { id: 'GLU', name: 'GLUTAMIC ACID', type: 'L-peptide linking' },
-        { id: 'THR', name: 'THREONINE', type: 'L-peptide linking' },
-        { id: 'PRO', name: 'PROLINE', type: 'L-peptide linking' },
-        { id: 'SEC', name: 'SELENOCYSTEINE', type: 'L-peptide linking' },
-        { id: 'PYL', name: 'PYRROLYSINE', type: 'L-peptide linking' },
-
-        { id: 'MSE', name: 'SELENOMETHIONINE', type: 'L-peptide linking' },
-        { id: 'SEP', name: 'PHOSPHOSERINE', type: 'L-peptide linking' },
-        { id: 'TPO', name: 'PHOSPHOTHREONINE', type: 'L-peptide linking' },
-        { id: 'PTR', name: 'O-PHOSPHOTYROSINE', type: 'L-peptide linking' },
-        { id: 'PCA', name: 'PYROGLUTAMIC ACID', type: 'L-peptide linking' },
-
-        { id: 'A', name: 'ADENOSINE-5\'-MONOPHOSPHATE', type: 'RNA linking' },
-        { id: 'C', name: 'CYTIDINE-5\'-MONOPHOSPHATE', type: 'RNA linking' },
-        { id: 'T', name: 'THYMIDINE-5\'-MONOPHOSPHATE', type: 'RNA linking' },
-        { id: 'G', name: 'GUANOSINE-5\'-MONOPHOSPHATE', type: 'RNA linking' },
-        { id: 'I', name: 'INOSINIC ACID', type: 'RNA linking' },
-        { id: 'U', name: 'URIDINE-5\'-MONOPHOSPHATE', type: 'RNA linking' },
-
-        { id: 'DA', name: '2\'-DEOXYADENOSINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
-        { id: 'DC', name: '2\'-DEOXYCYTIDINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
-        { id: 'DT', name: 'THYMIDINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
-        { id: 'DG', name: '2\'-DEOXYGUANOSINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
-        { id: 'DI', name: '2\'-DEOXYINOSINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
-        { id: 'DU', name: '2\'-DEOXYURIDINE-5\'-MONOPHOSPHATE', type: 'DNA linking' },
+        { id: 'SER', name: 'SERINE', type: 'l-peptide linking' },
+        { id: 'GLN', name: 'GLUTAMINE', type: 'l-peptide linking' },
+        { id: 'TYR', name: 'TYROSINE', type: 'l-peptide linking' },
+        { id: 'ASP', name: 'ASPARTIC ACID', type: 'l-peptide linking' },
+        { id: 'GLU', name: 'GLUTAMIC ACID', type: 'l-peptide linking' },
+        { id: 'THR', name: 'THREONINE', type: 'l-peptide linking' },
+        { id: 'PRO', name: 'PROLINE', type: 'l-peptide linking' },
+        { id: 'SEC', name: 'SELENOCYSTEINE', type: 'l-peptide linking' },
+        { id: 'PYL', name: 'PYRROLYSINE', type: 'l-peptide linking' },
+
+        { id: 'MSE', name: 'SELENOMETHIONINE', type: 'l-peptide linking' },
+        { id: 'SEP', name: 'PHOSPHOSERINE', type: 'l-peptide linking' },
+        { id: 'TPO', name: 'PHOSPHOTHREONINE', type: 'l-peptide linking' },
+        { id: 'PTR', name: 'O-PHOSPHOTYROSINE', type: 'l-peptide linking' },
+        { id: 'PCA', name: 'PYROGLUTAMIC ACID', type: 'l-peptide linking' },
+
+        { id: 'A', name: 'ADENOSINE-5\'-MONOPHOSPHATE', type: 'rna linking' },
+        { id: 'C', name: 'CYTIDINE-5\'-MONOPHOSPHATE', type: 'rna linking' },
+        { id: 'T', name: 'THYMIDINE-5\'-MONOPHOSPHATE', type: 'rna linking' },
+        { id: 'G', name: 'GUANOSINE-5\'-MONOPHOSPHATE', type: 'rna linking' },
+        { id: 'I', name: 'INOSINIC ACID', type: 'rna linking' },
+        { id: 'U', name: 'URIDINE-5\'-MONOPHOSPHATE', type: 'rna linking' },
+
+        { id: 'DA', name: '2\'-DEOXYADENOSINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
+        { id: 'DC', name: '2\'-DEOXYCYTIDINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
+        { id: 'DT', name: 'THYMIDINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
+        { id: 'DG', name: '2\'-DEOXYGUANOSINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
+        { id: 'DI', name: '2\'-DEOXYINOSINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
+        { id: 'DU', name: '2\'-DEOXYURIDINE-5\'-MONOPHOSPHATE', type: 'dna linking' },
     ];
     components.forEach(c => map.set(c.id, c));
     return map;
@@ -87,12 +87,12 @@ const StandardComponents = (function () {
 const CharmmIonComponents = (function () {
     const map = new Map<string, Component>();
     const components: Component[] = [
-        { id: 'ZN2', name: 'ZINC ION', type: 'Ion' },
-        { id: 'SOD', name: 'SODIUM ION', type: 'Ion' },
-        { id: 'CES', name: 'CESIUM ION', type: 'Ion' },
-        { id: 'CLA', name: 'CHLORIDE ION', type: 'Ion' },
-        { id: 'CAL', name: 'CALCIUM ION', type: 'Ion' },
-        { id: 'POT', name: 'POTASSIUM ION', type: 'Ion' },
+        { id: 'ZN2', name: 'ZINC ION', type: 'ion' },
+        { id: 'SOD', name: 'SODIUM ION', type: 'ion' },
+        { id: 'CES', name: 'CESIUM ION', type: 'ion' },
+        { id: 'CLA', name: 'CHLORIDE ION', type: 'ion' },
+        { id: 'CAL', name: 'CALCIUM ION', type: 'ion' },
+        { id: 'POT', name: 'POTASSIUM ION', type: 'ion' },
     ];
     components.forEach(c => map.set(c.id, c));
     return map;
@@ -140,9 +140,9 @@ export class ComponentBuilder {
         if (this.hasAtomIds(atomIds, ProteinAtomIdsList)) {
             return 'peptide linking';
         } else if (this.hasAtomIds(atomIds, RnaAtomIdsList)) {
-            return 'RNA linking';
+            return 'rna linking';
         } else if (this.hasAtomIds(atomIds, DnaAtomIdsList)) {
-            return 'DNA linking';
+            return 'dna linking';
         } else {
             return 'other';
         }

src/mol-model-formats/structure/pdb/secondary-structure.ts

@@ -23,19 +23,19 @@ const HelixTypes: {[k: string]: mmCIF_Schema['struct_conf']['conf_type_id']['T']
     // Left-handed gamma                           8
     // 2 - 7 ribbon/helix                          9
     // Polyproline                                10
-    1: 'HELX_RH_AL_P',
-    2: 'HELX_RH_OM_P',
-    3: 'HELX_RH_PI_P',
-    4: 'HELX_RH_GA_P',
-    5: 'HELX_RH_3T_P',
-    6: 'HELX_LH_AL_P',
-    7: 'HELX_LH_OM_P',
-    8: 'HELX_LH_GA_P',
-    9: 'HELX_RH_27_P', // TODO or left-handed???
-    10: 'HELX_RH_PP_P', // TODO or left-handed???
+    1: 'helx_rh_al_p',
+    2: 'helx_rh_om_p',
+    3: 'helx_rh_pi_p',
+    4: 'helx_rh_ga_p',
+    5: 'helx_rh_3t_p',
+    6: 'helx_lh_al_p',
+    7: 'helx_lh_om_p',
+    8: 'helx_lh_ga_p',
+    9: 'helx_rh_27_p', // TODO or left-handed???
+    10: 'helx_rh_pp_p', // TODO or left-handed???
 };
 function getStructConfTypeId(type: string): mmCIF_Schema['struct_conf']['conf_type_id']['T'] {
-    return HelixTypes[type] || 'HELX_P';
+    return HelixTypes[type] || 'helx_p';
 }
 
 interface PdbHelix {

src/mol-model-formats/structure/property/bonds/chem_comp.ts

@@ -73,7 +73,7 @@ export namespace ComponentBond {
             const nameA = atom_id_1.value(i)!;
             const nameB = atom_id_2.value(i)!;
             const order = value_order.value(i)!;
-            const aromatic = pdbx_aromatic_flag.value(i) === 'Y';
+            const aromatic = pdbx_aromatic_flag.value(i) === 'y';
 
             if (entry.id !== id) {
                 entry = addEntry(id);

src/mol-model-formats/structure/property/bonds/struct_conn.ts

@@ -138,7 +138,7 @@ export namespace StructConn {
             if (partnerA === undefined || partnerB === undefined) continue;
 
             const type = conn_type_id.value(i);
-            const orderType = (pdbx_value_order.value(i) || '').toLowerCase();
+            const orderType = (pdbx_value_order.value(i) || '');
             let flags = BondType.Flag.None;
             let order = 1;
 

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

@@ -303,7 +303,7 @@ export namespace Model {
         if (!MmcifFormat.is(model.sourceData)) return false;
         const { db } = model.sourceData.data;
         for (let i = 0, il = db.database_2.database_id.rowCount; i < il; ++i) {
-            if (db.database_2.database_id.value(i) === 'PDB') return true;
+            if (db.database_2.database_id.value(i) === 'pdb') return true;
         }
         return false;
     }

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

@@ -17,7 +17,7 @@ export type EntitySubtype = (
     'lipid' |
     'peptide-like'
 )
-export const EntitySubtype = Column.Schema.Aliased<EntitySubtype>(Column.Schema.Str(''));
+export const EntitySubtype = Column.Schema.Aliased<EntitySubtype>(Column.Schema.Str());
 
 export interface Entities {
     data: mmCIF_Database['entity'],

src/mol-model/structure/model/properties/utils/atomic-derived.ts

@@ -11,6 +11,9 @@ import { MoleculeType, getMoleculeType, getComponentType, PolymerType, getPolyme
 import { getAtomIdForAtomRole } from '../../../../../mol-model/structure/util';
 import { ChemicalComponentMap } from '../common';
 import { isProductionMode } from '../../../../../mol-util/debug';
+import { mmCIF_chemComp_schema } from '../../../../../mol-io/reader/cif/schema/mmcif-extras';
+
+type ChemCompType = mmCIF_chemComp_schema['type']['T'];
 
 export function getAtomicDerivedData(data: AtomicData, segments: AtomicSegments, index: AtomicIndex, chemicalComponentMap: ChemicalComponentMap): AtomicDerivedData {
     const { label_comp_id, type_symbol, _rowCount: atomCount } = data.atoms;
@@ -42,7 +45,7 @@ export function getAtomicDerivedData(data: AtomicData, segments: AtomicSegments,
             molType = moleculeTypeMap.get(compId)!;
             polyType = polymerTypeMap.get(compId)!;
         } else {
-            let type: string;
+            let type: ChemCompType;
             if (chemCompMap.has(compId)) {
                 type = chemCompMap.get(compId)!.type;
             } else {

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

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2017-2021 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2017-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
  * @author David Sehnal <david.sehnal@gmail.com>
@@ -162,39 +162,41 @@ export const NucleicBackboneAtoms = new Set([
     'O2*', 'O3*', 'O4*', 'O5*', 'C1*', 'C2*', 'C3*', 'C4*', 'C5*'
 ]);
 
+type ChemCompType = mmCIF_chemComp_schema['type']['T'];
+
 /** Chemical component type names for D-linked protein */
-export const DProteinComponentTypeNames = new Set([
-    'D-PEPTIDE LINKING', 'D-PEPTIDE NH3 AMINO TERMINUS',
-    'D-PEPTIDE COOH CARBOXY TERMINUS', 'D-GAMMA-PEPTIDE, C-DELTA LINKING',
-    'D-BETA-PEPTIDE, C-GAMMA LINKING'
+export const DProteinComponentTypeNames = new Set<ChemCompType>([
+    'd-peptide linking', 'd-peptide nh3 amino terminus',
+    'd-peptide cooh carboxy terminus', 'd-gamma-peptide, c-delta linking',
+    'd-beta-peptide, c-gamma linking'
 ]);
 
 /** Chemical component type names for L-linked protein */
-export const LProteinComponentTypeNames = new Set([
-    'L-PEPTIDE LINKING', 'L-PEPTIDE NH3 AMINO TERMINUS',
-    'L-PEPTIDE COOH CARBOXY TERMINUS', 'L-GAMMA-PEPTIDE, C-DELTA LINKING',
-    'L-BETA-PEPTIDE, C-GAMMA LINKING'
+export const LProteinComponentTypeNames = new Set<ChemCompType>([
+    'l-peptide linking', 'l-peptide nh3 amino terminus',
+    'l-peptide cooh carboxy terminus', 'l-gamma-peptide, c-delta linking',
+    'l-beta-peptide, c-gamma linking'
 ]);
 
 /** Chemical component type names for gamma protein, overlaps with D/L-linked */
-export const GammaProteinComponentTypeNames = new Set([
-    'D-GAMMA-PEPTIDE, C-DELTA LINKING', 'L-GAMMA-PEPTIDE, C-DELTA LINKING'
+export const GammaProteinComponentTypeNames = new Set<ChemCompType>([
+    'd-gamma-peptide, c-delta linking', 'l-gamma-peptide, c-delta linking'
 ]);
 
 /** Chemical component type names for beta protein, overlaps with D/L-linked */
-export const BetaProteinComponentTypeNames = new Set([
-    'D-BETA-PEPTIDE, C-GAMMA LINKING', 'L-BETA-PEPTIDE, C-GAMMA LINKING'
+export const BetaProteinComponentTypeNames = new Set<ChemCompType>([
+    'd-beta-peptide, c-gamma linking', 'l-beta-peptide, c-gamma linking'
 ]);
 
 /** Chemical component type names for protein termini, overlaps with D/L-linked */
-export const ProteinTerminusComponentTypeNames = new Set([
-    'D-PEPTIDE NH3 AMINO TERMINUS', 'D-PEPTIDE COOH CARBOXY TERMINUS',
-    'L-PEPTIDE NH3 AMINO TERMINUS', 'L-PEPTIDE COOH CARBOXY TERMINUS'
+export const ProteinTerminusComponentTypeNames = new Set<ChemCompType>([
+    'd-peptide nh3 amino terminus', 'd-peptide cooh carboxy terminus',
+    'l-peptide nh3 amino terminus', 'l-peptide cooh carboxy terminus'
 ]);
 
 /** Chemical component type names for peptide-like protein */
-export const OtherProteinComponentTypeNames = new Set([
-    'PEPTIDE LINKING', 'PEPTIDE-LIKE',
+export const OtherProteinComponentTypeNames = new Set<ChemCompType>([
+    'peptide linking', 'peptide-like',
 ]);
 
 /** Chemical component type names for protein */
@@ -203,38 +205,42 @@ export const ProteinComponentTypeNames = SetUtils.unionMany(
 );
 
 /** Chemical component type names for DNA */
-export const DNAComponentTypeNames = new Set([
-    'DNA LINKING', 'L-DNA LINKING', 'DNA OH 5 PRIME TERMINUS', 'DNA OH 3 PRIME TERMINUS',
+export const DNAComponentTypeNames = new Set<ChemCompType>([
+    'dna linking', 'l-dna linking', 'dna oh 5 prime terminus', 'dna oh 3 prime terminus',
 ]);
 
 /** Chemical component type names for RNA */
-export const RNAComponentTypeNames = new Set([
-    'RNA LINKING', 'L-RNA LINKING', 'RNA OH 5 PRIME TERMINUS', 'RNA OH 3 PRIME TERMINUS',
+export const RNAComponentTypeNames = new Set<ChemCompType>([
+    'rna linking', 'l-rna linking', 'rna oh 5 prime terminus', 'rna oh 3 prime terminus',
 ]);
 
 /** 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',
-]);
+export const SaccharideComponentTypeNames = SetUtils.unionMany(
+    new Set<ChemCompType>([
+        'd-saccharide, beta linking', 'l-saccharide, beta linking',
+        'd-saccharide, alpha linking', 'l-saccharide, alpha linking',
+        'l-saccharide', 'd-saccharide', 'saccharide',
+    ]),
+    // deprecated in the mmCIF dictionary, kept for backward compatibility
+    new Set([
+        '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'
+    ]),
+);
 
 /** Chemical component type names for other */
-export const OtherComponentTypeNames = new Set([
-    'NON-POLYMER', 'OTHER'
+export const OtherComponentTypeNames = new Set<ChemCompType>([
+    'non-polymer', 'other'
 ]);
 
 /** Chemical component type names for ion (extension to mmcif) */
-export const IonComponentTypeNames = new Set([
-    'ION'
+export const IonComponentTypeNames = new Set<ChemCompType>([
+    'ion'
 ]);
 
 /** Chemical component type names for lipid (extension to mmcif) */
-export const LipidComponentTypeNames = new Set([
-    'LIPID'
+export const LipidComponentTypeNames = new Set<ChemCompType>([
+    'lipid'
 ]);
 
 /** Common names for water molecules */
@@ -298,8 +304,7 @@ export const isPyrimidineBase = (compId: string) => PyrimidineBaseNames.has(comp
 export const PolymerNames = SetUtils.unionMany(AminoAcidNames, BaseNames);
 
 /** get the molecule type from component type and id */
-export function getMoleculeType(compType: string, compId: string): MoleculeType {
-    compType = compType.toUpperCase();
+export function getMoleculeType(compType: ChemCompType, compId: string): MoleculeType {
     compId = compId.toUpperCase();
     if (PeptideBaseNames.has(compId)) {
         return MoleculeType.PNA;
@@ -319,7 +324,7 @@ export function getMoleculeType(compType: string, compId: string): MoleculeType
         return MoleculeType.Lipid;
     } else if (OtherComponentTypeNames.has(compType)) {
         if (SaccharideCompIdMap.has(compId)) {
-            // trust our saccharide table more than given 'non-polymer' or 'other' component type
+            // trust our saccharide table more than given 'NON-POLYMER' or 'OTHER' component type
             return MoleculeType.Saccharide;
         } else if (AminoAcidNames.has(compId)) {
             return MoleculeType.Protein;
@@ -335,8 +340,7 @@ export function getMoleculeType(compType: string, compId: string): MoleculeType
     }
 }
 
-export function getPolymerType(compType: string, molType: MoleculeType): PolymerType {
-    compType = compType.toUpperCase();
+export function getPolymerType(compType: ChemCompType, molType: MoleculeType): PolymerType {
     if (molType === MoleculeType.Protein) {
         if (GammaProteinComponentTypeNames.has(compType)) {
             return PolymerType.GammaProtein;
@@ -358,14 +362,14 @@ export function getPolymerType(compType: string, molType: MoleculeType): Polymer
     }
 }
 
-export function getComponentType(compId: string): mmCIF_chemComp_schema['type']['T'] {
+export function getComponentType(compId: string): ChemCompType {
     compId = compId.toUpperCase();
     if (AminoAcidNames.has(compId)) {
         return 'peptide linking';
     } else if (RnaBaseNames.has(compId)) {
-        return 'RNA linking';
+        return 'rna linking';
     } else if (DnaBaseNames.has(compId)) {
-        return 'DNA linking';
+        return 'dna linking';
     } else if (SaccharideCompIdMap.has(compId)) {
         return 'saccharide';
     } else {
@@ -400,9 +404,8 @@ export function getEntityType(compId: string): mmCIF_Schema['entity']['type']['T
     }
 }
 
-export function getEntitySubtype(compId: string, compType: string): EntitySubtype {
+export function getEntitySubtype(compId: string, compType: ChemCompType): EntitySubtype {
     compId = compId.toUpperCase();
-    compType = compType.toUpperCase();
     if (LProteinComponentTypeNames.has(compType)) {
         return 'polypeptide(L)';
     } else if (DProteinComponentTypeNames.has(compType)) {

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

@@ -1,5 +1,5 @@
 /**
- * Copyright (c) 2019-2021 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ * Copyright (c) 2019-2022 mol* contributors, licensed under MIT, See LICENSE file for more info.
  *
  * @author Alexander Rose <alexander.rose@weirdbyte.de>
  * @author David Sehnal <david.sehnal@gmail.com>