diff --git a/CHANGELOG.md b/CHANGELOG.md
index 494610e16bfbfd0baa9ec169b39599e65a8086bd..397b8354c9c0b742a8754834610f9653426a6316 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,7 @@ Note that since we don't clearly distinguish between a public and private interf
## [Unreleased]
- Add `tubularHelices` parameter to Cartoon representation
+- Add `SdfFormat` and update SDF parser to be able to parse data headers according to spec (hopefully :)) #230
## [v2.1.0] - 2021-07-05
diff --git a/src/mol-io/reader/_spec/sdf.spec.ts b/src/mol-io/reader/_spec/sdf.spec.ts
index fb6dad9869bb9f9e6d02d283114ddb64b4218dfb..d7e47781990de7b517baa9c2c8c9d402d2499a53 100644
--- a/src/mol-io/reader/_spec/sdf.spec.ts
+++ b/src/mol-io/reader/_spec/sdf.spec.ts
@@ -22,8 +22,8 @@ M END
> <DATABASE_NAME>
drugbank
-> <SMILES>
-[O-]P([O-])([O-])=O
+> 5225 <TEST_FIELD>
+whatever
> <INCHI_IDENTIFIER>
InChI=1S/H3O4P/c1-5(2,3)4/h(H3,1,2,3,4)/p-3
@@ -362,22 +362,25 @@ describe('sdf reader', () => {
expect(bonds.atomIdxB.value(3)).toBe(5);
expect(bonds.order.value(3)).toBe(1);
- expect(dataItems.dataHeader.value(0)).toBe('DATABASE_ID');
+ expect(dataItems.dataHeader.value(0)).toBe('<DATABASE_ID>');
expect(dataItems.data.value(0)).toBe('0');
- expect(dataItems.dataHeader.value(1)).toBe('DATABASE_NAME');
+ expect(dataItems.dataHeader.value(1)).toBe('<DATABASE_NAME>');
expect(dataItems.data.value(1)).toBe('drugbank');
- expect(dataItems.dataHeader.value(31)).toBe('SYNONYMS');
+ expect(dataItems.dataHeader.value(2)).toBe('5225 <TEST_FIELD>');
+ expect(dataItems.data.value(2)).toBe('whatever');
+
+ expect(dataItems.dataHeader.value(31)).toBe('<SYNONYMS>');
expect(dataItems.data.value(31)).toBe('Orthophosphate; Phosphate');
expect(compound1.dataItems.data.value(0)).toBe('0');
expect(compound2.dataItems.data.value(0)).toBe('1');
- expect(compound3.dataItems.dataHeader.value(2)).toBe('PUBCHEM_CONFORMER_DIVERSEORDER');
+ expect(compound3.dataItems.dataHeader.value(2)).toBe('<PUBCHEM_CONFORMER_DIVERSEORDER>');
expect(compound3.dataItems.data.value(2)).toBe('1\n11\n10\n3\n15\n17\n13\n5\n16\n7\n14\n9\n8\n4\n18\n6\n12\n2');
- expect(compound3.dataItems.dataHeader.value(21)).toBe('PUBCHEM_COORDINATE_TYPE');
+ expect(compound3.dataItems.dataHeader.value(21)).toBe('<PUBCHEM_COORDINATE_TYPE>');
expect(compound3.dataItems.data.value(21)).toBe('2\n5\n10');
});
});
diff --git a/src/mol-io/reader/sdf/parser.ts b/src/mol-io/reader/sdf/parser.ts
index cced43dd6320dde488417cc009448ea24605b77c..71594930183d66cdaf939bb5ff7fa41ccb119fb2 100644
--- a/src/mol-io/reader/sdf/parser.ts
+++ b/src/mol-io/reader/sdf/parser.ts
@@ -13,16 +13,20 @@ import { Tokenizer, TokenBuilder } from '../common/text/tokenizer';
import { TokenColumnProvider as TokenColumn } from '../common/text/column/token';
/** http://c4.cabrillo.edu/404/ctfile.pdf - page 41 */
+
+export interface SdfFileCompound {
+ readonly molFile: MolFile,
+ readonly dataItems: {
+ readonly dataHeader: Column<string>,
+ readonly data: Column<string>
+ }
+}
+
export interface SdfFile {
- readonly compounds: {
- readonly molFile: MolFile,
- readonly dataItems: {
- readonly dataHeader: Column<string>,
- readonly data: Column<string>
- }
- }[]
+ readonly compounds: SdfFileCompound[]
}
+
const delimiter = '$$$$';
function handleDataItems(tokenizer: Tokenizer): { dataHeader: Column<string>, data: Column<string> } {
const dataHeader = TokenBuilder.create(tokenizer.data, 32);
@@ -33,8 +37,8 @@ function handleDataItems(tokenizer: Tokenizer): { dataHeader: Column<string>, da
if (line.startsWith(delimiter)) break;
if (!line) continue;
- if (line.startsWith('> <')) {
- TokenBuilder.add(dataHeader, tokenizer.tokenStart + 3, tokenizer.tokenEnd - 1);
+ if (line.startsWith('> ')) {
+ TokenBuilder.add(dataHeader, tokenizer.tokenStart + 2, tokenizer.tokenEnd);
Tokenizer.markLine(tokenizer);
const start = tokenizer.tokenStart;
@@ -42,7 +46,7 @@ function handleDataItems(tokenizer: Tokenizer): { dataHeader: Column<string>, da
let added = false;
while (tokenizer.position < tokenizer.length) {
const line2 = Tokenizer.readLine(tokenizer);
- if (!line2 || line2.startsWith(delimiter) || line2.startsWith('> <')) {
+ if (!line2 || line2.startsWith(delimiter) || line2.startsWith('> ')) {
TokenBuilder.add(data, start, end);
added = true;
break;
diff --git a/src/mol-model-formats/structure/mol.ts b/src/mol-model-formats/structure/mol.ts
index fb66c34e8e2e80da8dce161d42c7f768e10707ad..b6847e852adbf7b8faf3e2fed75ffd21f4c37a86 100644
--- a/src/mol-model-formats/structure/mol.ts
+++ b/src/mol-model-formats/structure/mol.ts
@@ -17,7 +17,7 @@ import { ModelFormat } from '../format';
import { IndexPairBonds } from './property/bonds/index-pair';
import { Trajectory } from '../../mol-model/structure';
-async function getModels(mol: MolFile, ctx: RuntimeContext) {
+export async function getMolModels(mol: MolFile, format: ModelFormat<any> | undefined, ctx: RuntimeContext) {
const { atoms, bonds } = mol;
const MOL = Column.ofConst('MOL', mol.atoms.count, Column.Schema.str);
@@ -61,7 +61,7 @@ async function getModels(mol: MolFile, ctx: RuntimeContext) {
atom_site
});
- const models = await createModels(basics, MolFormat.create(mol), ctx);
+ const models = await createModels(basics, format ?? MolFormat.create(mol), ctx);
if (models.frameCount > 0) {
const indexA = Column.ofIntArray(Column.mapToArray(bonds.atomIdxA, x => x - 1, Int32Array));
@@ -91,5 +91,5 @@ namespace MolFormat {
}
export function trajectoryFromMol(mol: MolFile): Task<Trajectory> {
- return Task.create('Parse MOL', ctx => getModels(mol, ctx));
+ return Task.create('Parse MOL', ctx => getMolModels(mol, void 0, ctx));
}
diff --git a/src/mol-model-formats/structure/sdf.ts b/src/mol-model-formats/structure/sdf.ts
new file mode 100644
index 0000000000000000000000000000000000000000..77f9b6bf8176d6ba14331503f7d868bd8c4f0ff0
--- /dev/null
+++ b/src/mol-model-formats/structure/sdf.ts
@@ -0,0 +1,29 @@
+/**
+ * Copyright (c) 2021 mol* contributors, licensed under MIT, See LICENSE file for more info.
+ *
+ * @author David Sehnal <david.sehnal@gmail.com>
+ */
+
+import { SdfFileCompound } from '../../mol-io/reader/sdf/parser';
+import { Trajectory } from '../../mol-model/structure';
+import { Task } from '../../mol-task';
+import { ModelFormat } from '../format';
+import { getMolModels } from './mol';
+
+export { SdfFormat };
+
+type SdfFormat = ModelFormat<SdfFileCompound>
+
+namespace SdfFormat {
+ export function is(x?: ModelFormat): x is SdfFormat {
+ return x?.kind === 'sdf';
+ }
+
+ export function create(mol: SdfFileCompound): SdfFormat {
+ return { kind: 'sdf', name: mol.molFile.title, data: mol };
+ }
+}
+
+export function trajectoryFromSdf(mol: SdfFileCompound): Task<Trajectory> {
+ return Task.create('Parse SDF', ctx => getMolModels(mol.molFile, SdfFormat.create(mol), ctx));
+}
diff --git a/src/mol-plugin-state/transforms/model.ts b/src/mol-plugin-state/transforms/model.ts
index 68e9dd9676e75cb59a669105af0dd736ce8fe02c..1d5a79d4fa4e0dc71a96052f1b4fafab49ad1ecb 100644
--- a/src/mol-plugin-state/transforms/model.ts
+++ b/src/mol-plugin-state/transforms/model.ts
@@ -40,6 +40,7 @@ import { coordinatesFromXtc } from '../../mol-model-formats/structure/xtc';
import { parseXyz } from '../../mol-io/reader/xyz/parser';
import { trajectoryFromXyz } from '../../mol-model-formats/structure/xyz';
import { parseSdf } from '../../mol-io/reader/sdf/parser';
+import { trajectoryFromSdf } from '../../mol-model-formats/structure/sdf';
export { CoordinatesFromDcd };
export { CoordinatesFromXtc };
@@ -308,8 +309,8 @@ const TrajectoryFromSDF = PluginStateTransform.BuiltIn({
const models: Model[] = [];
- for (const { molFile } of parsed.result.compounds) {
- const traj = await trajectoryFromMol(molFile).runInContext(ctx);
+ for (const compound of parsed.result.compounds) {
+ const traj = await trajectoryFromSdf(compound).runInContext(ctx);
for (let i = 0; i < traj.frameCount; i++) {
models.push(await Task.resolveInContext(traj.getFrameAtIndex(i), ctx));
}