diff --git a/data/mmcif-field-names.csv b/data/mmcif-field-names.csv
index e7d8b64c4dbc8e512ab6775f8f846f71f7acc807..45602d31ed609b3422c9bff19906fd5ffe8f1ce8 100644
--- a/data/mmcif-field-names.csv
+++ b/data/mmcif-field-names.csv
@@ -106,6 +106,16 @@ pdbx_entity_branch_link.atom_stereo_config_2
pdbx_entity_branch_link.value_order
pdbx_entity_branch_link.details
+pdbx_branch_scheme.asym_id
+pdbx_branch_scheme.entity_id
+pdbx_branch_scheme.mon_id
+pdbx_branch_scheme.num
+pdbx_branch_scheme.auth_seq_num
+pdbx_branch_scheme.auth_mon_id
+pdbx_branch_scheme.auth_strand_id
+pdbx_branch_scheme.auth_ins_code
+pdbx_branch_scheme.hetero
+
pdbx_entity_descriptor.ordinal
pdbx_entity_descriptor.entity_id
pdbx_entity_descriptor.descriptor
diff --git a/src/apps/schema-generator/schema-from-cif-dic.ts b/src/apps/schema-generator/schema-from-cif-dic.ts
index 72dd804af122e1d8442f3f9f99002a2f2d6214b6..ecef972dd62070a65ff748f39688db29b95483c4 100644
--- a/src/apps/schema-generator/schema-from-cif-dic.ts
+++ b/src/apps/schema-generator/schema-from-cif-dic.ts
@@ -24,11 +24,17 @@ async function runGenerateSchema(name: string, fieldNamesPath?: string, typescri
const ihmDic = await CIF.parseText(fs.readFileSync(IHM_DIC_PATH, 'utf8')).run();
if (ihmDic.isError) throw ihmDic
+ await ensureBranchDicAvailable()
+ const branchDic = await CIF.parseText(fs.readFileSync(BRANCH_DIC_PATH, 'utf8')).run();
+ if (branchDic.isError) throw branchDic
+
const mmcifDicVersion = CIF.schema.dic(mmcifDic.result.blocks[0]).dictionary.version.value(0)
const ihmDicVersion = CIF.schema.dic(ihmDic.result.blocks[0]).dictionary.version.value(0)
- const version = `Dictionary versions: mmCIF ${mmcifDicVersion}, IHM ${ihmDicVersion}.`
+ // const branchDicVersion = CIF.schema.dic(branchDic.result.blocks[0]).dictionary.version.value(0)
+ const branchDicVersion = 'draft'
+ const version = `Dictionary versions: mmCIF ${mmcifDicVersion}, IHM ${ihmDicVersion}, entity_branch ${branchDicVersion}.`
- const frames: CifFrame[] = [...mmcifDic.result.blocks[0].saveFrames, ...ihmDic.result.blocks[0].saveFrames]
+ const frames: CifFrame[] = [...mmcifDic.result.blocks[0].saveFrames, ...ihmDic.result.blocks[0].saveFrames, ...branchDic.result.blocks[0].saveFrames]
const schema = generateSchema(frames)
const filter = fieldNamesPath ? await getFieldNamesFilter(fieldNamesPath) : undefined
@@ -70,15 +76,20 @@ async function ensureIhmDicAvailable() {
await ensureDicAvailable(IHM_DIC_PATH, IHM_DIC_URL)
}
+async function ensureBranchDicAvailable() {
+ await ensureDicAvailable(BRANCH_DIC_PATH, BRANCH_DIC_URL)
+}
+
async function ensureDicAvailable(dicPath: string, dicUrl: string) {
if (FORCE_DIC_DOWNLOAD || !fs.existsSync(dicPath)) {
- console.log('downloading mmcif dic...')
+ const name = dicUrl.substr(dicUrl.lastIndexOf('/') + 1)
+ console.log(`downloading ${name}...`)
const data = await fetch(dicUrl)
if (!fs.existsSync(DIC_DIR)) {
fs.mkdirSync(DIC_DIR);
}
fs.writeFileSync(dicPath, await data.text())
- console.log('done downloading mmcif dic')
+ console.log(`done downloading ${name}`)
}
}
@@ -87,10 +98,12 @@ const MMCIF_DIC_PATH = `${DIC_DIR}/mmcif_pdbx_v50.dic`
const MMCIF_DIC_URL = 'http://mmcif.wwpdb.org/dictionaries/ascii/mmcif_pdbx_v50.dic'
const IHM_DIC_PATH = `${DIC_DIR}/ihm-extension.dic`
const IHM_DIC_URL = 'https://raw.githubusercontent.com/ihmwg/IHM-dictionary/master/ihm-extension.dic'
+const BRANCH_DIC_PATH = `${DIC_DIR}/entity_branch-extension.dic`
+const BRANCH_DIC_URL = 'https://raw.githubusercontent.com/wwpdb-dictionaries/mmcif_pdbx/master/extensions/entity_branch-extension.dic'
const parser = new argparse.ArgumentParser({
addHelp: true,
- description: 'Create schema from mmcif dictionary (v50, downloaded from wwPDB)'
+ description: 'Create schema from mmcif dictionary (v50 plus IHM and entity_branch extensions, downloaded from wwPDB)'
});
parser.addArgument([ '--name', '-n' ], {
defaultValue: 'mmCIF',
@@ -123,5 +136,7 @@ const args: Args = parser.parseArgs();
const FORCE_DIC_DOWNLOAD = args.forceDicDownload
if (args.name) {
- runGenerateSchema(args.name, args.fieldNamesPath, args.typescript, args.out)
+ runGenerateSchema(args.name, args.fieldNamesPath, args.typescript, args.out).catch(e => {
+ console.error(e)
+ })
}
diff --git a/src/mol-io/reader/cif/schema/mmcif.ts b/src/mol-io/reader/cif/schema/mmcif.ts
index c40dc41590eaaff7db46d245e6ba3c963f05baf0..b0799e894d3049013f18076b7fe913df6b2df5fd 100644
--- a/src/mol-io/reader/cif/schema/mmcif.ts
+++ b/src/mol-io/reader/cif/schema/mmcif.ts
@@ -1,7 +1,7 @@
/**
* Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
- * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.299, IHM 0.134.
+ * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.299, IHM 0.134, entity_branch draft.
*
* @author mol-star package (src/apps/schema-generator/generate)
*/
@@ -3746,6 +3746,168 @@ export const mmCIF_Schema = {
*/
dataset_list_id: int,
},
+ /**
+ * Data items in the PDBX_ENTITY_BRANCH_LIST category specify the list
+ * of monomers in a branched entity. Allowance is made for the possibility
+ * of microheterogeneity in a sample by allowing a given sequence
+ * number to be correlated with more than one monomer ID. The
+ * corresponding ATOM_SITE entries should reflect this
+ * heterogeneity.
+ */
+ pdbx_entity_branch_list: {
+ /**
+ * This data item is a pointer to _entity.id in the ENTITY category.
+ */
+ entity_id: str,
+ /**
+ * A flag to indicate whether this monomer in the entity is
+ * heterogeneous in sequence.
+ */
+ hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+ /**
+ * This data item is a pointer to _chem_comp.id in the CHEM_COMP
+ * category.
+ */
+ comp_id: str,
+ /**
+ * The value pair _pdbx_entity_branch_list.num and _pdbx_entity_branch_list.comp_id
+ * must uniquely identify a record in the PDBX_ENTITY_BRANCH_LIST list.
+ */
+ num: int,
+ },
+ /**
+ * Data items in the PDBX_ENTITY_BRANCH_LINK category give details about
+ * the linkages between components within branched entities.
+ */
+ pdbx_entity_branch_link: {
+ /**
+ * The value of _pdbx_entity_branch_link.link_id uniquely identifies
+ * linkages within the branched entity.
+ */
+ link_id: int,
+ /**
+ * A description of special aspects of this linkage.
+ */
+ details: str,
+ /**
+ * The entity id for this branched entity.
+ *
+ * This data item is a pointer to _pdbx_entity_branch_list.entity_id
+ * in the PDBX_ENTITY_BRANCH_LIST category.
+ */
+ entity_id: str,
+ /**
+ * The component number for the first component making the linkage.
+ *
+ * This data item is a pointer to _pdbx_entity_branch_list.num
+ * in the PDBX_ENTITY_BRANCH_LIST category.
+ */
+ entity_branch_list_num_1: int,
+ /**
+ * The component number for the second component making the linkage.
+ *
+ * This data item is a pointer to _pdbx_entity_branch_list.num
+ * in the PDBX_ENTITY_BRANCH_LIST category.
+ */
+ entity_branch_list_num_2: int,
+ /**
+ * The component identifier for the first component making the linkage.
+ *
+ * This data item is a pointer to _pdbx_entity_branch_list.comp_id
+ * in the PDBX_ENTITY_BRANCH_LIST category.
+ */
+ comp_id_1: str,
+ /**
+ * The component identifier for the second component making the linkage.
+ *
+ * This data item is a pointer to _pdbx_entity_branch_list.comp_id
+ * in the PDBX_ENTITY_BRANCH_LIST category.
+ */
+ comp_id_2: str,
+ /**
+ * The atom identifier/name for the first atom making the linkage.
+ */
+ atom_id_1: str,
+ /**
+ * The leaving atom identifier/name bonded to the first atom making the linkage.
+ */
+ leaving_atom_id_1: str,
+ /**
+ * The chiral configuration of the first atom making the linkage.
+ */
+ atom_stereo_config_1: Aliased<'R' | 'S' | 'N'>(str),
+ /**
+ * The atom identifier/name for the second atom making the linkage.
+ */
+ atom_id_2: str,
+ /**
+ * The leaving atom identifier/name bonded to the second atom making the linkage.
+ */
+ leaving_atom_id_2: str,
+ /**
+ * The chiral configuration of the second atom making the linkage.
+ */
+ atom_stereo_config_2: Aliased<'R' | 'S' | 'N'>(str),
+ /**
+ * The bond order target for the chemical linkage.
+ */
+ value_order: Aliased<'sing' | 'doub' | 'trip' | 'quad' | 'arom' | 'poly' | 'delo' | 'pi'>(str),
+ },
+ /**
+ * Data items in the PDBX_ENTITY_BRANCH category specify the list
+ * of branched entities and the type.
+ */
+ pdbx_entity_branch: {
+ /**
+ * The entity id for this branched entity.
+ *
+ * This data item is a pointer to _entity.id
+ */
+ entity_id: str,
+ /**
+ * The type of this branched oligosaccharide.
+ */
+ type: Aliased<'oligosaccharide'>(str),
+ },
+ /**
+ * The PDBX_BRANCH_SCHEME category provides residue level nomenclature
+ * mapping for branch chain entitie.
+ */
+ pdbx_branch_scheme: {
+ /**
+ * This data item is a pointer to _entity.id in the ENTITY category.
+ */
+ entity_id: str,
+ /**
+ * A flag to indicate whether this monomer in the entity is
+ * heterogeneous in sequence.
+ */
+ hetero: Aliased<'no' | 'n' | 'yes' | 'y'>(str),
+ /**
+ * Pointer to _atom_site.label_asym_id.
+ */
+ asym_id: str,
+ /**
+ * This data item is a pointer to _atom_site.label_comp_id in the
+ * PDBX_ENTITY_BRANCH_LIST category.
+ */
+ mon_id: str,
+ /**
+ * This data item is a pointer to _pdbx_entity_branch_list.num in the
+ * PDBX_ENTITY_BRANCH_LIST category.
+ */
+ num: int,
+ /**
+ * This data item is a pointer to _atom_site.pdbx_auth_seq_id in the
+ * ATOM_SITE category.
+ */
+ auth_seq_num: str,
+ /**
+ * This data item is a pointer to _atom_site.pdbx_auth_comp_id in the
+ * ATOM_SITE category.
+ */
+ auth_mon_id: str,
+ },
}
export type mmCIF_Schema = typeof mmCIF_Schema;
diff --git a/src/mol-model/structure/export/mmcif.ts b/src/mol-model/structure/export/mmcif.ts
index dd9c71b1f3b64573eacbb03d828bc96f812b62b9..2bfa34c5609985e4f10e006109f0baffbeb80905 100644
--- a/src/mol-model/structure/export/mmcif.ts
+++ b/src/mol-model/structure/export/mmcif.ts
@@ -70,9 +70,15 @@ const Categories = [
copy_mmCif_category('entity_poly'),
copy_mmCif_category('entity_poly_seq'),
+ // Branch
+ copy_mmCif_category('pdbx_entity_branch'),
+ copy_mmCif_category('pdbx_entity_branch_link'),
+ copy_mmCif_category('pdbx_branch_scheme'),
+
// Misc
// TODO: filter for actual present residues?
copy_mmCif_category('chem_comp'),
+ copy_mmCif_category('pdbx_chem_comp_identifier'),
copy_mmCif_category('atom_sites'),
_pdbx_struct_mod_residue,