diff --git a/README.md b/README.md
index 6544cb77d7cdc4517cbac92842c2c3452093d095..56b4a5658081517fc00215f598ab4d98e9578421 100644
--- a/README.md
+++ b/README.md
@@ -100,8 +100,6 @@ Run the image
node build/node_modules/apps/schema-generator/schema-from-cif-dic.js -ts -o src/mol-io/reader/cif/schema/bird.ts --fieldNamesPath data/bird-field-names.csv --name BIRD
- node --max-old-space-size=8192 build/node_modules/apps/chem-comp-bond/create-table.js build/data/ccb.bcif -b
-
**GraphQL schemas**
node data/rcsb-graphql/codegen.js
diff --git a/data/mmcif-field-names.csv b/data/mmcif-field-names.csv
index fba153c636ab478f0cdf50ec74a25b7e2245bfa5..cf042045e4dd08ac3965b595057ec935e8484c9d 100644
--- a/data/mmcif-field-names.csv
+++ b/data/mmcif-field-names.csv
@@ -47,6 +47,15 @@ pdbx_chem_comp_identifier.program
pdbx_chem_comp_identifier.program_version
pdbx_chem_comp_identifier.identifier
+pdbx_chem_comp_related.comp_id
+pdbx_chem_comp_related.related_comp_id
+pdbx_chem_comp_related.relationship_type
+pdbx_chem_comp_related.details
+
+pdbx_chem_comp_synonyms.comp_id
+pdbx_chem_comp_synonyms.name
+pdbx_chem_comp_synonyms.provenance
+
cell.entry_id
cell.length_a
cell.length_b
diff --git a/src/apps/schema-generator/schema-from-cif-dic.ts b/src/apps/schema-generator/schema-from-cif-dic.ts
index ecef972dd62070a65ff748f39688db29b95483c4..88bd34a8fbb078fe171f0a0c9957d87772df3498 100644
--- a/src/apps/schema-generator/schema-from-cif-dic.ts
+++ b/src/apps/schema-generator/schema-from-cif-dic.ts
@@ -24,17 +24,20 @@ 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
+ await ensureCarbBranchDicAvailable()
+ const carbBranchDic = await CIF.parseText(fs.readFileSync(CARB_BRANCH_DIC_PATH, 'utf8')).run();
+ if (carbBranchDic.isError) throw carbBranchDic
+
+ await ensureCarbCompDicAvailable()
+ const carbCompDic = await CIF.parseText(fs.readFileSync(CARB_COMP_DIC_PATH, 'utf8')).run();
+ if (carbCompDic.isError) throw carbCompDic
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 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 carbDicVersion = 'draft'
+ const version = `Dictionary versions: mmCIF ${mmcifDicVersion}, IHM ${ihmDicVersion}, CARB ${carbDicVersion}.`
- const frames: CifFrame[] = [...mmcifDic.result.blocks[0].saveFrames, ...ihmDic.result.blocks[0].saveFrames, ...branchDic.result.blocks[0].saveFrames]
+ const frames: CifFrame[] = [...mmcifDic.result.blocks[0].saveFrames, ...ihmDic.result.blocks[0].saveFrames, ...carbBranchDic.result.blocks[0].saveFrames, ...carbCompDic.result.blocks[0].saveFrames]
const schema = generateSchema(frames)
const filter = fieldNamesPath ? await getFieldNamesFilter(fieldNamesPath) : undefined
@@ -68,17 +71,10 @@ async function getFieldNamesFilter(fieldNamesPath: string): Promise<Filter> {
return filter
}
-async function ensureMmcifDicAvailable() {
- await ensureDicAvailable(MMCIF_DIC_PATH, MMCIF_DIC_URL)
-}
-
-async function ensureIhmDicAvailable() {
- await ensureDicAvailable(IHM_DIC_PATH, IHM_DIC_URL)
-}
-
-async function ensureBranchDicAvailable() {
- await ensureDicAvailable(BRANCH_DIC_PATH, BRANCH_DIC_URL)
-}
+async function ensureMmcifDicAvailable() { await ensureDicAvailable(MMCIF_DIC_PATH, MMCIF_DIC_URL) }
+async function ensureIhmDicAvailable() { await ensureDicAvailable(IHM_DIC_PATH, IHM_DIC_URL) }
+async function ensureCarbBranchDicAvailable() { await ensureDicAvailable(CARB_BRANCH_DIC_PATH, CARB_BRANCH_DIC_URL) }
+async function ensureCarbCompDicAvailable() { await ensureDicAvailable(CARB_COMP_DIC_PATH, CARB_COMP_DIC_URL) }
async function ensureDicAvailable(dicPath: string, dicUrl: string) {
if (FORCE_DIC_DOWNLOAD || !fs.existsSync(dicPath)) {
@@ -98,8 +94,10 @@ const MMCIF_DIC_PATH = `${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 CARB_BRANCH_DIC_PATH = `${DIC_DIR}/entity_branch-extension.dic`
+const CARB_BRANCH_DIC_URL = 'https://raw.githubusercontent.com/pdbxmmcifwg/carbohydrate-extension/master/dict/entity_branch-extension.dic'
+const CARB_COMP_DIC_PATH = `${DIC_DIR}/chem_comp-extension.dic`
+const CARB_COMP_DIC_URL = 'https://raw.githubusercontent.com/pdbxmmcifwg/carbohydrate-extension/master/dict/chem_comp-extension.txt'
const parser = new argparse.ArgumentParser({
addHelp: true,
diff --git a/src/mol-io/reader/cif/schema/bird.ts b/src/mol-io/reader/cif/schema/bird.ts
index 5cf18d4663f9ec48ae251730e3174961f9cb5c1b..a4398188b62edbe7dac06619f83260f744fc6ccb 100644
--- a/src/mol-io/reader/cif/schema/bird.ts
+++ b/src/mol-io/reader/cif/schema/bird.ts
@@ -1,7 +1,7 @@
/**
* Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
- * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.299, IHM 0.134.
+ * Code-generated 'BIRD' schema file. Dictionary versions: mmCIF 5.300, IHM 0.136, CARB draft.
*
* @author mol-star package (src/apps/schema-generator/generate)
*/
diff --git a/src/mol-io/reader/cif/schema/ccd.ts b/src/mol-io/reader/cif/schema/ccd.ts
index 06a77ba67de4616307baa458397f54a9a9809e5c..d8d61e76b4a783703f0f842da7710b4db9c77914 100644
--- a/src/mol-io/reader/cif/schema/ccd.ts
+++ b/src/mol-io/reader/cif/schema/ccd.ts
@@ -1,7 +1,7 @@
/**
* Copyright (c) 2017-2018 mol* contributors, licensed under MIT, See LICENSE file for more info.
*
- * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.299, IHM 0.134.
+ * Code-generated 'CCD' schema file. Dictionary versions: mmCIF 5.300, IHM 0.136, CARB draft.
*
* @author mol-star package (src/apps/schema-generator/generate)
*/
diff --git a/src/mol-io/reader/cif/schema/mmcif.ts b/src/mol-io/reader/cif/schema/mmcif.ts
index d2565a478cdb4bb7a9deebaacf3afec883279d59..8cb54134c190888954e50550a6bdb0571ac75dcf 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, entity_branch draft.
+ * Code-generated 'mmCIF' schema file. Dictionary versions: mmCIF 5.300, IHM 0.136, CARB draft.
*
* @author mol-star package (src/apps/schema-generator/generate)
*/
@@ -1470,6 +1470,54 @@ export const mmCIF_Schema = {
*/
'space_group_name_H-M': str,
},
+ /**
+ * The PDBX_NONPOLY_SCHEME category provides residue level nomenclature
+ * mapping for non-polymer entities.
+ */
+ pdbx_nonpoly_scheme: {
+ /**
+ * Pointer to _atom_site.label_asym_id.
+ */
+ asym_id: str,
+ /**
+ * Pointer to _atom_site.label_entity_id.
+ */
+ entity_id: str,
+ /**
+ * Pointer to _atom_site.label_comp_id.
+ */
+ mon_id: str,
+ /**
+ * PDB strand/chain id.
+ */
+ pdb_strand_id: str,
+ /**
+ * NDB/RCSB residue number.
+ */
+ ndb_seq_num: str,
+ /**
+ * PDB residue number.
+ */
+ pdb_seq_num: str,
+ /**
+ * Author provided residue numbering. This value may differ from the PDB residue
+ * number and may not correspond to residue numbering within the coordinate records.
+ */
+ auth_seq_num: str,
+ /**
+ * PDB residue identifier.
+ */
+ pdb_mon_id: str,
+ /**
+ * Author provided residue identifier. This value may differ from the PDB residue
+ * identifier and may not correspond to residue identification within the coordinate records.
+ */
+ auth_mon_id: str,
+ /**
+ * PDB insertion code.
+ */
+ pdb_ins_code: str,
+ },
/**
* Data items in the CHEM_COMP_IDENTIFIER category provide
* identifiers for chemical components.
@@ -1934,7 +1982,7 @@ export const mmCIF_Schema = {
/**
* This data item contains the descriptor type.
*/
- type: Aliased<'LINUCS' | 'IUPAC' | 'IUPAC Abbreviated'>(str),
+ type: Aliased<'LINUCS'>(str),
/**
* This data item contains the name of the program
* or library used to compute the descriptor.
@@ -1950,18 +1998,6 @@ export const mmCIF_Schema = {
*/
ordinal: int,
},
- pdbx_nonpoly_scheme: {
- asym_id: str,
- entity_id: str,
- mon_id: str,
- ndb_seq_num: int,
- pdb_seq_num: int,
- auth_seq_num: int,
- pdb_mon_id: str,
- auth_mon_id: str,
- pdb_strand_id: str,
- pdb_ins_code: str
- },
/**
* Data items in the IHM_STARTING_MODEL_DETAILS category records the
* details about structural models used as starting inputs in
@@ -1974,7 +2010,7 @@ export const mmCIF_Schema = {
starting_model_id: str,
/**
* A unique identifier for the distinct molecular entities.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -2165,8 +2201,8 @@ export const mmCIF_Schema = {
segment_id: int,
/**
* A unique identifier distinct molecular entities.
- * This data item is a pointer to _entity_poly_seq.entity_id in the
- * ENTITY_POLY_SEQ category.
+ * This data item is a pointer to _entity.id in the
+ * ENTITY category.
*/
entity_id: str,
/**
@@ -2181,10 +2217,12 @@ export const mmCIF_Schema = {
entity_asym_id: str,
/**
* The leading residue index for the sequence segment modeled using this starting model.
+ * This data item is a pointer to _entity_poly_seq.num in the ENTITY_POLY_SEQ category.
*/
seq_id_begin: int,
/**
* The trailing residue index for the sequence segment modeled using this starting model.
+ * This data item is a pointer to _entity_poly_seq.num in the ENTITY_POLY_SEQ category.
*/
seq_id_end: int,
/**
@@ -2244,8 +2282,8 @@ export const mmCIF_Schema = {
entity_description: str,
/**
* A unique identifier for distinct molecular entities.
- * This data item is a pointer to _entity_poly_seq.entity_id in the
- * ENTITY_POLY_SEQ category.
+ * This data item is a pointer to _entity.id in the
+ * ENTITY category.
*/
entity_id: str,
/**
@@ -2257,11 +2295,13 @@ export const mmCIF_Schema = {
/**
* The starting residue index for the sequence segment of the entity instance
* that is part of the assembly.
+ * This data item is a pointer to _entity_poly_seq.num in the ENTITY_POLY_SEQ category.
*/
seq_id_begin: int,
/**
* The ending residue index for the sequence segment of the entity instance
* that is part of the assembly.
+ * This data item is a pointer to _entity_poly_seq.num in the ENTITY_POLY_SEQ category.
*/
seq_id_end: int,
},
@@ -2612,7 +2652,7 @@ export const mmCIF_Schema = {
/**
* The type of data held in the dataset.
*/
- data_type: Aliased<'NMR data' | '3DEM volume' | '2DEM class average' | 'EM raw micrographs' | 'SAS data' | 'CX-MS data' | 'Mass Spectrometry data' | 'EPR data' | 'H/D exchange data' | 'Single molecule FRET data' | 'Experimental model' | 'Comparative model' | 'Integrative model' | 'De Novo model' | 'Predicted contacts' | 'Mutagenesis data' | 'DNA footprinting data' | 'Yeast two-hybrid screening data' | 'Other'>(str),
+ data_type: Aliased<'NMR data' | '3DEM volume' | '2DEM class average' | 'EM raw micrographs' | 'SAS data' | 'CX-MS data' | 'Mass Spectrometry data' | 'EPR data' | 'H/D exchange data' | 'Single molecule FRET data' | 'Experimental model' | 'Comparative model' | 'Integrative model' | 'De Novo model' | 'Predicted contacts' | 'Mutagenesis data' | 'DNA footprinting data' | 'Hydroxyl radical footprinting data' | 'Yeast two-hybrid screening data' | 'Other'>(str),
/**
* A flag that indicates whether the dataset is archived in
* an IHM related database or elsewhere.
@@ -2821,7 +2861,7 @@ export const mmCIF_Schema = {
ensemble_id: int,
/**
* The entity identifier corresponding to this localization density.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -3009,7 +3049,7 @@ export const mmCIF_Schema = {
/**
* The type of crosslinker used.
*/
- linker_type: Aliased<'EDC' | 'DSS' | 'EGS' | 'BS3' | 'BS2G' | 'DST' | 'sulfo-SDA' | 'sulfo-SMCC' | 'Other'>(str),
+ linker_type: Aliased<'EDC' | 'DSS' | 'EGS' | 'BS3' | 'BS2G' | 'DST' | 'sulfo-SDA' | 'sulfo-SMCC' | 'DSSO' | 'Other'>(str),
/**
* Identifier to the crosslinking dataset.
* This data item is a pointer to the _ihm_dataset_list.id in the
@@ -3423,7 +3463,7 @@ export const mmCIF_Schema = {
type_symbol: str,
/**
* The entity identifier corresponding to this coordinate position.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -3434,7 +3474,7 @@ export const mmCIF_Schema = {
atom_id: str,
/**
* The component identifier corresponding to this coordinate position.
- * This data item is a pointer to _entity_poly_seq.mon_id in the ENTITY_POLY category.
+ * This data item is a pointer to _chem_comp.id in the CHEM_COMP category.
*/
comp_id: str,
/**
@@ -3477,7 +3517,7 @@ export const mmCIF_Schema = {
ordinal_id: int,
/**
* The entity identifier corresponding to this sphere object.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -3534,7 +3574,7 @@ export const mmCIF_Schema = {
ordinal_id: int,
/**
* The entity identifier corresponding to this gaussian object.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -3590,7 +3630,7 @@ export const mmCIF_Schema = {
ordinal_id: int,
/**
* The entity identifier corresponding to this gaussian object.
- * This data item is a pointer to _entity_poly_seq.entity_id in the ENTITY_POLY category.
+ * This data item is a pointer to _entity.id in the ENTITY category.
*/
entity_id: str,
/**
@@ -3789,7 +3829,7 @@ export const mmCIF_Schema = {
},
/**
* Data items in the PDBX_ENTITY_BRANCH_LINK category give details about
- * the linkages between components within branched entities.
+ * the linkages between components within a branched entity.
*/
pdbx_entity_branch_link: {
/**
@@ -3883,7 +3923,7 @@ export const mmCIF_Schema = {
},
/**
* The PDBX_BRANCH_SCHEME category provides residue level nomenclature
- * mapping for branch chain entitie.
+ * mapping for branch chain entities.
*/
pdbx_branch_scheme: {
/**
@@ -3920,6 +3960,44 @@ export const mmCIF_Schema = {
*/
auth_mon_id: str,
},
+ /**
+ * PDBX_CHEM_COMP_SYNONYMS holds chemical name and synonym correspondences.
+ */
+ pdbx_chem_comp_synonyms: {
+ /**
+ * The synonym of this particular chemical component.
+ */
+ name: str,
+ /**
+ * The chemical component for which this synonym applies.
+ */
+ comp_id: str,
+ /**
+ * The provenance of this synonym.
+ */
+ provenance: Aliased<'AUTHOR' | 'DRUGBANK' | 'CHEBI' | 'CHEMBL' | 'PDB' | 'PUBCHEM'>(str),
+ },
+ /**
+ * PDBX_CHEM_COMP_RELATED describes the relationship between two chemical components.
+ */
+ pdbx_chem_comp_related: {
+ /**
+ * The chemical component for which this relationship applies.
+ */
+ comp_id: str,
+ /**
+ * The related chemical component for which this chemical component is based.
+ */
+ related_comp_id: str,
+ /**
+ * Describes the type of relationship
+ */
+ relationship_type: Aliased<'Carbohydrate core' | 'Precursor'>(str),
+ /**
+ * Describes the type of relationship
+ */
+ details: str,
+ },
}
export type mmCIF_Schema = typeof mmCIF_Schema;