Merge branch 'main' into clinvar-id-change

CHANGELOG.md

@@ -2,6 +2,32 @@
 
 All notable changes to this project will be documented in this file. See [standard-version](https://github.com/conventional-changelog/standard-version) for commit guidelines.
 
+## [3.10.0](https://github.com/biothings/biomedical_id_resolver.js/compare/v3.9.1...v3.10.0) (2021-08-16)
+
+
+### Features
+
+* support Disease NCIT, SNOMEDCT IDs ([9cc4908](https://github.com/biothings/biomedical_id_resolver.js/commit/9cc4908a62fe176212e0f2b23ed0d9ca381b7c83))
+
+
+### Bug Fixes
+
+* add BiologicalProcess KEGG back in ([ccf257a](https://github.com/biothings/biomedical_id_resolver.js/commit/ccf257a6041d01157d6646113b1ff699145d63f6))
+* add ClinicalFinding semantic type ([56f083f](https://github.com/biothings/biomedical_id_resolver.js/commit/56f083ff06406bdb5d8ebc59d0ebe40319928c4b))
+* add Disease, SequenceVariant mappings ([e36bc09](https://github.com/biothings/biomedical_id_resolver.js/commit/e36bc091d1f1988441fd96f987829fe146f65de0))
+* add MEDDRA id mapping for Disease semantic type ([e914976](https://github.com/biothings/biomedical_id_resolver.js/commit/e9149760a1361389b27d5b674545f897068a16a6))
+* add Pathway GO, SMPDB IDs ([c8b2556](https://github.com/biothings/biomedical_id_resolver.js/commit/c8b2556846dcf8d482cfabab85cb39afdf6b37db))
+* adjust fields for mapping SNOMEDCT ([88dd2a4](https://github.com/biothings/biomedical_id_resolver.js/commit/88dd2a49021bfc42b22ade2936fb0f56d7a80e80))
+* config + types file: ChemicalSubstance -> SmallMolecule, drug semantic type ([2cfbe88](https://github.com/biothings/biomedical_id_resolver.js/commit/2cfbe889bc32d070a2712a7dbbc43649ecdaa754))
+* quick fixes to README to match config file ([da6df54](https://github.com/biothings/biomedical_id_resolver.js/commit/da6df549d54837d340501a8424e7a7166be241a0))
+* reformatting, add mappings + ID prefixes ([546f5a7](https://github.com/biothings/biomedical_id_resolver.js/commit/546f5a70f6f2a003e737e27a0133440829d8095a))
+* remove ChemicalSubstance support ([d78a30f](https://github.com/biothings/biomedical_id_resolver.js/commit/d78a30f7fd254812a808ca2479d0a3c759d7b3ff))
+* simple changes ([df2139c](https://github.com/biothings/biomedical_id_resolver.js/commit/df2139c70c3be0292fddf9e1a6bcfa78961874d6))
+* try to add backwards compatibility for ChemicalSubstance ([987ab97](https://github.com/biothings/biomedical_id_resolver.js/commit/987ab97fb52fb9baa94f3bd425f19857c130065e))
+* update README to reflect config/types file changes ([3792602](https://github.com/biothings/biomedical_id_resolver.js/commit/3792602fcc361b65f5551b13451f3fa7f4d2b1a1))
+* update rhea tests ([95ec48f](https://github.com/biothings/biomedical_id_resolver.js/commit/95ec48f23e9eca197f1d31db61815afb163fb845))
+* update tests for ChemicalSubstance -> SmallMolecule ([0699af0](https://github.com/biothings/biomedical_id_resolver.js/commit/0699af00ede0dedbb063bf405c7d59159ce517f7))
+
 ### [3.9.1](https://github.com/biothings/biomedical_id_resolver.js/compare/v3.9.0...v3.9.1) (2021-06-22)
 
 ## [3.9.0](https://github.com/kevinxin90/biomedical_id_resolver.js/compare/v3.8.0...v3.9.0) (2021-04-27)

README.md

@@ -1,10 +1,10 @@
-![Test Coveralls](https://github.com/kevinxin90/biomedical_id_resolver.js/workflows/Test%20Coveralls/badge.svg)
-[![Coverage Status](https://coveralls.io/repos/github/kevinxin90/biomedical_id_resolver.js/badge.svg?branch=master)](https://coveralls.io/github/kevinxin90/biomedical_id_resolver.js?branch=master)
+![Test Coveralls](https://github.com/biothings/biomedical_id_resolver.js/workflows/Test%20Coveralls/badge.svg)
+[![Coverage Status](https://coveralls.io/repos/github/biothings/biomedical_id_resolver.js/badge.svg?branch=main)](https://coveralls.io/github/biothings/biomedical_id_resolver.js?branch=main)
 ![npm](https://img.shields.io/npm/dw/biomedical_id_resolver)
-![GitHub issues](https://img.shields.io/github/issues/kevinxin90/biomedical_id_resolver.js)
+![GitHub issues](https://img.shields.io/github/issues/biothings/biomedical_id_resolver.js)
 ![NPM](https://img.shields.io/npm/l/biomedical_id_resolver)
 ![npm](https://img.shields.io/npm/v/biomedical_id_resolver?style=plastic)
-![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/kevinxin90/biomedical_id_resolver.js)
+![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/biothings/biomedical_id_resolver.js)
 
 
 
@@ -25,7 +25,7 @@ const resolve = require('biomedical_id_resolver');
 // input should be an object, with semantic type as the key, and array of CURIEs as value
 let input = {
     "Gene": ["NCBIGene:1017", "NCBIGene:1018", "HGNC:1177"],
-    "ChemicalSubstance": ["CHEBI:15377"],
+    "SmallMolecule": ["CHEBI:15377"],
     "Disease": ["MONDO:0004976"],
     "Cell": ["CL:0002372"]
   };
@@ -104,43 +104,76 @@ let input = {
 
 ## Available Semantic Types & prefixes
 
-> Gene ID resolution is done through MyGene.info API
+> Gene, Transcript, Protein ID resolution is done through MyGene.info API
 
 - Gene
   1. NCBIGene
   2. ENSEMBL
   3. HGNC
-  4. SYMBOL
+  4. MGI
   5. OMIM
-  6. UniProtKB
-  7. UMLS
-  8. name
+  6. UMLS
+  7. SYMBOL
+  8. UniProtKB
+  9. name
+
+- Transcript
+  1. ENSEMBL
+  2. SYMBOL
+  3. name
+
+- Protein
+  1. UniProtKB
+  2. ENSEMBL
+  3. UMLS
+  4. SYMBOL
+  5. name
 
 > Variant ID resolution is done through MyVariant.info API
 
 - SequenceVariant
-  1. HGVS
+  1. CLINVAR
   2. DBSNP
-  3. MYVARIANT_HG19
-  4. ClinVar
+  3. HGVS
+  4. MYVARIANT_HG19
 
-> ChemicalSubstance ID resolution is done through MyChem.info API
+> SmallMolecule, Drug ID resolution is done through MyChem.info API
 
-- ChemicalSubstance
-    1. CHEBI
+- SmallMolecule
+    1. PUBCHEM.COMPOUND
     2. CHEMBL.COMPOUND
+    3. UNII
+    4. CHEBI
+    5. DRUGBANK
+    6. MESH
+    7. CAS
+    8. HMDB
+    9. KEGG.COMPOUND
+    10. INCHI
+    11. INCHIKEY
+    12. UMLS
+    13. LINCS
+    14. name
+
+- Drug
+    1. RXCUI
+    2. NDC
     3. DRUGBANK
-    4. PUBCHEM
-    5. MESH
-    6. INCHI
-    7. INCHIKEY
-    8. UNII
-    9. KEGG
-    10. UMLS
-    11. name
-    12. id
-
-> Disease ID Resolution is done through MyDisease.info API
+    4. PUBCHEM.COMPOUND
+    5. CHEMBL.COMPOUND
+    6. UNII
+    7. CHEBI
+    8. MESH
+    9. CAS
+    10. HMDB
+    11. KEGG.COMPOUND
+    12. INCHI
+    13. INCHIKEY
+    14. UMLS
+    15. LINCS
+    16. name
+
+> Disease, ClinicalFinding ID Resolution is done through MyDisease.info API
 
 - Disease
 
@@ -151,80 +184,88 @@ let input = {
   5. EFO
   6. UMLS
   7. MESH
-  8. GARD
-  9. name
+  8. MEDDRA
+  9. NCIT
+  10. SNOMEDCT
+  11. HP
+  12. GARD
+  13. name
+
+- ClinicalFinding
+  1. LOINC
+  2. NCIT
+  3. EFO
+  4. name
 
 > Pathway ID Resolution is done through biothings.ncats.io/geneset API
 
 - Pathway
-  1. Reactome
-  2. KEGG
-  3. PHARMGKB
-  4. WIKIPATHWAYS
-  5. name
+  1. GO
+  2. REACT
+  3. KEGG
+  4. SMPDB
+  5. PHARMGKB.PATHWAYS
+  6. WIKIPATHWAYS
+  7. BIOCARTA
+  8. name
 
 > MolecularActivity ID Resolution is done through BioThings Gene Ontology Molecular Activity API
 
 - MolecularActivity
   1. GO
-  2. MetaCyc
+  2. REACT
   3. RHEA
-  4. KEGG.REACTION
-  5. Reactome
+  4. MetaCyc
+  5. KEGG.REACTION
+  6. name
 
 > CellularComponent ID Resolution is done through BioThings Gene Ontology Cellular Component API
 
 - CellularComponent
   1. GO
-  2. MESH
-  3. UMLS
-  4. NCIT
-  5. SNOMEDCT
-  6. UBERON
-  7. CL
-  8. name
+  2. MetaCyc
+  3. name
 
 > BiologicalProcess ID Resolution is done through BioThings Gene Ontology Biological Process API
 
 - BiologicalProcess
 
   1. GO
-  2. MetaCyc
-  3. Reactome
-  4. name
+  2. REACT
+  3. MetaCyc
+  4. KEGG
+  5. name
 
 > AnatomicalEntity ID Resolution is done through BioThings UBERON API
 
 - AnatomicalEntity
   1. UBERON
   2. UMLS
-  3. NCIT
-  4. MESH
+  3. MESH
+  4. NCIT
   5. name
 
 > PhenotypicFeature ID Resolution is done through BioThings HPO API
 
 - PhenotypicFeature
-  1. UMLS
-  2. SNOMEDCT
-  3. HP
-  4. MEDDRA
-  5. EFO
-  6. NCIT
-  7. MESH
-  8. MP
+  1. HP
+  2. EFO
+  3. NCIT
+  4. UMLS
+  5. MEDDRA
+  6. MP
+  7. SNOMEDCT
+  8. MESH
   9. name
 
-> Cell ID Resolution is done through nodenormalization API
+> Cell ID Resolution is done through Biothings Cell Ontology API
 
 - Cell
   1. CL
-  2. UMLS
-  3. NCIT
-  4. MESH
-  5. UBERON
-  6. SNOMEDCT
-  7. name
+  2. NCIT
+  3. MESH
+  4. EFO
+  5. name
 
 ## Development
 
@@ -234,9 +275,9 @@ let input = {
 3. Run `npm ci` to install the dependencies.
 4. scripts are stored in `/src` folder
 5. Add test to `/__tests__` folder
-6. run `npm run release` to bump version and generte change log
+6. run `npm run release` to bump version and generate change log
 7. run `npx depcheck` to check for unused packages in package.json
 
 ## CHANGELOG
 
-See [CHANGELOG.md](https://github.com/kevinxin90/biomedical_id_resolver.js/blob/master/CHANGELOG.md)
+See [CHANGELOG.md](https://github.com/biothings/biomedical_id_resolver.js/blob/main/CHANGELOG.md)

__tests__/integration/biolink_based_resolver.test.ts

@@ -16,14 +16,14 @@ describe("Test ID Resolver", () => {
 
     test("Test BioThings output include integer should be converted to string", async () => {
         const resolver = new BioLinkBasedResolver();
-        const res = await resolver.resolve({ "ChemicalSubstance": ["CHEMBL.COMPOUND:CHEMBL744"] });
+        const res = await resolver.resolve({ "SmallMolecule": ["CHEMBL.COMPOUND:CHEMBL744"] });
         expect(res['CHEMBL.COMPOUND:CHEMBL744'][0]).toBeInstanceOf(ResolvableBioEntity);
         expect(res['CHEMBL.COMPOUND:CHEMBL744'][0].dbIDs["PUBCHEM.COMPOUND"]).toEqual(["5070"]);
     })
 
     test("Test valid inputs from multiple semantic types should be corretly resolved", async () => {
         const resolver = new BioLinkBasedResolver();
-        const res = await resolver.resolve({ "Gene": ["NCBIGene:1017"], "ChemicalSubstance": ["DRUGBANK:DB01609"] });
+        const res = await resolver.resolve({ "Gene": ["NCBIGene:1017"], "SmallMolecule": ["DRUGBANK:DB01609"] });
         expect(res).toHaveProperty("NCBIGene:1017");
         expect(res['NCBIGene:1017']).toHaveLength(1);
         expect(res['NCBIGene:1017'][0]).toBeInstanceOf(ResolvableBioEntity);
@@ -52,7 +52,7 @@ describe("Test ID Resolver", () => {
         const resolver = new BioLinkBasedResolver();
         const res = await resolver.resolve({
             Gene: [...fakeNCBIGeneInputs, ...fakeOMIMGeneInputs],
-            ChemicalSubstance: fakeDrugbankInputs
+            SmallMolecule: fakeDrugbankInputs
         })
         expect(Object.keys(res)).toHaveLength(fakeDrugbankInputs.length + fakeNCBIGeneInputs.length + fakeOMIMGeneInputs.length);
         expect(res['OMIM:0'][0]).toBeInstanceOf(IrresolvableBioEntity)
@@ -127,7 +127,7 @@ describe("Test ID Resolver", () => {
 
     test("Test input with space in it should be correctly resolved", async () => {
         const resolver = new BioLinkBasedResolver();
-        const res = await resolver.resolve({ "ChemicalSubstance": ["name:Regorafenib", "name:Sunitinib", "name:Imatinib", "name:Ponatinib", "name:Dasatinib", "name:Bosutinib", "name:Imatinib Mesylate"] });
+        const res = await resolver.resolve({ "SmallMolecule": ["name:Regorafenib", "name:Sunitinib", "name:Imatinib", "name:Ponatinib", "name:Dasatinib", "name:Bosutinib", "name:Imatinib Mesylate"] });
         expect(res).toHaveProperty("name:Imatinib Mesylate");
         expect(res).toHaveProperty("name:Regorafenib");
         expect(res["name:Imatinib Mesylate"]).toHaveLength(1);

__tests__/integration/biolink_based_validator.test.ts

@@ -79,11 +79,11 @@ describe("Integration test for BioLink Based Validator", () => {
 
     test("Item with comma in it should be counted as irresolvable", () => {
         const input = {
-            ChemicalSubstance: ["KEGG:1,2"]
+            SmallMolecule: ["KEGG:1,2"]
         }
         const validator = new BioLinkBasedValidator(input);
         validator.validate();
         expect(validator.resolvable).toEqual({});
-        expect(validator.irresolvable).toHaveProperty('ChemicalSubstance', ["KEGG:1,2"]);
+        expect(validator.irresolvable).toHaveProperty('SmallMolecule', ["KEGG:1,2"]);
     })
 })