Databases, lexical resources and nomenclatures
- PubChem
- Jochem
- MeSH (substance record)
- ChEBI
- ChEMBL
- DrugBank
- ChemSpider
- HMDB
- RxNorm
- UMLS
- KEGG DRUG
- KEGG COMPOUND
- Wikipedia (some categories)
- International Nonproprietary Name (INN) provides useful name stems
- British Approved Name (BAN)
- European Pharmacopoeia
- United States Adopted Name (USAN)
- Drug nomenclature
- Comparative Toxicogenomics Database
- Hazardous Substances Data Bank
- NIAID ChemDB
- Therapeutic Target Database (TTD)
- ChemIDplus
- MedlinePlus: drug generic or brand names
- NCI Drug Dictionary
- LookChem
Chemical/drug NER/indexing programs
- Oscar3
- Oscar4
- ChemicalTagger
- ChemSpot
- Reflect
- MetaMap
- Whatizit(see whatizitChebiDictCh, whatizitCheponer, whatizitEuropePmc, whatizitOscar3, whatizitDrugs, whatizitChemicals)
- MiniChem/Drug Tagger (a GATE plugin - more info)
- STITCH
- Polysearch
- FACTA+
- PubTator
- ChemProt
- ChemEx
- NCBO Annotator (ChEBI ontology)
- chemicalize.org
- Cocoa
- LeadMine
Useful Machine Learning and NER software (short)
- Standford Core NLP(Java)
- Standford NER(Java)
- LingPipe(Java)
- OpenNLP(Java)
- Mallet(Java)
- CRF++(C/C++)
- CRFsuite(C/C++)
- FlexCRF(C/C++)
- Weka
- LibSVM
- SVMLight
