Home Aims & Objectives NaCTeM Services Text Mining Tools Internal External UIMA U-Compare Resources Terms & Conditions FAQ News & Events People Projects Publications Community External Collaboration Vacancies Teaching & Tutorials Feedback How to find us Site Map Search

External Text Mining Software

In addition to tools and service systems developed or customised by The National Centre for Text Mining, we provide the following links to useful text mining resources developed by other members of the community.

• Information Retrieval
• Natural Language Processing
  
  • Part-of-speech Taggers
  • Acronym Recognition
  • Named Entity Recognisers
  • Parsers
    
• Information Extraction
• Biomedical Applications
  
  • NCIBI Tools: A suite of tools developed in the National Center for Integrative Biomedical Informatics (NCIBI), including NLP tools, search tools, network analysis tools, visualisation tools etc.
  • Arrowsmith Compendium -- A list of free, public Biomedical Text Mining tools available on the Web.
  • Bio-NLP resources database (BioNLPdb) -- A list of commented links to major bionlp tools and resources.
  • Protein Interaction Discovery
  • Biomedical Search
  • Annotation Tools
  • Gene Expression Data Analysis
• Biomedical Search Engines
  • EBIMed: A web-based search system developed by EBI (European Bioinformatics Institute) which combines information retrieval and extraction from Medline. In particular, it uses HitPair table to show the co-occurrence information of named entities.
  • FABLE: Fast Automated Biomedical Literature Extraction. FABLE mines the biomedical literature for information about human genes and proteins. FABLE v3 allows a user to find articles mentioning a gene of interest (Article Finder), to generate a list of genes associated with one or more keywords (Gene Lister), or use a local mirror of the UCSC Genome Browser with a literature track (LitTrack).
  • GoPubMed: An ontology-based key-word search system for PUBMED developed by Transinsight and TU Dresden, Germany. For a given query, the resultant abstracts are classified using Gene Ontology terms.
  • Novoseek: A search engine and information extraction system for biomedical literature, developed by Bioalma. Key biomedical concepts related to searches are identified and highlighted. Information relating to identified concepts may be viewed, in addition to relevant bibliographic information.
  • Pharmspresso: An information retrieval and extraction system for pharmacogenomic-related literature developed in the lab of Russ Altman at Stanford University.
  • PubFinder: Given a small set of seed abstracts relevant to a specific scientific topic, it produces a "hit-list of references" ranked according to likelihood.
  • Query Science: A Google-powered web searching system which provides three search models:
    • Query Chem: Combine text and chemical structure;
    • Query Gene: Combine text and gene sequence fragment;
    • Query Protein: Combine text and protein sequence fragment.

If you have software of interest to the text mining community which you would like adding to this collection of software — or you would like us to update or remove a link to an existing text mining resource — please contact us.