The Documents and Text Collection provides a broad set of core text mining capabilities as well as discipline-specific functionality to convert scientific data into actionable knowledge.
- Support for science
- Biology: Amino Acids, Proteins, DNA, RNA, Cell Lines, and Cell Type
- Chemistry: systematic names (IUPAC, InChI, and SMILES), formulae, family names, abbreviations, identifiers, CAS numbers, and non-systematic (trivial) names
- Generate interactive reports
- Add content to documents or create expert views such as Tag Clouds
- Explore internal & external data sources
- Search PubMed, patent offices, Twitter, Bing, websites and more
- Simplify text mining
- Automate analysis to extract key concepts to find correlations in documents and online literature
- Search flexibly
- Phrase, wildcard, fielded and synonym matching
- Read in a variety of file formats
- PDF, PowerPoint, websites, EndNotes, Medline, RSS news feeds and more