XTractorTM is a platform for discovery & analysis of published biomedical facts. XTractorTM has been widely adopted by the life sciences research community and has more than 2800 users from 350 organizations across the globe.
The platform allows semantic searching reducing the time spent on retrieving relevant information from the public literature sources. The platform provides association information with reference to various biomedical entities such as biomarkers, molecular targets (genes/proteins), disease mechanisms, pathways, clinical trials, biological processes, drugs.

xtractor

  • Hybrid approach of indexing PubMed abstracts to make it easier to search
  • Proprietary indexing and tagging cycle for every day’s PubMed downloads
  • More than 3000 abstracts processed everyday
  • Mapping of metadata to multiple ontologies
  • Categorization of abstracts to 24 different categories – Biomarkers, Clinical Trials, knockout studies, toxicity, disease mechanisms, pathways etc.
  • Proteins, drugs, diseases & processes are mapped to standard ontologies.
  • Provides outputs for more than 13 million relationships
  • The metadata is linked to more than 20 external databases
  • Annotation : Semantically annotated content
  • Semantic Consistency : Standard ontologies followed, including MeSH, GO, Swiss Prot, Drug bank
  • Time saving : saves time on scientific literature searches by facilitating semantic searches
  • Comprehensiveness : Covers a large proportion of all the major protein, disease and drug databases
  • Categorization of content : The content is classified into broader categories such as Protein/Gene, Disease, Drug based information for easier access and filtering
  • Pharmaceutical and life science companies
  • Academic labs
  • Text/data mining companies
  • Life science and healthcare analytics companies
  • Database providers