Linguamatics Launches Cloud-based OMIM Text Mining Service
Product News Feb 25, 2015
Linguamatics has announced that it is making the Online Mendelian Inheritance in Man® (OMIM) data available with its market-leading text analytics platform, I2E. The new service will be offered on the cloud via Linguamatics I2E OnDemand platform and is part of Linguamatics’ ongoing strategy to expand the range of off-the-shelf content accessible through its text mining and knowledge discovery solutions.
I2E OnDemand provides access to a wide variety of data such as MEDLINE, FDA Drug Labels, Patents, ClinicalTrials.gov, PubMed Central (open access subset) and NIH grants. The addition of OMIM allows users to accurately identify and extract information to reveal genetic associations for unusual clinical case presentations or phenotypes; or to search for potential targets for a particular therapeutic area, for initial target selection.
OMIM is a comprehensive catalogue of all known human diseases with a genetic component. The database includes documented associations to the relevant genes in the human genome, and related information including gene and disease descriptions, clinical synopsis, animal models, inheritance, mapping, history and more.
Dr David Milward, Chief Technology Officer at Linguamatics, explains “Combining genotype-phenotype relationships extracted from OMIM with relationships from other sources, such as MEDLINE, gives I2E users an excellent resource for NGS annotation, target discovery, and clinical genomics, in order to better target the molecular basis of disease.”
The key benefits of accessing OMIM in I2E are:
• Use of domain-specific ontologies (e.g. for diseases, genes, mutations and other gene variants) to enable high recall compared to searching via the OMIM interface
• Powerful querying, either out-of-the-box or custom, to enable deeper access to the valuable scientific detail within each OMIM record, such as extraction of gene-gene interactions, gene/protein mutations, mouse models, clinical details
• Ability to pull out relationships (e.g. between genes and phenotypes) from both structured data within the OMIM record, and the unstructured text fields
• Creating structured output from both the structured and unstructured text means results can be visualized for rapid decision support