Life Sciences

Researchers and others in life sciences face numerous challenges brought about by huge increases in the amount of relevant unstructured data that is published. For example, bringing a drug to market requires the examination of patents and patent filings, research papers and all types of research reports. Alternatively, genetics and proteomics researchers are faced with the time-consuming task of scouring research abstracts for relevant information. All of this is occurring in an increasingly competitive marketplace where speedy analysis is of critical importance.

Finding new ways to speed up the handling of unstructured data is essential to helping a company or research teams reach their goals. Text mining technology is a very effective means of getting control of an organization’s unstructured data. The use of search, extraction and visualization software, as provided by NetOwl TextMiner, promotes the identification of critical information and relationships between superficially distinct pieces of information. It allows the normalization of information to facilitate search, retrieval and analysis.

NetOwl automates the analysis and extraction of critical information found in unstructured textual data. For example, NetOwl Extractor has been used to analyze a large amount of research papers for customers in the bioinformatics field. Extractor frees up researchers’ time by providing intuitively structured information about biomedical data that had previously been located in unstructured texts. In particular:

  • Extractor provides automatic derivation of gene annotations from MEDLINE texts, including the functions of a gene as reported in the abstracts, as well as the diseases, tissues and other genes associated with it. All of this information is conveniently structured and normalized.
  • Extractor addresses the serious problem of varying nomenclature by automatically linking the various ways of referring to a specific gene found in the literature.

NetOwl helps researchers cut through large amounts of unstructured text data. It enhances the accuracy of searches and enables real text mining within the life sciences. Benefits include acceleration of the drug approval process and better understanding of the scientific literature. Companies and research organizations are better able to maintain their competitiveness.