IBM Watson debuts data-driven discovery

IBM has announced advances in Watson’s cognitive computing capabilities that are enabling researchers to accelerate the pace of scientific breakthroughs by discovering previously unknown connections in Big Data.

It can take 10-15 years on average for a pharmaceutical treatment to go from initial research until it is commercially available in clinical practice. Five of the 5,000 drugs that begin pre-clinical testing make it to human testing: of these five, only one drug is ever approved for use with humans.

IBM has announced an advancement with Watson’s cognitive capabilities, moving beyond engagement and searching through data for known answers to helping researchers accelerate scientific breakthroughs by uncovering discoveries and making connections in massive amounts of data.

Watson Discovery Advisor, available as a cloud service, can visually reveal patterns and pinpoint connections in data to help accelerate the discovery process. By helping researchers to gain awareness, understand relationships and clarify ideas, this new service can help reduce the time researchers need to formulate conclusions that can advance their work from months to days to just hours.

Researchers and scientists from leading life sciences organizations, including academic, pharmaceutical and research centres, have begun deploying Watson Discovery Advisor to overcome the complex challenges of absorbing, analyzing and creating hypothesis from the millions of scientific papers.

– In a retrospective, peer reviewed study release by Baylor College of Medicine and IBM, scientists demonstrated a possible new path for generating scientific questions that may be helpful in the long term for developing new effective treatments for disease. In a matter of weeks, biologists and data scientists using the Baylor Knowledge Integration Toolkit based on Watson technology, accurately identified proteins that modify p53, an important protein related to many cancers. Watson analyzed 70,000 scientific articles to predict proteins that turn on/off p53’s activity. This automated analysis led the Baylor cancer researchers to identify 6 potential proteins to target for new research.

– Johnson & Johnson is collaboration with Watson Discovery Advisor to teach Watson to read and understand scientific papers that detail clinical trial outcomes used to develop and evaluate medications and other treatments.

– Sanofi is working with Watson to speed up the discovery of alternate indications for existing drugs (drug pre-purposing).

Watson Discovery Advisor not only maps previously unknown correlations between key data points and understands nuances in natural language, but also understands the language of chemical compounds and how they interact: addressing critical dimensions in discovery in life sciences and other industries – such as public sector and financial services.

* Follow Gadget on Twitter on @GadgetZA