‘Drug Discovery for 1,000, Please’

The New York Times' Steve Lohr reports at the Bits blog that IBM is using Watson-style software as part of it's "Strategic Intellectual Property Insight Platform," a cloud-based service resulting from "several years of joint development between IBMResearch and four companies — AstraZeneca, Bristol-Myers Squibb, DuPont, and Pfizer." Lohr says the platform "uses data mining, natural-language processing and analytics to pore through millions of patent filings and biomedical journals to look for chemical compounds used in drug discovery." Searching for the "names of compounds, related words, drawings of the compounds, the names of companies working with specific chemicals and molecules, and the names of scientists who created the patented inventions," IBM's platform can quickly retrieve patent information, he adds. IBM is also contributing "more than 2.4 million chemical compounds extracted from 4.7 million patents and 11 million biomedical journal extracts from 1976 to 2000" to NIH's PubChem as a byproduct of its research efforts in an attempt to speed up drug discovery, Lohr says. The company’s data deposition appears "both generous and calibrated. … Most of the [chemical compound] data will be on patents that have already expired, useful for scientific research but far less useful commercially," he adds.