On Thursday, IBM and four drug companies announced plans to donate a massive database of chemical information to NIH in an effort to accelerate drug discovery, Health Data Management reports.
The four drug companies that provided information for the database are:
- AstraZeneca;
- Bristol-Myers Squibb;
- DuPont; and
- Pfizer.
For the project, IBM used its Strategic Intellectual Property Insight Platform -- or SIIP -- to extract data on 2.4 million chemical compounds from 4.7 million patents and 11 million biomedical journal abstracts dating from 1976 to 2000 (Goedert, Health Data Management, 12/8).
To sift through the patent filings and biomedical journals, IBM's SIIP tool used data mining, natural-language processing and analytics. Although all of the chemical compound information previously was published, it often was inaccessible to researchers.
Chris Moore -- head of business analytics and optimization for the global services unit at IBM -- said the database "provides a landscape that shows who is working with what chemicals and drugs."
Mark Nicklaus -- head of the computer-aided drug discovery group at NIH's National Cancer Institute -- said the donation of chemical data reflects a growing movement in the industry. He said, "It's a nice contribution to the field of open chemistry -- and that's a growing trend, inspired by and similar to open-source software" (Lohr, "Bits," New York Times, 12/8).