IBM is contributing to the National Institutes of Health a massive, searchable database of chemical and pharmaceutical data, extracted from millions of patents and scientific literature. This contribution will allow researchers to more easily visualize important relationships among chemical compounds to aid in drug discovery and support advanced cancer research.
The data was extracted using the IBM BAO strategic IP insight platform (SIIP). This new IBM solution aggregates patent and scientific literature data and offers powerful search and analytics capabilities to comb intellectual property for new insights. It uses a computer-driven method for curating and analyzing massive amounts of patents, scientific content and molecular data, automatically extracting chemical entities from textual content as well as from images and symbols.