Life sciences researchers are under pressure to innovate faster than ever. Big data offer the promise of unlocking novel insights and accelerating breakthroughs. Ironically, although more data are available than ever, only a fraction is being integrated, understood, and analyzed. The challenge lies in harnessing volumes of data, integrating the data from hundreds of sources, and understanding their various formats. New technologies such as cognitive computing offer promise for addressing this challenge because cognitive solutions are specifically designed to integrate and analyze big datasets. Cognitive solutions can understand different types of data such as lab values in a structured database or the text of a scientific publication. Cognitive solutions are trained to understand technical, industry-specific content and use advanced reasoning, predictive modeling, and machine learning techniques to advance research faster. Watson, a cognitive computing technology, has been configured to support life sciences research. This version of Watson includes medical literature, patents, genomics, and chemical and pharmacological data that researchers would typically use in their work. Watson has also been developed with specific comprehension of scientific terminology so it can make novel connections in millions of pages of text. Watson has been applied to a few pilot studies in the areas of drug target identification and drug repurposing. The pilot results suggest that Watson can accelerate identification of novel drug candidates and novel drug targets by harnessing the potential of big data.

SignificanceWe adapted natural language processing to the biological literature and demonstrated end-to-end automated knowledge discovery by exploring subtle word connections. General text mining scanned 21 million publication abstracts and selected a reliable 130,000 from which hypothesis generation algorithms predicted kinases not known to phosphorylate p53, but likely to do so. Six of these p53 kinase candidates passed experimental validation. Among them NEK2 was examined in depth and shown to repress p53 and promote cell division. This work demonstrates the possibility of integrating a vast corpora of written knowledge to compute valuable hypotheses that will often test true and fuel discovery.

We present KnIT, the Knowledge Integration Toolkit, a system for accelerating scientific discovery and predicting previously unknown protein-protein interactions. Such predictions enrich biological research and are pertinent to drug discovery and the understanding of disease. Unlike a prior study, KnIT is now fully automated and demonstrably scalable. It extracts information from the scientific literature, automatically identifying direct and indirect references to protein interactions, which is knowledge that can be represented in network form. It then reasons over this network with techniques such as matrix factorization and graph diffusion to predict new, previously unknown interactions. The accuracy and scope of KnIT's knowledge extractions are validated using comparisons to structured, manually curated data sources as well as by performing retrospective studies that predict subsequent literature discoveries using literature available prior to a given date. The KnIT methodology is a step towards automated hypothesis generation from text, with potential application to other scientific domains.