Supervised Hypothesis Discovery Using Syllogistic Patterns in the Biomedical Literature

Abstract

The ever-growing literature in biomedicine makes it virtually impossible for individuals to grasp all the information relevant to their interests. Since even experts' knowledge is limited, important associations among key biomedical concepts may remain unnoticed in the flood of information. Discovering those hidden associations is called hypothesis discovery. This paper reports our approach to this problem taking advantage of a triangular chain of relations extracted from published knowledge. We consider such chains of relations as implicit rules to generate potential hypotheses. The generated hypotheses are then compared with newer knowledge for assessing their validity and, if validated, they are served as positive examples for learning a regression model to rank hypotheses. This framework, called supervised hypothesis discovery, is tested on real-world knowledge from the biomedical literature to demonstrate its effectiveness.