Inferring disease association using clinical factors in a combinatorial manner and their use in drug repositioning.

MOTIVATION: Complex physiological relationships exist among human diseases. Thus, the identification of disease associations could provide new methods of disease care and diagnosis. To this end, numerous studies have investigated disease associations. However, combinatorial effect of physiological factors, which is the main characteristic of biological systems, has not been considered in most previous studies.
RESULTS: In this study, we inferred disease associations with a novel approach that considered disease-related clinical factors in combinatorial ways by using the National Health and Nutrition Examination Survey data, and the results have been shown as disease networks. Here, the FP-growth algorithm, an association rule mining algorithm, was used to generate a clinical attribute combination profile of each disease. In addition, we characterized the 22 clinical risk attribute combinations frequently discovered from the 26 diseases in this study. Furthermore, we validated that the results of this study have great potential for drug repositioning and outperform other existing disease networks in this regard. Finally, we suggest a few disease pairs as new candidates for drug repositioning and provide the evidence of their associations from the literature.