TNMCA: generation and application of network motif based inference models for drug repositioning

Since the increase of the public biomedical data, Undiscovered Public Knowledge (UPK, proposed by Swanson) became an important research topic in the biological field. Drug repositioning is one of famous UPK tasks which infer alternative indications for approved drugs. Many researchers tried to find novel candidates of existing drugs, but these previous works are not fully automated which required manual modulations to desired tasks, and was not able to cover various biomedical entities. In addition, they had inference limitations that those works could infer only pre-defined cases using limited patterns. In this paper, we propose the Typed Network Motif Comparison Algorithm (TNMCA) to discover novel drug indications using topological patterns of data. Typed network motifs (TNM) are connected sub-graphs of data, which store types of data, instead of values of data. While previous researches depends on ABC model (or extension of it), TNMCA utilizes more generalized patterns as its inference models. Also, TNMCA can infer not only an existence of interaction, but also the type of the interaction. TNMCA is suited for multi-level biomedical interaction data as TNMs depend on the different types of entities and relations. We apply TNMCA to a public database, Comparative Toxicogenomics Database (CTD), to validate our method. The results show that TNMCA could infer meaningful indications with high performance (AUC=0.7469) compared to the ABC model (AUC=0.7050).