RT Journal Article SR Electronic T1 Prioritizing 2nd and 3rd order interactions via support vector ranking using sensitivity indices on static Wnt measurements† JF bioRxiv FD Cold Spring Harbor Laboratory SP 059469 DO 10.1101/059469 A1 shriprakash sinha YR 2017 UL http://biorxiv.org/content/early/2017/08/08/059469.abstract AB It is widely known that the sensitivity analysis plays a major role in computing the strength of the influence of involved factors in any phenomena under investigation. When applied to expression profiles of various intra/extracellular factors that form an integral part of a signaling pathway, the variance and density based analysis yields a range of sensitivity indices for individual as well as various combinations of factors. These combinations denote the higher order interactions among the involved factors that might be of interest in the working mechanism of the pathway. For example, DACT3 is known to be a epigenetic regulator of the Wnt pathway in colorectal cancer and subject to histone modifications. But many of the nth ≥ 2 order interactions of DACT3 that might be influential have not been explored/tested. In this work, after estimating the individual effects of factors for a higher order combination, the individual indices are considered as discriminative features. A combination, then is a multivariate feature set in higher order (≥ 2). With an excessively large number of factors involved in the pathway, it is difficult to search for important combinations in a wide search space over different orders. Exploiting the analogy of prioritizing webpages using ranking algorithms, for a particular order, a full set of combinations of interactions can then be prioritized based on these features using a powerful ranking algorithm via support vectors. The computational ranking sheds light on unexplored combinations that can further be investigated using hypothesis testing based on wet lab experiments. Here, the basic framework and results obtained on 2nd and 3rd order interactions for members of family of DACT, SFRP, DKK (to name a few) in both normal and tumor cases is presented using a static data set.Significance The search and wet lab testing of unknown biological hypotheses in the form of combinations of various intra/extracellular factors that are involved in a signaling pathway, costs a lot in terms of time, investment and energy. To reduce this cost of search in a vast combinatorial space, a pipeline has been developed that prioritises these list of combinations so that a biologist can narrow down their investigation. The pipeline uses kernel based sensitivity indices to capture the influence of the factors in a pathway and employs powerful support vector ranking algorithm. The generic workflow and future improvements are bound to cut down the cost for many wet lab experiments and reveal unknown/untested biological hypothesis.