Consensus clustering applied to multi-omic disease subtyping

BackgroundFacing the diversity of omic data and the difficulty of selecting one result over all those produced by several clustering methods, consensus strategies have the potential to reconcile multiple inputs and to produce robust results. ResultsHere, we introduce ClustOmics, a generic consensus clustering tool that we use in the context of cancer subtyping. ClustOmics relies on a non-relational graph database, which allows for the simultaneous integration of both multiple omic data and results from various clustering methods. This new tool conciliates input clusterings, regardless of their origin, their number, their size or their shape. ClustOmics implements an intuitive and flexible strategy, based upon the idea of evidence accumulation clustering. It computes co-occurrences of pairs of samples in input clusters and uses this score as a similarity measure to reorganise data into consensus clusters. ConclusionWe applied ClustOmics to multi-omic disease subtyping on real TCGA cancer data from ten different cancer types. We showed that ClustOmics is robust to heterogeneous qualities of input partitions, smoothing and reconciling preliminary predictions into high quality consensus clusters, both from a computational and a biological point of view. In this regard, ClustOmics is not meant to compete with other integrative tools, but rather to make profit from their various predictions when no gold-standard metric is available to assess their significance. AvailabilityClustOmics source code, released under MIT licence, as well as the results obtained on TCGA cancer data are available on Github: https://github.com/galadrielbriere/ClustOmics.