NEMO: Cancer subtyping by integration of partial multi-omic data

Abstract

Motivation: Cancer subtypes were usually defined based on molecular characterization of single omic data. Increasingly, measurements of multiple omic profiles for the same cohort are available. Defining cancer subtypes using multi-omic data may improve our understanding of cancer, and suggest more precise treatment for patients.\n\nResults: We present NEMO (NEighborhood based Multi-Omics clustering), a novel algorithm for multiomics clustering. Importantly, NEMO can be applied to partial datasets in which some patients have data for only a subset of the omics, without performing data imputation. In extensive testing on ten cancer datasets spanning 3168 patients, NEMO outperformed nine state-of-the-art multi-omics clustering algorithms on full data and on imputed partial data. On some of the partial data tests, PVC, a multiview algorithm, performed better, but it is limited to two omics and to positive partial data. Finally, we demonstrate the advantage of NEMO in detailed analysis of partial data of AML patients. NEMO is fast and much simpler than existing multi-omics clustering algorithms, and avoids iterative optimization.\n\nAvailability: Code for NEMO and for reproducing all NEMO results in this paper is in github.\n\nContact: rshamir@tau.ac.il\n\nSupplementary information: Supplementary data are available online.