Predicting the recurrence of noncoding regulatory mutations in cancer

Abstract

BackgroundOne of the greatest challenges in cancer genomics is to distinguish driver mutations from passenger mutations. Whereas recurrence is a hallmark of driver mutations, it is difficult to observe recurring noncoding mutations owing to a limited amount of whole-genome sequenced samples. Hence, it is required to develop a method to predict potentially recurrent mutations.ResultsIn this work, we developed a random forest classifier that predicts regulatory mutations that may recur based on the features of the mutations repeatedly appearing in a given cohort. With breast cancer as a model, we profiled 35 quantitative features describing genetic and epigenetic signals at the mutation site, transcription factors whose binding motif was disrupted by the mutation, and genes targeted by long-range chromatin interactions. A true set of mutations for machine learning was generated by interrogating publicly available pan-cancer genomes based on our statistical model of mutation recurrence. The performance of our random forest classifier was evaluated by cross validations. The variable importance of each feature in the classification of mutations was investigated. Our statistical recurrence model for the random forest classifier showed an area under the curve (AUC) of ~0.78 in predicting recurrent mutations. Chromatin accessibility at the mutation sites, the distance from the mutations to known cancer risk loci, and the role of the target genes in the regulatory or protein interaction network were among the most important variables.ConclusionsOur methods enable to characterize recurrent regulatory mutations using a limited number of whole-genome samples, and based on the characterization, to predict potential driver mutations whose recurrence is not found in the given samples but likely to be observed with additional samples.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1385-y) contains supplementary material, which is available to authorized users.

Recurrent somatic mutations reveal new insights into consequences of mutagenic processes in cancer

“…Recurrence is considered an important indication that a mutation might be under selective pressure in protein-coding regions [37, 38]. Hence, by focusing on recurrence we are inherently not only looking at the mutational consequences of mutational and repair processes, but also at positively selected mutations.…”

“…In either case, it also implies that over a million mutations are assumed to be under positive selection. Besides the fact that recurrence is not a sufficient condition for positive selection [37], it may not even be a necessary one in a dataset of the size of our cohort [3, 38]. Another option is to remove all predicted driver mutations.…”

pDriver: A novel method for unravelling personalised coding and miRNA cancer drivers

“…miRNAs). Because protein-coding regions only account for about two percent of the human genome (Yang et al, 2016a), a large percentage of mutations might exist in non-coding regions, and thus non-coding genes may act as cancer drivers too (Puente et al, 2015;Weinhold et al, 2014). Consequently, novel and effective methods are needed for both coding and non-coding personalised cancer drivers.…”

DriverGroup: A novel method for identifying driver gene groups

“…However, the idea of driver gene groups is that all genes in a group collaboratively drive cancer. In addition, these methods only deal with coding genes while cancer drivers may be non-coding genes since a large portion of mutations may exist in non-coding regions (Yang et al, 2016a), and non-coding genes can regulate gene targets to drive cancer (Puente et al, 2015;Weinhold et al, 2014). Thus, there is a strong need for novel methods to identify both coding and non-coding driver gene groups of which the members of each driver group work in concert to progress cancer.…”