A new deep learning technique reveals the exclusive functional contributions of individual cancer mutations.

Cancers are caused by genomic alterations that may be inherited, induced by environmental carcinogens, or caused due to random replication errors. Postinduction of carcinogenicity, mutations further propagate and drastically alter the cancer genomes. Although a subset of driver mutations has been identified and characterized to date, most cancer-related somatic mutations are indistinguishable from germline variants or other noncancerous somatic mutations. Thus, such overlap impedes appreciation of many deleterious but previously uncharacterized somatic mutations. The major bottleneck arises due to patient-to-patient variability in mutational profiles, making it difficult to associate specific mutations with a given disease outcome. Here, we describe a newly developed technique Continuous Representation of Codon Switches (CRCS), a deep learning-based method that allows us to generate numerical vector representations of mutations, thereby enabling numerous machine learning-based tasks. We demonstrate three major applications of CRCS; first, we show how CRCS can help detect cancer-related somatic mutations in the absence of matched normal samples, which has applications in cell-free DNA-based assessment of tumor mutation burden. Second, the proposed approach also enables identification and exploration of driver genes; our analyses implicate DMD, RSK4, OFD1, WDR44, and AFF2 as potential cancer drivers. Finally, we used CRCS to score individual mutations in a tumor sample, which was found to be predictive of patient survival in bladder urothelial carcinoma, hepatocellular carcinoma, and lung adenocarcinoma. Taken together, we propose CRCS as a valuable computational tool for analysis of the functional significance of individual cancer mutations.

Discovery of rare cells from voluminous single cell expression data.

Single cell messenger RNA sequencing (scRNA-seq) provides a window into transcriptional landscapes in complex tissues. The recent introduction of droplet based transcriptomics platforms has enabled the parallel screening of thousands of cells. Large-scale single cell transcriptomics is advantageous as it promises the discovery of a number of rare cell sub-populations. Existing algorithms to find rare cells scale unbearably slowly or terminate, as the sample size grows to the order of tens of thousands. We propose Finder of Rare Entities (FiRE), an algorithm that, in a matter of seconds, assigns a rareness score to every individual expression profile under study. We demonstrate how FiRE scores can help bioinformaticians focus the downstream analyses only on a fraction of expression profiles within ultra-large scRNA-seq data. When applied to a large scRNA-seq dataset of mouse brain cells, FiRE recovered a novel sub-type of the pars tuberalis lineage.