Cancer mutational signatures representation by large-scale context embedding

Abstract

Motivation The accumulation of somatic mutations plays critical roles in cancer development and progression. However, the global patterns of somatic mutations, especially non-coding mutations, and their roles in defining molecular subtypes of cancer have not been well characterized due to the computational challenges in analysing the complex mutational patterns. Results Here, we develop a new algorithm, called MutSpace, to effectively extract patient-specific mutational features using an embedding framework for larger sequence context. Our method is motivated by the observation that the mutation rate at megabase scale and the local mutational patterns jointly contribute to distinguishing cancer subtypes, both of which can be simultaneously captured by MutSpace. Simulation evaluations show that MutSpace can effectively characterize mutational features from known patient subgroups and achieve superior performance compared with previous methods. As a proof-of-principle, we apply MutSpace to 560 breast cancer patient samples and demonstrate that our method achieves high accuracy in subtype identification. In addition, the learned embeddings from MutSpace reflect intrinsic patterns of breast cancer subtypes and other features of genome structure and function. MutSpace is a promising new framework to better understand cancer heterogeneity based on somatic mutations. Availability and implementation Source code of MutSpace can be accessed at: https://github.com/ma-compbio/MutSpace. Supplementary information Supplementary data are available at Bioinformatics online.

Mutation Rate Variations in the Human Genome are Encoded in DNA Shape

“…Nucleotide mutation is an important genetic process showing potentially causal association with diseases like cancer, autism spectrum disorder, and Alzheimer's disease (1)(2)(3)(4)(5)(6)(7). Single nucleotide mutation rate ("mutation rate") represents the probability of a single nucleotide mutating in an individual genome.…”

“…Predictive modeling of mutation rates and explaining the source of its genomewide variations is an essential goal in human genetics. This understanding is the key to studying evolutionary divergence between species, inferring ancestral states, detecting adaptive evolution (8)(9)(10), identifying functional elements in the genome and predicting deleterious single nucleotide variants in the human genome (1)(2)(3)8), and identifying disease subtypes (4)(5)(6)(7). Predicting the high variations in genome-wide mutation rates is known to be difficult.…”

Representation learning applications in biological sequence analysis

“…In performance evaluation using the ENCODE ChIP-seq dataset, BindSpace achieved high classification performance even between paralogous TFs, which contain highly similar binding motifs. The second application is MutSpace , which is used to estimate the cancer types of patients from somatic mutation patterns [67] . This method regarded mutation patterns and cancer types as words and labels, respectively.…”

Representation learning applications in biological sequence analysis

“…In performance evaluation using the EN-CODE ChIP-seq dataset, BindSpace achieved high classification performance even between paralogous TFs, which have highly similar binding motifs. The second application is MutSpace, which estimates the cancer types of patients from somatic mutation patterns [61]. This method regarded mutation patterns and cancer types as words and labels, respectively.…”