Cancer classification based on chromatin accessibility profiles with deep adversarial learning model

Abstract

Given the complexity and diversity of the cancer genomics profiles, it is challenging to identify distinct clusters from different cancer types. Numerous analyses have been conducted for this propose. Still, the methods they used always do not directly support the high-dimensional omics data across the whole genome (Such as ATAC-seq profiles). In this study, based on the deep adversarial learning, we present an end-to-end approach ClusterATAC to leverage high-dimensional features and explore the classification results. On the ATAC-seq dataset and RNA-seq dataset, ClusterATAC has achieved excellent performance. Since ATAC-seq data plays a crucial role in the study of the effects of non-coding regions on the molecular classification of cancers, we explore the clustering solution obtained by ClusterATAC on the pan-cancer ATAC dataset. In this solution, more than 70% of the clustering are single-tumor-type-dominant, and the vast majority of the remaining clusters are associated with similar tumor types. We explore the representative non-coding loci and their linked genes of each cluster and verify some results by the literature search. These results suggest that a large number of non-coding loci affect the development and progression of cancer through its linked genes, which can potentially advance cancer diagnosis and therapy.

A deep learning approach to automate whole‐genome prediction of diverse epigenomic modifications in plants

“…There are recent demonstrations for the successful applications of deep learning methods for biomedicine, genetics, and genomics (Ainscough et al ., 2018; Eraslan et al ., 2019; Zou et al ., 2019; Arbab et al ., 2020; Kim et al ., 2021), as well as some examples from plant biology and agricultural science (Washburn et al ., 2019; Wang et al ., 2020; Dunker et al ., 2021; Warman et al ., 2021). Owing to the availability of big datasets generated by epigenetic and epigenomic research, it makes sense that deep learning models have shown promise for the identification of DNA methylation (Angermueller et al ., 2017; Holder et al ., 2017; Lv et al ., 2020; Li et al ., 2021), histone modifications (Xu et al ., 2017; Hoffman et al ., 2019), RNA methylation (Sun et al ., 2019; Wang & Wang, 2020), and chromatin interactions (Zhang et al ., 2018a; Yang et al ., 2020). However, these deep learning models are mostly implemented in nonplant species, so whether these models can be applied usefully in plant species remains unclear.…”