Rxivist logo

DeepMosaic: Control-independent mosaic single nucleotide variant detection using deep convolutional neural networks

By Xiaoxu Yang, Xin Xu, Martin W Breuss, Danny Antaki, Laurel L Ball, Changuk Chung, Chen Li, Renee D George, Yifan Wang, Taejeong Bae, Alexej Abyzov, Liping Wei, Jonathan Sebat, Joseph G Gleeson

Posted 16 Nov 2020
bioRxiv DOI: 10.1101/2020.11.14.382473

Mosaic variants (MVs) reflect mutagenic processes during embryonic development and environmental exposure, accumulate with aging, and underlie diseases such as cancer and autism. The detection of MVs has been computationally challenging due to sparse representation in non-clonally expanded tissues. While heuristic filters and tools trained on clonally expanded MVs with high allelic fractions are proposed, they showed relatively lower sensitivity and more false discoveries. Here we present DeepMosaic, combining an image-based visualization module for single nucleotide MVs, and a convolutional neural networks-based classification module for control-independent MV detection. DeepMosaic achieved a higher accuracy compared with existing methods on biological and simulated sequencing data, with a 96.34% (158/164) experimental validation rate. Of 932 mosaic variants detected by DeepMosaic in 16 whole genome sequenced samples, 21.89-58.58% (204/932-546/932) MVs were overlooked by other methods. Thus, DeepMosaic represents a highly accurate MV classifier that can be implemented as an alternative or complement to existing methods.

Download data

  • Downloaded 564 times
  • Download rankings, all-time:
    • Site-wide: 57,950
    • In genomics: 4,276
  • Year to date:
    • Site-wide: 18,630
  • Since beginning of last month:
    • Site-wide: 28,224

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide