NBT: Control-independent mosaic single nucleotide variant detection with DeepMosaic
Mosaic variants (MVs) reflect mutagenic processes during embryonic development and environmental exposure, accumulate with aging, and underlie diseases such as cancer and autism. Detecting noncancer MVs has been computationally challenging due to the sparse representation of nonclonally expanded MVs. In this intro video, First and co-corresponding author Dr. Xiaoxu Yang, co-first Xin Xu, and co-corresponding author Dr. Joseph Gleeson presents DeepMosaic, combining an image-based visualization module for single nucleotide MVs and a convolutional neural network-based classification module for control-independent MV detection. DeepMosaic was trained on 180,000 simulated or experimentally assessed MVs, and was benchmarked on 619,740 simulated MVs and 530 independent biologically tested MVs from 16 whole-genome sequences and 181 from whole-exome sequencing. DeepMosaic achieved higher accuracy compared with existing methods on genomic data, as well as doubling the validation rate over previous best-practice methods on noncancer whole-exome sequencing data. DeepMosaic represents an accurate MV classifier for noncancer samples that can be implemented as an alternative or complement to existing methods. For more information please visit the full text at https://www.nature.com/articles/s4158... or https://rdcu.be/c2DI5.