Nature Communications · 2022 · 34 citations · 24 references
Life SciencesBioinformaticsOncologyGenomicsMachine LearningMolecular OncologyCancer GenomicsDeep LearningNext-generation Sequencing In OncologyVariant AnalysisVariant CallingVariant DetectionBenchmark DatasetsNext-generation Sequencing AnalysisSomatic Mutation AnalysisSomatic Mutation CallingSomatic MutationsSomatic Variant AnalysisSomatic Variant CallingSomatic Variant Detection
Identification of somatic mutations in tumor samples is commonly based on statistical methods in combination with heuristic filters. Here we develop VarNet, an end-to-end deep learning approach for identification of somatic variants from aligned tumor and matched normal DNA reads. VarNet is trained using image representations of 4.6 million high-confidence somatic variants annotated in 356 tumor whole genomes. We benchmark VarNet across a range of publicly available datasets, demonstrating performance often exceeding current state-of-the-art methods. Overall, our results demonstrate how a scalable deep learning approach could augment and potentially supplant human engineered features and heuristic filters in somatic variant calling.
24
The Sequence Alignment/Map format and SAMtools
Heng Li, Alec Wysoker, Tim Fennell et al. · Bioinformatics · 2009 · 67.5K citations · Full text
Highly accurate protein structure prediction with AlphaFold
John Jumper, Alexander Pritzel, Tim Green et al. · Nature · 2021 · 45.2K citations · Full text
Rethinking the Inception Architecture for Computer Vision
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. · 2016 · 30.9K citations
BEDTools: a flexible suite of utilities for comparing genomic features
Aaron R. Quinlan, Ira M. Hall · Bioinformatics · 2010 · 30.4K citations · Full text