Robust Cancer Mutation Detection with Deep Learning Models Derived from Tumor-Normal Sequencing Data
2019
Accurate detection of
somaticmutations is challenging but critical to the understanding of cancer formation, progression, and treatment. We recently proposed NeuSomatic, the first deep convolutional neural network based
somaticmutation detection approach and demonstrated performance advantages on in silico data. In this study, we used the first comprehensive and well-characterized
somaticreference samples from the SEQC-II consortium to investigate best practices for utilizing deep learning framework in cancer mutation detection. Using the high-confidence
somaticmutations established for these reference samples by the consortium, we identified strategies for building robust models on multiple datasets derived from samples representing real scenarios. The proposed strategies achieved high robustness across
multiple sequencingtechnologies such as WGS, WES, AmpliSeq target sequencing for fresh and FFPE DNA input, varying tumor/normal purities, and different coverages (ranging from 10x - 2000x). NeuSomatic significantly outperformed conventional detection approaches in general, as well as in challenging situations such as low coverage, low
mutation frequency, DNA damage, and difficult genomic regions.
Keywords:
-
Correction
-
Source
-
Cite
-
Save
20
References
4
Citations
NaN
KQI