Deep convolutional neural networks for accurate somatic mutation detection.
Where this comes from
- Record sourced from PubMed, PMID 30833567.
- Also identified by DOI 10.1038/s41467-019-09027-x and PMC identifier 6399298.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Accurate detection of somatic mutations is still a challenge in cancer analysis. Here we present NeuSomatic, the first convolutional neural network approach for somatic mutation detection, which significantly outperforms previous methods on different sequencing platforms, sequencing strategies, and tumor purities. NeuSomatic summarizes sequence alignments into small matrices and incorporates more than a hundred features to capture mutation signals effectively. It can be used universally as a stand-alone somatic mutation detection method or with an ensemble of existing methods to achieve the highest accuracy.
Medical subject headings
- Computational Biology
- DNA Mutational Analysis
- Machine Learning
- Mutation
- Neural Networks, Computer