Safety and Robustness in Decision Making: Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer
This work addresses the need for safe and robust decision-making in precision oncology by offering statistically confident mutation calls for oncologists, though it is incremental as it builds on existing neural network methods.
The authors tackled the problem of providing confidence estimates for somatic mutation calls in cancer genomics, presenting a deep Bayesian recurrent neural network that matches the performance of standard neural networks while enabling flexible priors to avoid overfitting.
The genomic profile underlying an individual tumor can be highly informative in the creation of a personalized cancer treatment strategy for a given patient; a practice known as precision oncology. This involves next generation sequencing of a tumor sample and the subsequent identification of genomic aberrations, such as somatic mutations, to provide potential candidates of targeted therapy. The identification of these aberrations from sequencing noise and germline variant background poses a classic classification-style problem. This has been previously broached with many different supervised machine learning methods, including deep-learning neural networks. However, these neural networks have thus far not been tailored to give any indication of confidence in the mutation call, meaning an oncologist could be targeting a mutation with a low probability of being true. To address this, we present here a deep bayesian recurrent neural network for cancer variant calling, which shows no degradation in performance compared to standard neural networks. This approach enables greater flexibility through different priors to avoid overfitting to a single dataset. We will be incorporating this approach into software for oncologists to obtain safe, robust, and statistically confident somatic mutation calls for precision oncology treatment choices.