University of Cambridge > > Data Intensive Science Seminar Series > Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling

Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact James Fergusson.

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 (NGS) of a tumor sample and the subsequent identification of genomic abberations, such as somatic mutations, to provide potential candidates of targeted therapy. The identification of these abberations from sequencing artifacts can be seen as a classification task. This has been previously broached with many different supervised machine learning methods, including 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 real. To address this, we present a deep bayesian recurrent neural network for cancer variant calling, which shows no degradation in performance compared to standard neural networks but yet returnss a measure of the confidence that reflects its performance on out-of-distribution data. We hope this approach can be incorporated into software used by oncologists to provide statistical confidence in precision oncology treatment choices.

This talk is part of the Data Intensive Science Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity