English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The emerging field of precision oncology relies on the accurate pinpointingof alterations in the molecular profile of a tumor to provide personalizedtargeted treatments. Current methodologies in the field commonly include theapplication of next generation sequencing technologies to a tumor sample,followed by the identification of mutations in the DNA known as somaticvariants. The differentiation of these variants from sequencing error poses aclassic classification problem, which has traditionally been approached withBayesian statistics, and more recently with supervised machine learning methodssuch as neural networks. Although these methods provide greater accuracy,classic neural networks lack the ability to indicate the confidence of avariant call. In this paper, we explore the performance of deep Bayesian neuralnetworks on next generation sequencing data, and their ability to giveprobability estimates for somatic variant calls. In addition to demonstratingsimilar performance in comparison to standard neural networks, we show that theresultant output probabilities make these better suited to the disparate andhighly-variable sequencing data-sets these models are likely to encounter inthe real world. We aim to deliver algorithms to oncologists for which modelcertainty better reflects accuracy, for improved clinical application. Bymoving away from point estimates to reliable confidence intervals, we expectthe resultant clinical and treatment decisions to be more robust and moreinformed by the underlying reality of the tumor molecular profile.

Deep Bayesian Recurrent Neural Networks for Somatic Variant Calling in Cancer