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

Recent studies reveal even the smallest genomes such as viruses evolvethrough complex and stochastic processes, and the assumption of independentalleles is not valid in most applications. Advances in sequencing technologiesproduce multiple time-point whole-genome data, which enable potentialinteractions between these alleles to be investigated empirically. Toinvestigate these interactions, we represent alleles as distributed vectorsthat encode for relationships with other alleles in the course of evolution,and apply artificial neural networks to time-sampled whole-genome datasets forfeature learning. We build this platform using methods and algorithms derivedfrom Natural Language Processing (NLP), and we denote it as the nucleotideskip-gram neural network. We learn distributed vectors of alleles using thechanges in allele frequency of echovirus 11 in the presence or absence of thedisinfectant from the experimental evolution data. Results from the trainingusing a new open-source software TensorFlow show that the learned distributedvectors can be clustered using Principal Component Analysis and HierarchicalClustering to reveal a list of non-synonymous mutations that arise on thestructural protein VP1 in connection to the candidate mutation for disinfectantadaptation. Furthermore, this method can account for recombination rates bysetting the extent of interactions as a biological hyper-parameter, and theresults show the most realistic scenario of mid-range interactions across thegenome is most consistent with the previous studies.

Feature learning of virus genome evolution with the nucleotide skip-gram neural network