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

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused anongoing pandemic infecting 219 million people as of 10/19/21, with a 3.6%mortality rate. Natural selection can generate favorable mutations withimproved fitness advantages; however, the identified coronaviruses may be thetip of the iceberg, and potentially more fatal variants of concern (VOCs) mayemerge over time. Understanding the patterns of emerging VOCs and forecastingmutations that may lead to gain of function or immune escape is urgentlyrequired. Here we developed PhyloTransformer, a Transformer-baseddiscriminative model that engages a multi-head self-attention mechanism tomodel genetic mutations that may lead to viral reproductive advantage. In orderto identify complex dependencies between the elements of each input sequence,PhyloTransformer utilizes advanced modeling techniques, including a novel FastAttention Via positive Orthogonal Random features approach (FAVOR+) fromPerformer, and the Masked Language Model (MLM) from Bidirectional EncoderRepresentations from Transformers (BERT). PhyloTransformer was trained with1,765,297 genetic sequences retrieved from the Global Initiative for SharingAll Influenza Data (GISAID) database. Firstly, we compared the predictionaccuracy of novel mutations and novel combinations using extensive baselinemodels; we found that PhyloTransformer outperformed every baseline method withstatistical significance. Secondly, we examined predictions of mutations ineach nucleotide of the receptor binding motif (RBM), and we found ourpredictions were precise and accurate. Thirdly, we predicted modifications ofN-glycosylation sites to identify mutations associated with alteredglycosylation that may be favored during viral evolution. We anticipate thatPhyloTransformer may guide proactive vaccine design for effective targeting offuture SARS-CoV-2 variants.

PhyloTransformer: A Discriminative Model for Mutation Prediction Based on a Multi-head Self-attention Mechanism