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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

COVID-19 pandemic, is still unknown and is an important open question. Thereare speculations that bats are a possible origin. Likewise, there are manyclosely related (corona-) viruses, such as SARS, which was found to betransmitted through civets. The study of the different hosts which can bepotential carriers and transmitters of deadly viruses to humans is crucial tounderstanding, mitigating and preventing current and future pandemics. Incoronaviruses, the surface (S) protein, or spike protein, is an important partof determining host specificity since it is the point of contact between thevirus and the host cell membrane. In this paper, we classify the hosts of overfive thousand coronaviruses from their spike protein sequences, segregatingthem into clusters of distinct hosts among avians, bats, camels, swines, humansand weasels, to name a few. We propose a feature embedding based on thewell-known position-weight matrix (PWM), which we call PWM2Vec, and use togenerate feature vectors from the spike protein sequences of thesecoronaviruses. While our embedding is inspired by the success of PWMs inbiological applications such as determining protein function, or identifyingtranscription factor binding sites, we are the first (to the best of ourknowledge) to use PWMs in the context of host classification from viralsequences to generate a fixed-length feature vector representation. The resultson the real world data show that in using PWM2Vec, we are able to performcomparably well as compared to baseline models. We also measure the importanceof different amino acids using information gain to show the amino acids whichare important for predicting the host of a given coronavirus.

PWM2Vec: An Efficient Embedding Approach for Viral Host Specification from Coronavirus Spike Sequences