A plethora of emerging technologies are being utilized in the fight against the COVID-19 pandemic. Massachusetts Institute of Technology (MIT) researchers have trained algorithms in a task they call constrained semantic change search (CSCS) that enables them to study viral mutations, including those that develop into highly infectious coronavirus variants such as those that first emerged in the UK and South Africa. Quartz Africa brought this interesting news to our attention in their article, “Scientists are using natural-language algorithms to predict Covid-19 variants.”

This approach carries particular urgency for regions like Africa, where the spread of the novel coronavirus among largely unvaccinated populations increases the opportunity for concerning mutations to occur.

The ability of scientists to successfully adapt COVID-19 vaccines for use against coronavirus variants of concern will turn in part on the ability to spot infectious mutations in the virus’s genetic makeup quickly. For that, natural language processing (NLP) may help.

Public health officials around the world have already used NLP techniques for a variety of reasons related to COVID-19, such as tracking surges.

Melody K. Smith

Sponsored by Access Innovations, the world leader in thesaurus, ontology, and taxonomy creation and metadata application.