COVID-19: Researchers create AI tool to detect coronavirus-fighting molecules

Scientists have created a unique tool that can help drug researchers quickly identify the molecules capable of disarming the coronavirus SARS-CoV-2 before it ultimately invades the human cells. In a study published this week in Nature Machine Intelligence led by The University of New Mexico's Tudor Oprea, the researchers unveiled ‘REDIAL-2020’ which is an open-source online suite of 'computational' models that can help the scientists swiftly screen the molecules for their potential COVID-19-fighting properties.

As per Science Daily, Oprea, chief of the Translational Informatics Division in the UNM School of Medicine has said, “To some extent this replaces (laboratory) experiments, it narrows the field of what people need to focus on. That's why we placed it online for everyone to use."

After describing the models that can reduce the burden of scientists to experiment and identify the coronavirus-eliminating molecules, the researchers wrote in conclusion, “The REDIAL-2020 platform provides a fast and reliable way to screen novel compounds for anti-SARS-CoV-2 activities. REDIAL-2020 is available on GitHub and DockerHub as well, and the command-line version supports large-scale virtual screening purposes." In other words, REDIAL-2020 is a hub of source researchers with tools that can be used to screen molecules in an individual to screen anti-coronavirus properties in them.

Oprea’s team at UNM and another group from the University of Texas had begun working on the REDIAL-2020 tool in the spring of 2020 after scientists at the National Center for Advancing Translational Sciences (NCATS) released data from their own COVID-19 drug repurposing studies.

AI To Crack COVID-19 Genome Signature

‘REDIAL-2020’ is not the only time that artificial intelligence tools contributed to the world’s fight against COVID-19, earlier, a  team of scientists including India’s Gurjit Randhawa from Western University in Canada used artificial intelligence technology to identify the underlying genomic signature for 29 different DNA sequences of the novel coronavirus.

In the study that was published in the Science journal PLOS ONE, the researchers asserted that the newly discovered tool would allow other researchers to easily classify viruses like SARS-CoV-2 in minutes. They also added that their discovery provided a process of “high importance for strategic planning and mobilizing needs during a pandemic”.

Image credits: Unsplash/Pixabay