Two students of the Data Science Institute (DSI) at Columbia University are utilizing computational design to discover remedies for the coronavirus rapidly.
Andrew Satz and Brett Averso are the chief executive officer (CEO) and chief technology officer (CTO), respectively, of EVQLV, a startup developing algorithms capable of computationally generating, screening, and optimizing of millions of therapeutic antibodies. They apply their technology to find treatments most likely to help those infected by the COVID-19. Machine learning (ML) algorithms rapidly screen for therapeutic antibodies with a high probability of success.
Performing antibody discovery in a laboratory typically takes years; it takes just a week for the algorithms to establish antibodies that can battle against any virus. Accelerating the development of a treatment that might help infected people is crucial, says Satz, who’s a 2018 DSI alumnus and 2015 graduate of Columbia’s School of General Studies.
Expediting the primary stage of the process—antibody discovery—goes a long way toward speeding up the development of a treatment for COVID-19. After EVQLV carries out computational antibody discovery and optimization, it sends the promising antibody gene series to its laboratory partners.
Laboratory technicians then develop and test the antibodies, a process that takes a few months, versus several years.