A team of researchers at MIT CSAIL is using machine learning to predict its efficacy across populations.

MIT’s Optivax design system is a combinatorial machine learning system. It selects peptides (short strings of amino acids) that are predicted to provide high population coverage for a vaccine. (MIT-CSAIL)

Optivax

The system is able to zero in on peptides. Then, using machine learning, it ranks them according to their ability to elicit an immune response. It then selects those that maximize population coverage of who could benefit from the vaccine.

“We evaluated a common vaccine design based on the spike protein for COVID-19 that is currently in multiple clinical trials,” says Ge Liu and Brandon Carter, CSAIL Ph.D. students and lead authors on a new paper about OptiVax. “Based on our analysis, we developed an augmentation to improve its population coverage by adding peptides. If this works in animal models, the design could move to human clinical trials.”

The MIT system could be invaluable in short-listing a vaccine that could be effective across a wide swathe of populations across the globe. It would also help to shorten development time and the costs incurred.

According to VentureBeat, and data from the Pharmaceutical Research and Manufacturers of America, the average development cost of a drug is $2.6 billion. The time frame from discovery to commercial availability is around ten years.

How the system works

• Optivax identifies all possible peptide fragments from the virus’ proteins that could lead to a vaccine
• The peptide fragments are then evaluated and ranked on multiple criteria. It includes their observed mutation rate across nearly 5,000 geographically sampled genomes
• The system then designs a vaccine that will be the most effective across populations in different geographical areas, as well as provide the required immunity.

“One of the challenges here was assembling good data on how people differ in their genetic makeup, in key genes that control the response to a vaccine or viral infection,” says MIT professor David Gifford on Optivax. “And then, we had to solve a difficult optimization problem to design a vaccine with good population coverage.”

According to the New York Times Coronavirus Vaccine Tracker, as on date, more than 165 vaccines are under development, but only 27 are in human trials.

Related Story:  Baricitinib, An AI-flagged Rheumatoid Drug, Could Treat COVID-19