"The best ideas in drug discovery were often blocked not by biology, but by synthesis," Boiko told TechCrunch."
"The compounds never even got a chance to be tested," Boiko told TechCrunch."
"The models could generate ideas in hours, but it could take months for the lab to catch up," he told TechCrunch."
"We both saw that the world was throwing money into molecular design and almost ignoring the harder problem of actually making the molecules," Boiko said."
Daniil Boiko and Andrei Tyrin identified small-molecule synthesis as the key bottleneck preventing promising drug candidates from being tested. Boiko, a Ph.D. candidate in machine learning in chemistry at Carnegie Mellon with prior degrees in organic chemistry from Russia, observed that many compounds were abandoned because they were difficult to synthesize. Tyrin, with a computer science background from MIT, noted that computational models outpaced lab capabilities. They founded Onepot to rebuild synthesis capacity in the United States, creating the POT-1 synthesis lab and an AI organic chemist named Phil to automate and accelerate molecule creation and reduce reliance on fragile global supply chains.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]