How AI can make drug discovery fail less, with Daphne Koller from Insitro
Show notes
Life-saving therapeutics continue to grow more costly to discover. At the same time, recent advances in using machine learning for the life sciences and medicine are extraordinary. Are we on the verge of a paradigm shift in biotech? This week on the podcast, a pioneer in AI, Daphne Koller, joins Sarah Guo and Elad Gil on the podcast to help us explore that question. Daphne is the CEO and founder of Insitro — a company that applies machine learning to pharma discovery and development, specifically by leveraging “induced pluripotent stem cells.” We explain Insitro’s approach, why they’re focused on generating their own data, why you can’t cure schizophrenia in mice, and how to design a culture that supports both research and engineering. Daphne was previously a computer science professor at Stanford, and co-founder and co-CEO of edutech company Coursera. Show Links: Insitro - About Video: AWS re:Invent 2019 – Daphne Koller of insitro Talks About Using AWS to Transform Drug Development Sign up for new podcasts every week. Email feedback to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @DaphneKoller Show Notes: [1:49] - How Daphne combined her biology and tech interests and ran a bifurcated lab at Stanford [4:34] - Why Daphne resigned an endowed chair at Stanford to build Coursera [14:14] - How insitro approaches target identification problems and training data [18:33] - What are pluripotent stem cells and how insitro identifies individual neurons [24:08 ] - How insitro operates as an engine for drug discovery and partners to create the drugs themselves [26:48] - Role of regulations, clinical trials and disease progression in drug delivery [33:19] - Building a team and workplace culture that can bridge both bio and computer sciences [39:50] - What Daphne is paying attention to in the so-called golden age of machine learning [43:12] - Advice for leading a startup in edtech and healthtech
Guests
.jpg?width=400){kind=small}
Analysis: done · source seed