

Machine Learning: A New Approach to Drug Discovery with Daphne Koller - #332
Dec 26, 2019
Daphne Koller, the co-founder of Coursera and CEO of Insitro, shares her expertise on the revolutionary role of machine learning in drug discovery. She discusses the hurdles of the pharmaceutical landscape, including high costs and regulatory challenges. Koller emphasizes how ML can streamline decision-making and enhance drug efficacy through targeted therapies. Highlighting innovative techniques like CRISPR and high throughput biology, she stresses the need for collaboration between biology and tech experts to transform healthcare.
AI Snips
Chapters
Transcript
Episode notes
NeurIPS Growth
- Daphne Koller reflects on the growth of NeurIPS, from 1,000 attendees in 2007 to 13,000+ in the present.
- She notes the transition from intimate gatherings to massive crowds, highlighting the field's expansion.
Shift to Biology
- Koller's early machine learning work focused on classifying newsgroup articles, which she found uninspiring.
- She transitioned to biology in the late 90s, drawn by more aspirational datasets like tuberculosis infection and gene expression.
Predicting Medical Difficulties in Premature Babies
- At Stanford, Koller applied ML to predict medical difficulties in premature babies using non-invasive measurements.
- This work allowed her to discover new scientific insights as a byproduct of the machine learning predictions.