James Zou

Stories

AI agent team designs a lung-cancer drug in Stanford's virtual biotech

As of October 2026: Principal investigator of the Stanford virtual lab

Stanford built a drug-discovery operation with 37,000 AI agents and no lab benches. The virtual biotech analyzed 55,984 clinical trials and proposed a lung-cancer therapy that a human pharmaceutical company matched months later.

Updated Oct 11

AI cracks the sleep code: one night predicts 130 diseases

New Capabilities

As of May 2026: Co-senior author of SleepFM study

Stanford researchers trained an AI on 600,000 hours of people sleeping. SleepFM analyzes brain waves, heartbeats, and breathing from a single night and predicts your risk for 130 diseases—dementia, heart attacks, cancer, mental disorders—with over 80% accuracy. The breakthrough turns a night of sleep into a comprehensive disease-screening tool.

Updated May 19

Notable Quotes

"Our next step is to bring the new findings from the virtual biotech into real labs and test how many hold up in the real world."

from AI agent team designs a lung-cancer drug in Stanford's virtual biotech · Updated Oct 11

"This was really exciting as an independent, third-party validation that's consistent with the effects and the design proposed by the virtual biotech." — on the matching pharma approach to B7-H3

from AI agent team designs a lung-cancer drug in Stanford's virtual biotech · Updated Oct 11

From an AI perspective, sleep is relatively understudied. There's a lot of other AI work that's looking at pathology or cardiology, but relatively little looking at sleep, despite sleep being such an important part of life.

from AI cracks the sleep code: one night predicts 130 diseases · Updated May 19

SleepFM is essentially learning the language of sleep.

from AI cracks the sleep code: one night predicts 130 diseases · Updated May 19