Vivodyne says AI drug discovery has a data problem it can fix

Biotech startup Vivodyne says the AI drug-discovery industry has a data problem, and that it has built a machine to fix it. HIVE, the company’s modular robotic labs, can grow 20 kinds of human tissue, then autonomously dose and monitor them — generating causal biological data that today mostly comes from animal testing or studies of single cells or proteins, not living tissue.

“Absent human testing, what are these [AI] models going to do?” asks Andrei Georgescu, Vivodyne’s CEO and co-founder. “They’re going to cure cancer in mice.”

The skepticism extends beyond Vivodyne. Anthropic CEO Dario Amodei wrote over the weekend that claims AI will cure cancer have become more cliché than credible — “the thing that will work is actually curing cancer,” as he put it — even though Amodei himself has floated the idea in past essays, alongside OpenAI’s Sam Altman and Google DeepMind’s Demis Hassabis, who said last year AI could potentially cure all disease within a decade.

Results so far remain tepid: a handful of AI-designed drugs have reached human trials, one as far as Phase III, but the roadblocks aren’t necessarily ones AI can solve today. AlphaFold, a Nobel-prize-winning advance in understanding the building blocks of life, has yet to produce a new drug. Isomorphic Labs, built on AlphaFold, now expects its first trials by the end of this year, after originally planning for 2025.

Georgescu says the field needs “a sanity check” — that existing models lack the data to capture the complexity of human biology, a problem already visible in the pharmaceutical industry, where 90% of drugs effective enough in animal testing to enter clinical trials don’t win human regulatory approval.

Vivodyne, spun out of the University of Pennsylvania in 2021 after Georgescu’s PhD in bioengineering there, says its tissues closely track real human organs: 94% predictive accuracy for liver-cell toxicity versus human trials, 96% concordance for airway tissue, and 100% concordance across 20 chemotherapy drugs tested on its bone marrow. The company, which has raised just under $80 million across two rounds led by Khosla Ventures, last week opened what it calls the world’s largest “human data center” outside San Francisco, and Georgescu says his team is already achieving twice the throughput of all US animal trials combined.

The goal is to de-risk drug candidates before the expense of a clinical trial. Georgescu compares the problem to automotive crash tests: automakers are typically confident a car will pass safety requirements before testing it, while drugmakers rarely have similar confidence entering trials where most drugs fail to win FDA approval. He says Vivodyne is working with multiple major pharma companies, though it won’t name them.

Why it matters

If Vivodyne’s tissue data can train AI models that understand causal biology rather than static snapshots, it could reshape how drug candidates are vetted before the costliest stage of development — clinical trials.