Scientists Build an AI ‘Early-Warning System’ That Could Spot the Next Pandemic Before It Strikes

Astromech is using 3.8 billion years of evolutionary history to train AI to predict biological threats, from emerging viruses to drug-resistant superbugs. The company has raised $20 million in new funding, bringing its total to $60 million at a $3.8 billion valuation.

Most computational biology looks at life as it exists today. Astromech wants to predict what happens next. Founded by entrepreneur Ben Lamm and geneticist George Church, the company is building AI models designed to learn from billions of years of evolution and identify where biological systems may be headed—and where they could become dangerous. If the approach works, it could one day help scientists detect emerging pandemics, drug resistance and other biological threats early enough to intervene.

It is the nightmare that keeps virus hunters awake at night: a deadly new bug that leaps from animals to humans before anyone sees it coming. Now a team of scientists says it is building the tool to help catch that threat early. Ben Lamm and George Church — the co-founders

behind Colossal Biosciences, launched Astromech, an artificial intelligence platform designed to predict how life itself will change.

The company soft launched last July and recently announced a fresh $20 million fundraise bringing the total funding to $60 million.

The concept is bold but surprisingly simple. Astromech’s AI has been trained on a staggering

3.8 billion years of evolution, reading the genetic code of creatures both living and long dead to work out how living things adapt and, crucially, where they are heading next. In effect, the company has built a smoke alarm for life on Earth, one designed to detect danger while there is still time to act. “Biology runs the world and historically, we have only reacted to it,” said Lamm, co-founder of Astromech. “We can describe biology in extraordinary detail, yet we still struggle to anticipate what comes next. Astromech is building the AI system predicting how living systems will change and where they are most likely to break. Every genome carries a record of what changed, when it changed, and the tradeoffs that followed —but almost none of that history is readable at scale today. Astromech was built to close that gap, and this funding allows us to further expand that work far more across the tree of life.”

Most science studies life exactly as it is today, frozen in a single snapshot. Astromech is trying to press play to spot the moment a virus is poised to jump species, a life-saving drug is about to stop working, or an endangered animal is quietly sliding towards extinction. Catch those warning signs early enough, its founders emphasize, and a looming disaster becomes a problem we can still handle.

To prove the idea works, the team started with one of humanity’s oldest obsessions: aging. Astromech’s first model compares nature’s most remarkable survivors: Asian elephants that rarely get cancer despite their size; bowhead whales that live beyond 200 years; and thumb-sized bats that live for 40 years against creatures like the Tasmanian devil, ravaged by a rare contagious cancer.

The trick, the scientists say, is reading the hidden switches that decide when our genes turn on and off. “Comparing living species by their genomes can fail to assign DNA differences to functional impacts,” said co-founder Church. “Most of the variations that matter for complex traits, for example, morphology and longevity are regulatory rather than coding, so reconstructing the ancestral regulatory state, not just the ancestral protein, has the crucial explanatory power. That takes functional data across many species rather than sequence alone, and AI reconstruction cheap enough to run genome-wide. Neither was true ten years ago.”

Astromech, still in its early days, has already hit a $3.8 billion valuation. A huge bet on a young idea, and the promise is hard to ignore. Throughout human history, we have watched nature throw its worst at us, leaving humanity sometimes scrambling to respond. This time, scientists are betting we can see it coming.