AI Startup's Cancer Bet That No Lab Could Ever Test

Jan de Vries · 2026-09-18

What if you could test 900 billion drug combinations without ever stepping into a lab? That's the wild idea behind Big Picture Bio, a London-based startup that just came out of stealth with a combined funding round of €2.55 million (about $2.8 million). They're using AI to design cancer drug combinations, and they claim their models can predict clinical trial outcomes with eerie accuracy. ### The Funding Breakdown Here's how the money shakes out: - A €1.75 million (roughly $1.9 million) pre-Seed round co-led by Kadmos Capital and Exceptional Ventures. - €815,000 (around $880,000) in non-dilutive support from Innovate UK's Investor Partnerships Programme. - Gloucester Ventures and angel investor John White also chipped in. Remy Kesrouani, Managing Partner at Kadmos Capital, put it simply: "Big Picture Bio is the culmination of that journey, applying a genuinely differentiated approach to AI to one of drug development's hardest problems: predicting how complex clinical trials will actually behave." ### The Big Idea: A World Model for Cancer Founded by CEO Dr. Kerstin Papenfuss and CTO Dr. Mark Hammond, the company has built a generative "world model" that simulates how tumors, immune cells, and surrounding tissue interact. The goal? Figure out which drug combinations—and in what sequence—are most likely to outsmart cancer resistance. Here's the problem they're tackling: a full pairwise screen of just 100 drugs at 100 doses would require roughly 50 million lab experiments. No physical lab can handle that. But their AI models can search computationally in seconds. > "Cancer is not one disease driven by one target, but we still develop drugs as if it were. Combinations are how we beat it – and with more than 900 billion of them possible, no lab on earth can test its way to the right ones," said Dr. Papenfuss. ### Proven Predictions Big Picture Bio isn't just talking a big game. They say their predictive approach has already been tested against real clinical data. They correctly forecasted the failure of Regeneron's fianlimab trial. And ahead of the 2026 ASCO oncology conference, they posted 14 predictions—12 of which proved accurate. That's not bad for a company that just emerged from stealth. ### From Deep Science Ventures to Big Picture Bio Both founders spent years at Deep Science Ventures (DSV) before spinning out. Papenfuss built and led DSV's therapeutics team, founding 12 therapeutics and enabling-technology companies. Hammond co-founded DSV and took it from €174k to a portfolio worth over €1.16 billion. He also led engineering work on agentic scientific discovery. The pair have worked together for seven years, building companies that tackle complex, evolving diseases. ### What's Next? The funding will take Big Picture Bio's AI-designed cancer combination therapies from computer models into the wet lab. They'll initially focus on cancer and immune-mediated diseases but aim to move beyond trial-and-error combination testing altogether. Their advisory team includes heavy hitters from AstraZeneca, Exscientia, and PhoreMost. So they're not short on expertise. If their models keep predicting trial outcomes accurately, Big Picture Bio could change how we think about drug development. And that's a big picture worth watching.