AI Startup's Bold Bet: 50 Million Lab Tests in Seconds?

Jan de Vries · 2026-09-18

What if you could test 50 million drug combinations without ever stepping into a lab? That's the promise of a London-based startup that just emerged from stealth with a cool $2.8 million in funding. ### The Big Idea: Simulating Cancer to Outsmart It Big Picture Bio is developing AI-designed combination therapies for cancer and other complex diseases. Their secret sauce? A generative "world model" that simulates how tumors, immune cells, and surrounding tissue interact. The goal is to predict which drug combinations—and in what sequence—are most likely to overcome cancer resistance. Think about it: 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 Big Picture Bio's models can search computationally in seconds. ### The Money Behind the Mission The company raised a combined $2.8 million (€2.55 million) in funding. Here's how it breaks down: - A $1.9 million (€1.75 million) pre-Seed round co-led by Kadmos Capital and Exceptional Ventures. - $890,000 (€815k) in non-dilutive support from Innovate UK's Investor Partnerships Programme. - Participation from Gloucester Ventures and angel investor John White. Remy Kesrouani, Managing Partner at Kadmos Capital, said, "I had the privilege of working closely with Kerstin and Mark at the very beginning of Deep Science Ventures, and saw first-hand the determination, conviction and sheer resolve they bring to building ambitious, scalable businesses." He added, "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 Minds Behind the Model Founded by CEO Dr. Kerstin Papenfuss and CTO Dr. Mark Hammond, Big Picture Bio isn't their first rodeo. Both spent years at Deep Science Ventures. Papenfuss built and led DSV's therapeutics team, founding 12 therapeutics and enabling-technology companies. Hammond co-founded DSV and took it from $190k to a portfolio worth over $1.3 billion. They've worked together for seven years, tackling complex diseases. Now, they're betting that AI can do what labs can't: find the right combinations faster. ### Early Wins and Big Promises The company says its predictive approach has already been tested against real clinical data. It correctly forecasted the failure of Regeneron's fianlimab trial. And ahead of the 2026 ASCO oncology conference, it posted 14 predictions—12 proved accurate. Dr. Papenfuss said, "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." She added, "That is the problem we built Big Picture Bio to solve: model the disease as the dynamic system it actually is, then design against it – combinations chosen because they are most likely to work in patients, not because they were the ones we could get to. This funding takes our first designed combinations out of the model and into the lab." ### What's Next? Big Picture Bio will use the funding to take its AI-designed cancer combination therapies from computer models into the wet lab. Initially, they'll focus on cancer and immune-mediated diseases. But their ultimate goal is to move beyond trial-and-error combination testing altogether. With a team of advisors from AstraZeneca, Exscientia, and PhoreMost, they're well-positioned to make a dent in drug development. If their models can consistently predict clinical outcomes, it could change how we approach cancer treatment. The startup's approach is a reminder that sometimes the biggest breakthroughs come from thinking differently—and from being willing to simulate millions of possibilities before ever touching a petri dish.