AI Startup Emerges to Solve Cancer's Toughest Puzzle

Jan de Vries · 2026-09-18

A London-based biotech startup just stepped out of stealth mode, and they're taking a swing at one of the hardest problems in medicine: figuring out which cancer drug combinations actually work, and in what order. Big Picture Bio, founded by Dr. Kerstin Papenfuss and Dr. Mark Hammond, has raised a combined $2.76 million (£2.2 million) to turn that ambition into reality. The funding includes a $1.9 million pre-Seed round co-led by Kadmos Capital and Exceptional Ventures, plus roughly $880,000 in non-dilutive support from Innovate UK's Investor Partnerships Programme. Gloucester Ventures and angel investor John White also joined the round. ### The Problem With How We Test Cancer Drugs Today Here's the thing about cancer: it's not one disease. It's hundreds of diseases wearing the same name tag. And while we keep developing drugs as if there's a single target to hit, the reality is messier. Cancer adapts. It resists. It finds workarounds. Combinations are how we outsmart it. But here's the catch: if you wanted to test every possible pairing of just 100 drugs at 100 different doses, you'd need around 50 million lab experiments. No lab on Earth can handle that. Not even close. That's where Big Picture Bio comes in. They've built what they call a generative "world model" that simulates how tumors, immune cells, and surrounding tissue interact. Instead of physically testing millions of combinations, their AI searches through them computationally, in seconds. ### A Track Record That's Hard to Ignore This isn't just theoretical. The company says its 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. Twelve of them proved accurate. That's the kind of hit rate that makes people pay attention. "Cancer is not one disease driven by one target, but we still develop drugs as if it were," Papenfuss said. "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 the goal is to design combinations "chosen because they are most likely to work in patients, not because they were the ones we could get to." ### Who's Behind the Wheel Papenfuss and Hammond aren't newcomers. They spent years at Deep Science Ventures, where Papenfuss built and led the therapeutics team, founding 12 companies during her tenure. Hammond co-founded DSV and helped grow it from a $190,000 operation into a portfolio worth over $1.26 billion. They've worked together for seven years. Their advisory team reads like a who's who of pharma: Dr. Laura Rosenberg and Dr. Duncan Young from AstraZeneca, Dr. Garry Pairaudeau (former CTO of Exscientia), and Dr. Christian Dillon (CSO at PhoreMost). ### What Happens Next The funding will take Big Picture Bio's AI-designed cancer combinations from computer models into the wet lab. They're starting with cancer and immune-mediated diseases, but the long-term vision is bigger: move beyond trial-and-error combination testing altogether. Remy Kesrouani, Managing Partner at Kadmos Capital, put it simply: "Big Picture Bio is applying a genuinely differentiated approach to AI to one of drug development's hardest problems." If they pull it off, the way we discover cancer treatments could change for good.