Dov Gertz is the founder of Converge Bio, a frontier AI lab that trains foundation models directly on DNA, RNA, proteins and small molecules. Biotech and pharma companies use those models to discover and design drugs. When Dov joined us in Episode 32 (February 21, 2026), Converge was a year and ten months old, had raised $33 million and had a team of 40.
Dov's starting point is that biology can be read like text. A human genome is about 3.2 billion nucleotides written in four letters, A, C, G and T. DNA, RNA and proteins can all be represented as sequences, so the same transformer-style architectures behind chatbots can be trained on them. Converge uses its models to predict molecular activity, generate new molecules and predict whether a patient will respond to a drug.
So if computer code is built out of zeros and ones, then we are built out of these four different basic building blocks.
— Dov Gertz, Episode 32
Customers are biotech and pharma companies, and Converge is now opening up to academic labs. Dov described the value as "faster, cheaper, better" and said most products only manage one or two of the three.
Dov walked us through Converge's website at 08:02 and showed its three systems, each built to plug into a workflow customers already run in the lab. The first engineers antibodies, which he called the most common therapeutic approach of the past few years. The second optimizes protein yield, one of the biggest barriers in manufacturing and scale-up. The third is a virtual cell for finding new targets and improving clinical trials through biomarker discovery and patient stratification, which means picking the right patients for a trial. He said the systems show state-of-the-art results and are starting to replace experimental workflows.
Another interesting thing to think of is because of the drastic reduction in cost of sequencing genomes, there's 400 times more sequenced DNA on the Internet than text on the Internet.
— Dov Gertz, Episode 32
But can you actually improve your quality of life and length of life? I think those are the real questions that we should be asking ourselves.
— Dov Gertz, Episode 32
In the news segment, Dov agreed with Jordan that development is moving to the cloud. Some of Converge's machines have 128 GB of RAM for local experiments, but most of its compute runs in the cloud. For other founders working on medicine, see AI in healthcare and our conversation with Dr. Chadi Nabhan on clinical trial site selection.
Sam opened the show with Cell Defense Arena, a late-80s style arcade game made for Converge to use at life science conferences. You defend a blue core from attacking cells, using a "data" power for better targeting and an energy boost, and the game ends when your energy runs out. Sam lasted 46 seconds on air. Dov loved it and asked Sam to send it over for Converge's next conference.
Dov Gertz is the founder of Converge Bio. When he joined Built This Week in February 2026, the company was a year and ten months old, had raised $33 million and had a team of 40.
Converge Bio trains foundation models on DNA, RNA, proteins and small molecules and offers them as systems that plug into biotech and pharma workflows: antibody engineering, protein yield optimization, and a virtual cell for target discovery and patient stratification.
Dov expects AI to shorten discovery, but clinical trials take about five years and he does not expect that to change soon. Instead of ten years, drugs might take six to eight years to reach patients in the foreseeable future.
Dov's hypothesis is cancer first, because it has the most data, then large markets like diabetes, inflammatory bowel and autoimmune disease. He expects neurodegenerative disease to come later.
