Converge Bio Raises $25M to Accelerate AI-Driven Drug Discovery
Artificial intelligence is rapidly transforming drug discovery, as pharmaceutical and biotech companies look to cut years off research timelines while improving success rates amid rising R&D costs. Over 200 startups are now integrating AI directly into research workflows, drawing growing attention from investors. Among them, Converge Bio is emerging as a key player, securing significant funding as competition in AI-driven drug development intensifies.
Generative AI Meets Drug Development
Converge Bio, headquartered in Boston and Tel Aviv, uses generative AI trained on molecular data to help pharma and biotech companies accelerate drug development. The startup has successfully raised an oversubscribed $25 million Series A round, led by Bessemer Venture Partners, with participation from TLV Partners, Vintage Investment Partners, and undisclosed executives from Meta, OpenAI, and Wiz.
The company’s approach involves training AI models on DNA, RNA, and protein sequences and integrating them directly into pharmaceutical workflows to streamline development processes.
“The drug-development lifecycle has defined stages — from target identification and discovery to manufacturing, clinical trials, and beyond — and within each, there are experiments we can support,” said Converge Bio CEO and co-founder Dov Gertz in an exclusive interview with TechCrunch.
“Our platform continues to expand across these stages, helping bring new drugs to market faster.”
Ready-to-Use AI Systems
Converge has introduced three customer-facing AI systems: one for antibody design, one for optimizing protein yields, and another for biomarker and target discovery.
“Take our antibody design system as an example. It’s not just a single model. It’s made up of three integrated components. First, a generative model creates novel antibodies. Next, predictive models filter those antibodies based on their molecular properties. Finally, a docking system, which uses physics-based modeling, simulates the three-dimensional interactions between the antibody and its target,” Gertz explained.
“The value lies in the system as a whole, not any single model. Our customers don’t have to piece models together themselves. They get ready-to-use systems that plug directly into their workflows.”
Rapid Growth and Global Expansion
This funding follows a $5.5 million seed round in 2024, roughly a year and a half ago. Since then, Converge Bio, founded two years ago, has expanded quickly, establishing 40 partnerships with pharmaceutical and biotech companies and running around 40 programs on its platform. The company now serves customers across the U.S., Canada, Europe, Israel, and is entering the Asian market.
The team has grown from nine employees in November 2024 to 34 today. Public case studies highlight the platform’s effectiveness: one partner boosted protein yield by 4 to 4.5X in a single computational iteration, while another generated antibodies with extremely high binding affinity in the single-nanomolar range, Gertz noted.
AI Momentum in Life Sciences
Interest in AI-driven drug discovery is surging across the industry. Last year, Eli Lilly partnered with Nvidia to develop what they described as the pharma sector’s most powerful supercomputer for drug discovery. Meanwhile, in October 2024, developers behind Google DeepMind’s AlphaFold received the Nobel Prize in Chemistry for predicting protein structures with their AI system.
“We feel the momentum deeply, especially in our inboxes. A year and a half ago, when we founded the company, there was a lot of skepticism,” Gertz told TechCrunch.
“That skepticism has vanished remarkably quickly, thanks to successful case studies from companies like Converge and from academia.”
Balancing Innovation and Risk
Large language models (LLMs) are gaining attention in drug discovery for analyzing biological sequences and suggesting new molecules. However, challenges such as hallucinations and accuracy remain significant.
“In text, hallucinations are usually easy to spot. In molecules, validating a novel compound can take weeks, so the cost is much higher,” Gertz said.
To mitigate risks, Converge pairs generative models with predictive ones to filter new molecules, improving outcomes for partners. “This filtration isn’t perfect, but it significantly reduces risk and delivers better outcomes for our customers.”
Addressing skeptics like Yann LeCun, Gertz clarified that Converge does not rely on text-based models for core scientific understanding:
“I’m a huge fan of Yann LeCun, and I completely agree with him. We don’t rely on text-based models for core scientific understanding. To truly understand biology, models need to be trained on DNA, RNA, proteins, and small molecules.”
Text-based LLMs are used only as support tools, for example, to navigate literature on generated molecules. Converge uses a flexible mix of LLMs, diffusion models, traditional machine learning, and statistical methods as appropriate.
A Generative AI Lab for Life Sciences
“Our vision is that every life-science organization will use Converge Bio as its generative AI lab. Wet labs will always exist, but they’ll be paired with generative labs that create hypotheses and molecules computationally. We want to be that generative lab for the entire industry,” Gertz concluded.
As the AI-driven drug discovery sector heats up, Converge Bio’s growth trajectory and recent funding underscore the accelerating shift from traditional trial-and-error approaches toward data-driven molecular design.
0 Comments