Converge Bio, a rapidly growing startup based in Boston and Tel Aviv, has raised $25 million in an oversubscribed Series A funding round led by Bessemer Venture Partners. The company is set to get a major financial infusion. Their goal is to revolutionize the pharmaceutical and biotechnology industries by speeding up the processes of drug development using generative artificial intelligence trained on molecular data.
Our founding mission at Converge Bio was to be a generative lab for the whole industry. Second, it gives pharmaceutical companies a platform that enables them to discover and develop new drugs more quickly and efficiently. The startup’s first-in-class technology helps researchers create entirely new types of antibodies. It mimics their interactions with particular targets, greatly accelerating the drug development pipeline.
Converge Bio’s platform employs a state-of-the-art docking system. It includes a physics-based model that simulates how antibodies interact in 3D with their targets. This innovative approach has enabled the early-stage startup to develop antibodies with incredible binding affinities. They have already gotten down now to the single-nanomolar range, essential for drug activity.
Even with its brief history, Converge Bio has made a name for itself by delivering outstanding results for their partners. One multi-institution collaboration was able to increase protein yield an astounding 4 to 4.5 times. To achieve this amazing outcome was only in a single computational iteration. Such a tremendous gain in efficiency couldn’t come at a better time for an industry whose leaders are faced with ever-limited time and resources.
To address the unique and evolving needs of different industries, Converge Bio has released three different versions of its AI systems. These systems help speed up antibody design, protein yield optimization, biomarker and target discovery. With a diverse staff of 34 employees, the company is rapidly establishing a loyal following of clients throughout the U.S., Canada, Europe and Israel. Recently, they put a great deal of effort into pushing their influence over to Asia.
This latest funding round continues Converge Bio’s momentum, following their success in bringing home a $5.5 million seed round in 2024. The major financial support will enable the ambitious startup to further develop its innovative platform. This expansion is key to prospering in an increasingly competitive marketplace that places the premium on speed for drug development.
“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 model, simulates the three-dimensional interactions between the antibody and its target,” – Gertz.
Innovation is at the heart of Converge Bio. This commitment is evident in its innovative technology and its overall approach to shortening research and development timelines for customers. The company endeavors to assist partners in cutting R&D timelines by years. At the same time, it increases their odds of success in the face of exploding costs in drug development.
What makes this startup successful is its atypical approach. It excels when it looks beyond the standardized text-based model for how we grow and share scientific knowledge. Gertz emphasizes the importance of training models on biological data such as DNA, RNA, proteins, and small molecule interactions. This collaborative approach sheds light on the real, practical, and meaningful insights.
“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,” – Gertz.
Converge Bio is in the process of creating more innovative/advanced technology. To help illustrate the value their platform can provide, they’ve recently begun publishing public case studies showcasing platforms success. This transparency goes a long way to engendering trust with potential clients. It serves to cement the company’s status as a leader in the field.
The startup’s adaptability is another key strength. As Gertz points out, Converge Bio plants no flags with a particular architectural style on its AI systems. It brings together popular methodologies such as foundation models, specifically LLMs and diffusion models. It incorporates the use of classical machine learning methods and statistical approaches as needed.
“We’re not tied to a single architecture. We use LLMs, diffusion models, traditional machine learning, and statistical methods when it makes sense,” – Gertz.
As for Gertz, he’s certain that the systems Converge Bio has developed can address the intricacies of drug development. When done well, they can dramatically lower risk and improve value for ratepayers.
“This filtration isn’t perfect, but it significantly reduces risk and delivers better outcomes for our customers,” – Gertz.
The startup promises on-turnkey systems. These systems integrate easily into current workflows, relieving clients from the burden of piecing together different models themselves.
“Our customers don’t have to piece models together themselves. They get ready-to-use systems that plug directly into their workflows,” – Gertz.