Converge Bio Secures $25M to Revolutionize Drug Discovery with Generative AI
The pharmaceutical and biotechnology industries are undergoing a seismic shift, driven by the promise of artificial intelligence (AI) to dramatically accelerate drug development and reduce escalating research and development (R&D) costs. Years can be shaved off traditional timelines, and the probability of success significantly increased with the integration of AI into research workflows. More than 200 startups are now vying for a piece of this burgeoning market, attracting substantial investor interest. Converge Bio, a Boston- and Tel Aviv–based startup, is the latest to capitalize on this trend, recently securing a significant funding boost to fuel its growth in the AI-driven drug discovery space.
Converge Bio’s Series A Funding and Market Position
Converge Bio has successfully closed an oversubscribed Series A funding round of $25 million, led by Bessemer Venture Partners. The round also saw participation from TLV Partners, Vintage Investment Partners, and strategic investments from executives at Meta, OpenAI, and Wiz. This new capital injection follows a $5.5 million seed round raised in 2024, demonstrating rapid progress and investor confidence in the company’s vision.
How Converge Bio is Leveraging Generative AI for Drug Development
Converge Bio distinguishes itself by focusing on generative AI models trained on vast datasets of molecular information – DNA, RNA, and protein sequences. These models are then seamlessly integrated into the existing workflows of pharmaceutical and biotechnology companies, streamlining and accelerating the drug development process. The company’s approach isn’t about replacing traditional “wet labs” but rather augmenting them with powerful computational capabilities.
A Platform Expanding Across the Drug Development Lifecycle
According to Dov Gertz, CEO and co-founder of Converge Bio, the platform is designed to support various stages of drug development. “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,” Gertz explained in an exclusive interview with GearTech. “Our platform continues to expand across these stages, helping bring new drugs to market faster.”
Three Core AI Systems Driving Innovation
Converge Bio has already launched three customer-facing AI systems:
- Antibody Design: A sophisticated system for creating novel antibodies with desired properties.
- Protein Yield Optimization: An AI-powered tool to maximize protein production efficiency.
- Biomarker and Target Discovery: A system designed to identify promising biomarkers and drug targets.
The antibody design system exemplifies Converge Bio’s integrated approach. It combines a generative model for antibody creation, predictive models for filtering based on molecular characteristics, and a physics-based docking system to simulate interactions between the antibody and its target. “Our customers don’t have to piece models together themselves. They get ready-to-use systems that plug directly into their workflows,” Gertz emphasizes. The value proposition lies in the holistic system, not individual components.
Rapid Growth and Expanding Partnerships
Since its inception two years ago, Converge Bio has experienced significant growth. The company has secured 40 partnerships with pharmaceutical and biotech companies and is currently managing approximately 40 programs on its platform. Its customer base spans the U.S., Canada, Europe, Israel, and is now expanding into Asia. The team has also grown from nine employees in November 2024 to 34 employees today.
Demonstrated Results: Case Studies Showcase Impact
Converge Bio is backing up its claims with tangible results. Published case studies demonstrate the platform’s effectiveness. One study showed a 4 to 4.5x increase in protein yield through a single computational iteration. Another highlighted the generation of antibodies with exceptionally high binding affinity, reaching the single-nanomolar range.
The Rise of AI in Drug Discovery: A Broader Trend
Converge Bio’s success is part of a larger trend of increasing investment and innovation in AI-driven drug discovery. Last year, Eli Lilly partnered with Nvidia to build a high-performance supercomputer specifically for drug discovery. Furthermore, the developers of Google DeepMind’s AlphaFold, an AI system capable of predicting protein structures, were awarded the Nobel Prize in Chemistry in October 2024, underscoring the transformative potential of AI in the field.
Navigating the Momentum and Future of Molecular Design
Gertz believes the industry is witnessing the largest financial opportunity in the history of life sciences, with a fundamental shift occurring from “trial-and-error” approaches to data-driven molecular design. “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 GearTech. That skepticism has largely dissipated, fueled by successful case studies from companies like Converge Bio and advancements in academic research.
Addressing the Challenges of Large Language Models (LLMs)
While large language models (LLMs) are gaining traction in drug discovery for their ability to analyze biological sequences and propose new molecules, challenges remain, including the risk of “hallucinations” and accuracy concerns. “In text, hallucinations are usually easy to spot,” Gertz explains. “In molecules, validating a novel compound can take weeks, so the cost is much higher.”
Converge Bio mitigates these risks by pairing generative models with predictive models, effectively filtering new molecules to improve outcomes. “This filtration isn’t perfect, but it significantly reduces risk and delivers better outcomes for our customers,” Gertz added.
Beyond Text: The Importance of Biological Data
Acknowledging the skepticism of experts like Yann LeCun regarding the use of LLMs, Gertz clarifies that Converge Bio doesn’t 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,” Gertz explained. Text-based LLMs are used as supporting tools, such as assisting customers in navigating literature related to generated molecules, but they are not the core technology.
Converge Bio adopts a flexible approach, utilizing LLMs, diffusion models, traditional machine learning, and statistical methods as appropriate. “We’re not tied to a single architecture. We use LLMs, diffusion models, traditional machine learning, and statistical methods when it makes sense.”
Converge Bio’s Vision: A Generative AI Lab for Every Life Science Organization
“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 concludes. The company’s focus on integrating AI directly into existing workflows, coupled with its demonstrated results and strategic funding, positions it as a key player in the ongoing revolution of drug discovery.