The AI drug discovery sector has seen unprecedented momentum since Google's AlphaFold developers won the Nobel Prize in Chemistry a year ago, with billions in venture capital pouring into the space. In October, Eli Lilly and Nvidia partnered to build the pharmaceutical industry's most powerful AI supercomputer for drug discovery. Last month, Eli Lilly became the first pharma company to reach a $1 trillion market cap.
Despite the momentum, there's still a significant gap between AI promise and reality in drug discovery. "The conversation needs to shift from models to AI systems," said Dov Gertz, CEO and co-founder of Converge Bio. "Unlike ChatGPT, you can't simply prompt a model and get useful results. There's a long road from a model that performs well on benchmarks to an AI system a biologist can actually use. It requires high-quality data, the right architectures for the domain, and a tight experimental validation loop. That's why the vast majority of drug development is still done the old way: through trial and error, taking years and costing hundreds of millions of dollars."
Converge's platform combines multiple proprietary models into an end-to-end system that plugs directly into existing drug development workflows. Biologists use the platform to get actionable outputs, like novel drug targets, optimized antibody candidates, or protein sequences optimized for increased yield, without needing to write code or build infrastructure. The company's models are experimentally validated and trained on Converge's large scale datasets, obtained from their high throughput screening, acquisition of data at scale and rigorous curation of public data. Customers can also use their own proprietary data to create private, fine-tuned instances of Converge's models while retaining full ownership.
The approach is already delivering results across multiple therapeutic areas, including oncology, neurodegenerative, and autoimmune diseases. In the past year, Converge completed over 40 programs with pharmaceutical and biotech companies. These efforts have enabled partners to discover novel antibodies with strong (single-digit nanomolar) binding affinities, consistently improve protein manufacturing yields by 4 to 7x, and identify novel molecular biomarkers to optimize patient response.
"The AI drug discovery revolution is here," said Gertz. "Our goal is simple: make every biotech and pharma company an AI company. We make it easy for scientists to identify where AI can deliver real results for them today, and provide them with our validated tools to get there."
"Converge has something rare in this space: real commercial traction and strong scientific results," said Andrew Hedin, Partner at Bessemer Venture Partners. "The team has built validated solutions that are already delivering results for paying customers. As one of the most results-driven players in the field, we believe Converge is well positioned to be the de facto generative AI lab for the life sciences industry."
About Converge Bio
Converge Bio is an AI platform that enables biotech and pharmaceutical companies to accelerate drug discovery and development. Founded in 2024, Converge's 40-person team has deep expertise in machine learning, computational biology, and drug development; about half hold advanced degrees in related fields. CEO Dov Gertz developed a machine-learning method for discovering novel CRISPR systems, leading to a U.S.-licensed patent and a scientific publication in collaboration with Nobel laureate Jennifer Doudna. CSO Iddo Weiner holds a PhD in Bioinformatics and Biomedical Engineering, and has led the development of two drug programs through positive Phase 2 clinical readouts. CTO Oded Kalev previously led cybersecurity AI teams and has advised U.S. government agencies on large-scale generative AI applications.
Media Contact
Lazer Cohen
[email protected]
347-753-8256
Photo: https://mma.prnewswire.com/media/2860529/Converge_Bio_Team.jpg
SOURCE Converge Bio
Share this article