A startup in Israel is revolutionizing the discovery and development of new drugs and vaccines, by harnessing the power of AI.

Converge Bio builds large language models (LLMs) that accelerate the research process and remove much of the guesswork for biotech and pharmaceutical businesses. It’s like ChatGPT for drug development.

Developing a new drug typically takes 10 years and costs an average of $1 billion. The vast majority – 90 percent – of drugs simply don’t make it. They appear promising at first, but it’s only when they reach the clinical trial stage, typically after three to six years of costly research, that it becomes clear they don’t work.

Converge Bio uses generative AI (artificial intelligence that generates content in response to the user’s request) to weed out many of the “dead end” drugs, select the best prospects, and point researchers in the right direction.

The technology analyzes huge swathes of data and trawls information on millions of molecules to identify those that might work against a specific disease. It also predicts how effective they’re likely to be.

“Just like how ChatGPT can instantly generate a string of words to answer a question, a model trained on biological data can help rapidly design optimized mRNA [messenger molecule] sequences for vaccines, cutting months or years from the process,” said Dov Gertz, the company’s CEO.

“Biological languages, like DNA and RNA, aren’t just random sequences — they have intricate structures and rules, similar to the grammar and syntax of spoken languages.”

Converge Bio, founded six months ago in Tel Aviv, recently announced the raise of $5.5 million in seed funding from Israel-based investors.

The company provides biotech and pharmaceutical businesses with a library of LLMs suited to their particular needs, offering potentially huge savings in terms of time, cost and uncertainty.

In addition to identifying and helping to formulate new drugs, the LLMs also analyze historical data to optimize trials and help navigate the complex regulatory landscapes.

Converge Bio has partnered with Israel-based Teva, one the world’s largest pharmaceutical companies, and with Compugen and BiomX, both cutting-edge drug discovery companies.

“We start by predicting biological outcomes, such as how well a potential drug might work,” said Gertz.

“Then we provide explanations for these predictions in biological terms that scientists can understand and trust. “Finally, we use this knowledge to generate novel biological products, like optimized drug candidates.”

The investment round was led by TLV Partners, a venture capital firm that specializes in early-stage startups, primarily in the technology sector.

Managing Partner Shahar Tzafrir said: “Converge Bio’s approach to integrating generative AI into the very fabric of biology blew us away. The concept of treating biological data as a language is transformative.

“What truly sets Converge Bio apart is their unique ability not just to predict biological outcomes but to explain the reasoning behind those predictions in a way that scientists can trust and act upon.”