Inductive Bio launches Indy, an AI chemistry assistant, to double the capacity of every medicinal chemist

Indy is the world's first medicinal chemistry agent. Indy outperforms Claude Opus 5 and GPT-5.6 Sol in head-to-head benchmarks that include QC'ing new assay data, analyzing SAR, and the design/triage of analogs.

NEW YORK, Sept. 14, 2026 /PRNewswire/ -- Inductive Bio today launched Indy, an AI chemistry assistant, available to partners now. Inductive's medicinal chemists, computational chemists, and DMPK scientists built Indy for their work inside partner programs, where it has doubled the team's productivity. Indy gives every scientist an AI chemistry assistant that has been trained from some of the best drug hunters in the world to work with a program's data and computational tools (including Inductive's benchmark-winning ADMET and PK models) to increase the rigor of every decision made every day on every program.

The constraint on a discovery program is rarely how quickly scientists can come up with new ideas for molecules. It is the quality of the day-to-day analyses and decisions, big and small, that add up over years to the success or failure of a drug program. Do I trust the data from this assay? What does the new data tell us about SAR? What design strategies will get me closer to my TPP? Are my synthetic resources focused on the right targets? What's the fastest route to test my design hypothesis? Are any of our synthetic targets falling behind? Getting the right answers to these questions takes up the majority of medicinal chemists' time, while getting the wrong answers can waste months of a team's time.

Indy removes this operational bottleneck from drug discovery, increasing the rigor of every decision a medicinal chemist makes. Indy parses CRO reports, QCs every dose-response curve, interprets historical SAR to discern trends, runs generative chemistry algorithms, sets up FEP calculations, and generates project update slides for your next meeting. Scientists get more time for the high-impact work only they can do, enabling higher-quality program decisions with greater confidence.

In a head-to-head comparison published today, Indy outperformed Claude Opus 5 and GPT-5.6 Sol on 84 dose-response curves from real programs. Indy had an accuracy of 89%, compared to 39% for GPT-5.6 Sol and 48% for Claude Opus 5, even when Claude and GPT were told to use the highest levels of effort.

"We have incorporated Indy into a number of workflows, including data QC, SAR table construction and analysis, and synthesis queue management," said Nicholas Perl, PhD, head of chemistry at Anvia Therapeutics. "Indy surfaces patterns in the data that help us make better decisions, and it lets me spend less time maintaining slides and more time driving scientific strategy."

"We trained Indy on the tasks that take medicinal chemists' time but not their creativity," said Josh Haimson, co-founder and CEO of Inductive Bio. "The result is an assistant that can double a chemist's productivity while fitting seamlessly into their existing workflows."

Indy is available to Inductive's partners today.

About Inductive Bio

Inductive builds virtual chemistry labs that help drug hunters design higher quality molecules, faster. Inductive's virtual labs are designed to scale proven scientific best practices across medicinal chemistry, computational chemistry, DMPK, and safety, enabling teams to make higher-quality decisions consistently throughout discovery. Inside these virtual labs, AI chemistry assistants, predictive ADMET and PK models, and human-relevant digital organ technologies work together to help scientists evaluate more hypotheses in silico and surface key risks earlier. The most promising molecules move from the virtual lab to the wet lab in a tight feedback loop that accelerates the advancement of high-quality molecules. Inductive already powers dozens of active discovery programs, including collaborations with leading biopharma partners. For more information, please visit www.inductive.bio.

SOURCE Inductive Bio, Inc.