AI-Designed Cancer Drug from Insilico Medicine Receives FDA IND Approval to Advance to Clinical Trials

May 24, 2023

Insilico Medicine, a leading company in the use of generative artificial intelligence (AI) for drug discovery and design, has announced that it has received investigational new drug (IND) approval from the FDA for its novel, small molecule inhibitor of USP1 to treat solid tumors. It's the first of Insilico's numerous AI-designed cancer drugs to advance to the clinical validation stage.



ISM3091, as the drug is known, is designed to treat solid tumors via synthetic lethality -- a promising new approach for cancer treatment in which two simultaneous genetic events result in cell death. Using Insilico Medicine's proprietary Pharma.AI platform, scientists found new ways to exploit this redundant pathway, creating a precision-designed therapeutic designed by generative AI.


“PARP inhibitors (PARPi) are the first clinically approved drugs designed to exploit synthetic lethality, which have demonstrated positive clinical treatment effects,” said Sujata Rao, MD, SVP, Head of Global Clinical Development at Insilico Medicine. “However, not all patients respond to PARPi, and those who do benefit often develop resistance. ISM3091 promises to be a next-generation synthetic lethal therapy with the potential to bring innovative solutions to patients with solid tumors.”


The new cancer drug will advance to clinical trials in both the U.S. and China, where scientists will evaluate the safety, tolerability, pharmacokinetics, and preliminary efficacy of ISM3091 in patients with advanced solid tumors. U.S. trials will launch in July 2023. 


Some 30-40% of Insilico's pipeline is focused on oncology targets, including immuno-oncology, and this is the first of its AI-designed cancer drugs to reach the clinical validation stage. The novel AI-designed molecule was one of four that the company presented as posters at the recent American Association for Cancer Research (AACR) Annual Meeting in April 2023. In addition to the USP1 inhibitor, Insilico also presented posters for a MAT2A inhibitor, a DGKA inhibitor, and a CDK12 inhibitor, all designed with its generative AI platform.


“Our oncology pipeline is growing rapidly thanks to the capabilities of our generative AI platform,” says Rao. “We’ve been able to rapidly produce and advance a number of promising potentially first-in-class and best-in-class molecules that we hope can soon bring new therapeutic options to cancer patients who are not responding to other treatments.”

The novel USP1 inhibitor is the company’s third drug to reach clinical trials. The company’s lead drug, ISM018_055, is the first both AI-discovered and AI-designed drug candidate for the treatment of Idiopathic Pulmonary Fibrosis (IPF) and has already been validated in Phase I trials and granted Orphan Drug Designation by the FDA. And Insilico’s COVID-19 drug, ISM3312, which demonstrates broad anti-coronavirus activity, is currently in Phase I trials.


Insilico has built a robust pipeline of promising molecules with its Chemistry42 generative AI drug design engine, which can generate unique molecules from scratch. 


Built on years of modeling and pre-training of large biological, chemical, and textual datasets, Chemistry42 includes 42 generative engines and more than 500 predictive engines for scoring that allows researchers to generate molecules with desired properties through structure-based and ligand-based drug design. Relying on the synergy between its powerful AI platform and strong internal drug discovery expertise, Insilico nominated the preclinical candidate targeting USP1 in April 2022, only 9 months after the program was initiated. 


“Since 2021, Insilico has nominated 12 preclinical candidate compounds, including ISM3091, the small molecule USP1 inhibitor, and our first oncology program to reach the clinical stage,” said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. “We hope to further validate our candidate compound in the multicenter trial, as well as the capabilities of our AI-driven drug discovery platform.”

Insilico Medicine’s AI platform, Pharma.AI, utilizes deep generative models, reinforcement learning, transformers, and other modern machine learning techniques for novel target discovery and the generation of novel molecular structures with desired properties. The company is developing breakthrough solutions to discover and develop innovative drugs for cancer, fibrosis, immunity, central nervous system diseases, infectious diseases, autoimmune diseases, and aging-related diseases.