KRAS, one of the most frequently mutated oncogenes, plays a fundamental role in cancer progression by regulating cellular proliferation and survival, and pan-KRAS inhibition has been of great interest due to broader application settings and anti-resistance potential. However, the high affinity of KRAS for GDP/GTP and the elusive nature of druggable pockets on the protein have posed challenge in drug development for decades.

Insilico Medicine, a clinical-stage biotechnology company driven by generative artificial intelligence (AI), today announces the development of novel pan-KRAS inhibitors of new chemotypes through structure-based drug design, scaffold hopping combined with intense molecular modeling, empowered by the generative chemistry methods of Chemistry42, Insilico’s proprietary generative chemistry platform. Developed in the joint efforts of artificial intelligence and human expertise, the candidate compounds demonstrated pan-KRAS inhibition with potency in the upper nanomolar range. The results have been recently published on ACS Medicinal Chemistry Letters.

The research started with an existent molecule with selectivity toward a certain KRAS variant, aiming to identify novel chemotypes in the field of pan-KRAS inhibitors. A diverse library of compounds with various central cores was designed utilizing the generative modules of Chemistry42, Insilico’s proprietary generative chemistry platform integrating more than 40 generative models after evaluation and optimization.

Using the Chemistry42 virtual screening module, the researchers conducted scaffold hopping, molecular modeling and structure-activity relationship (SAR) studies to refine the central core, before moving on to the SAR exploration around the amino side chain. With promising candidate compounds, synthesis and rigorous testing were carried out to evaluate potency, selectivity, and other druggability properties.

According to test results, the research yielded hit series that demonstrated mild selectivity toward KRAS mutants over the wild-type, up to 4-fold difference in potency. Additionally, the pan-KRAS inhibitors exhibited robust inhibition in KRAS mutant cell lines, as well as acceptable CYP inhibition profile in the current stage.

“I am thrilled to witness how our AI-driven Chemistry42 platform is transforming drug discovery,” said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. “This research highlights the potential of advanced molecular modeling and scaffold hopping to tackle challenging targets like KRAS, previously considered 'undruggable’, further validating the power of AI in accelerating the development of optimized clinical candidates.”

In 2016, Insilico first described the concept of using generative AI for the design of novel molecules in a peer-reviewed journal, which laid the foundation for the commercially available Pharma.AI platform. Since then, Insilico keeps integrating technical breakthroughs into Pharma.AI platform, which is currently a generative AI-powered solution spanning across biology, chemistry, medicine development and science research. Since its inception in 2014, Insilico has published over 200 peer-reviewed papers and has held more than 600 patents and patent applications.

References
[1] Aladinskiy, V. et al. (2025) 'Identification of novel pan-KRAS inhibitors via Structure-Based drug design, scaffold hopping, and biological evaluation,' ACS Medicinal Chemistry Letters [Preprint]. https://doi.org/10.1021/acsmedchemlett.5c00080.

About Insilico Medicine
Insilico Medicine, a leading and global AI-driven biotech company, utilizes its proprietary Pharma.AI platform and cutting-stage automated laboratory to accelerate drug discovery and advance innovations in life sciences research. By integrating AI and automation technologies and deep in-house drug discovery capabilities, Insilico is delivering innovative drug solutions for unmet needs including fibrosis, oncology, immunology, pain, and obesity and metabolic disorders. Additionally, Insilico is extending the reach of Pharma.AI across diverse industries, such as advanced materials, agriculture, nutritional products and veterinary medicine.
For more information, please visit www.insilico.com.