image: With the aid of Pharma.AI, Insilico’s proprietary AI platform for drug discovery and scientific research, the Insilico scientists have unveiled a series of potent and selective HPK1 inhibitor series for immunotherapy, each with better druggability potential compared to the previous one.
Credit: Insilico Medicine
Hematopoietic progenitor kinase 1 (HPK1), a member of the Ste20 serine/threonine kinases family, negatively regulates T cell function and is considered a promising target for immunotherapy. Despite the promising efficacy demonstrated in preclinical models, no HPK1 inhibitors are currently approved for clinical use, due to challenges including balance between kinase selectivity and pharmacokinetic properties.
CAMBRIDGE, Mass., Dec 17, 2024 --- Insilico Medicine (“Insilico”), a clinical-stage generative artificial intelligence (AI)-driven drug discovery company, is proud to announce its latest AI-powered research advancement, published on European Journal of Medicinal Chemistry, ACS Medicinal Chemistry Letters, and Journal of Medicinal Chemistry in a row. With the aid of Pharma.AI, Insilico’s proprietary AI platform for drug discovery and scientific research, the Insilico scientists have unveiled a series of potent and selective HPK1 inhibitor series for immunotherapy, each with better druggability potential compared to the previous one.
“As a researcher often involved in drug discovery efforts, I get the feeling that AI is truly a powerful helping hand in the biopharmaceutical industry,” says Jingjing Peng, PhD, the first author of the paper and a medicinal chemist at Insilico Medicine, “In our work, we utilized AI to systematically identify and optimize HPK1 inhibitors with enhanced potency and selectivity. The workflow was streamlined, and we were excited to see the constant improvement at each milestone.”
In the first paper published in September 2024, the team employed PandaOmics, the AI-powered discovery engine affiliated to Pharma.AI, which integrates over 20 AI bioinformatic models and billions of data points, for HPK1 target evaluation. Supported by the knowledge graph based on AI analysis, as well as previous studies, HPK1 is hypothesized to mitigate select immune responses, laying the foundation for further molecule design and synthesis.
With a novel candidate compound identified with potent in vitro activity, markedly improved PK properties, strong in vivo anti-tumor activity and promising toxicity profiles, Insilico scientists achieved a starting point for further optimization of kinase selectivity and more properties.
About 45 days later, the Insilico research team elaborates on the synthesis and optimization of spiro series HPK1 inhibitors in the second publication, which achieved not only nanomolecular HPK1 inhibition activity, but also good kinase selectivity against GLK with the aid of Chemistry42, Insilico’s comprehensive generative chemistry platform also under Pharma.AI.
Utilizing a conformation restriction strategy, the development efforts began with a currently available HPK1 inhibitor desiring improvements in oral exposure, bioavailability and clearance in animal models, yielding a selected compound with promising antitumor efficacy in murine colon cancer model and a synergistic effect when combined with anti-PD-1.
The final paper in the series had increased AI input, introducing a series of potent, selective HPK1 inhibitors with a pyridine-2-carboxamide core generated by Chemistry42, using a structure-based drug design and hybrid strategy. The candidate compound displayed improved kinase selectivity against GLK and improved PK properties compared with the previous HPK1 inhibitors. Moreover, AI models guided the iterative design process, and AI-assisted docking models helped analyze the key binding interactions with HPK1.
To conclude, Insilico’s generative AI applications under Pharma.AI have assisted the drug discovery process from target evaluation to molecule design and optimization. With the peer-reviewed publication trilogy, Insilico team produced a relatively balanced HPK1 inhibitor candidate with adequate in vitro ADME, in vivo PK properties, good oral bioavailability across multiple species, and most importantly, robust in vivo efficacy in various cancer models.
“Since Insilico’s foundation in 2014, I have seen, with my own eyes, lots of proof-of-concept cases in AI-driven drug discovery, and they are scattered across diseases areas and stages of the drug R&D process,” says Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine. “The application of AI is revolutionizing the whole scientific research spectrum by enabling us to tackle complex challenges more efficiently and effectively, so that we’ll be living healthier, better, and more sustainable lives.”
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. Powered by Pharma.AI, Insilico has nominated 21 preclinical candidates in its comprehensive portfolio of over 30 assets since 2021 and has received IND clearance for 10 molecules.
In early 2024, Insilico published a Nature Biotechnology paper presenting the entire R&D journey from AI algorithms to Phase II clinical trials of ISM001-055, the company's lead drug pipeline with AI-discovered target and AI-designed structure. Following that, Insilico has recently announced positive preliminary results from a Phase IIa trial (NCT05938920), where ISM001-055 showed favorable safety and tolerability across all dose levels, as well as dose-dependent response in forced vital capacity (FVC), after only 12 weeks of dosage.
References
[1] Peng, J., Ding, X., Shih, P., Meng, Q., Ding, X., Zhang, M., Aliper, A., Ren, F., Lu, H., & Zhavoronkov, A. (2024). Discovery of 1(2H)-phthalazinone and 1(2H)-isoquinolinone derivatives as potent hematopoietic progenitor kinase 1 (HPK1) inhibitors. European Journal of Medicinal Chemistry, 279, 116877. https://doi.org/10.1016/j.ejmech.2024.116877
[2] Peng, J., Ding, X., Chen, C. X. J., Shih, P., Meng, Q., Ding, X., Zhang, M., Aliper, A., Ren, F., Lu, H., & Zhavoronkov, A. (2024). Design, synthesis, and biological evaluation of a series of spiro analogues as novel HPK1 inhibitors. ACS Medicinal Chemistry Letters, 15(11), 2032–2041. https://doi.org/10.1021/acsmedchemlett.4c00434
[3] Peng, J., Ding, X., Chen, C. X. J., Shih, P., Meng, Q., Ding, X., Zhang, M., Aliper, A., Ren, F., Lu, H., & Zhavoronkov, A. (2024b). Design, synthesis, and biological evaluation of a series of spiro analogues as novel HPK1 inhibitors. ACS Medicinal Chemistry Letters, 15(11), 2032–2041. https://doi.org/10.1021/acsmedchemlett.4c00434
About Insilico Medicine
Insilico Medicine, a global clinical stage biotechnology company powered by generative AI, is connecting biology, chemistry and clinical trials analysis using next-generation AI systems. The company has developed AI platforms that utilize 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. Insilico Medicine 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.