Nature Communications | Insilico Medicine Presents AI-empowered Dual-Action PROTAC Targeting PKMYT1

• AI Designs a Novel RPOTAC from Scratch: Insilico's generative AI platform, Chemistry42, successfully designed a first-in-class PROTAC targeting PKMYT1 by creating an entirely new inhibitor and its complex linker, demonstrating a powerful, end-to-end approach to new modality drug discovery.
• A Superior Dual-Action Mechanism: The novel PROTAC, D16-M1P2, employs a powerful dual-action mechanism that simultaneously degrades and inhibits the cancer-driving PKMYT1 protein, resulting in a more potent, selective, and durable therapeutic effect than traditional inhibitors.
• Strong Preclinical Results Move Therapy Forward: The AI-designed PROTAC delivered potent anti-tumor activity with high selectivity and favorable oral bioavailability in preclinical studies and has now advanced to the pre-candidate validation stage.

CAMBRIDGE, Mass., Dec. 2, 2025 /PRNewswire/ -- PKMYT1 (Membrane-associated Tyrosine/Threonine Protein Kinase 1) is a serine/threonine protein kinase that plays a pivotal role in cell cycle regulation. Previous studies have shown that inhibiting PKMYT1 through a synthetic lethality approach allows for the selective elimination of cancer cells bearing specific genetic mutations, such as CCNE1 amplification or mutations in FBXW7 and PPP2R1A, while sparing normal healthy cells and minimizing adverse effects. It makes PKMYT1 a promising therapeutic target for biomarker-defined patient populations.

However, existing PKMYT1 inhibitors face significant limitations, including insufficient molecular diversity and poor selectivity, which can lead to off-target effects and dose-limiting toxicity in clinical trials. Additionally, concerns about acquired resistance arising from mutations in cancer cells further complicate inhibitors' efficacy. Research also indicates that PKMYT1 has important non-catalytic functions, such as stabilizing β-catenin and activating Wnt signaling, which are not addressed by conventional inhibitors. These challenges underscore the need for new therapeutic strategies that can more effectively and safely target PKMYT1 in cancer.

In a recent pioneering study, researchers at Insilico Medicine ("Insilico"), a generative artificial intelligence (AI)-driven clinical-stage biotechnology company, harnessed its AI-driven generative chemistry platform, Chemistry42, to design a novel, first-in-class PROTAC targeting PKMYT1, D16-M1P2, which employs a dual mechanism of action—inducing PKMYT1 degradation while directly inhibiting its kinase activity. This innovative strategy holds promises for overcoming limitations of existing inhibitors, such as poor selectivity and acquired resistance, and to effectively target both the catalytic and non-catalytic functions of PKMYT1. As a result, the PROTAC demonstrates the potential for a more selective, potent, and durable therapeutic effect.

Published in Nature Communications, this work highlights the powerful capabilities of Insilico's AI-driven generative chemistry and serves as a compelling example of its ability to guide complex, multi-component drug design.

The process of discovery began with the design of PKMYT1 inhibitors. Researchers at Insilico utilized the Chemistry42 AI platform to design a novel PKMYT1 inhibitor by integrating the pharmacophore features of two established kinase inhibitors. Guided by over 40 AI models within Chemistry42, they generated 2,023 novel molecules. A thorough filtering process—assessing novelty, binding interactions, and drug-like properties—identified the most promising candidate, which was subsequently synthesized as compound 1.

Subsequently, the team systematically optimized compound 1 through structure-based design and medicinal chemistry. This iterative process enhanced its potency and pharmacokinetic properties, ultimately yielding compound 4—an inhibitor with excellent kinase selectivity that provided an ideal attachment point for PROTAC development.

After obtaining the optimized inhibitor, the team constructed a 3D virtual model of the PKMYT1–PROTAC–CRBN ternary complex to determine optimal linker parameters. Leveraging the Chemistry42 AI platform, they generated novel linkers to connect compound 4 to the E3 ligase, ultimately synthesizing the first-generation PROTAC, D1. Through subsequent evaluation and modification, the PROTACs were further optimized for solubility, clearance, and oral exposure, leading to the development of D16-M1P2 as the final lead candidate.

The lead PROTAC, named D16-M1P2, demonstrated promising performance in preclinical studies.It exhibited remarkable selectivity, inhibiting only 4 out of 403 kinases tested, which resulted in potent anti-tumor activity in xenograft models as well as favorable oral bioavailability across multiple preclinical species. Compared to traditional PKMYT1 inhibitors, D16-M1P2 induces more durable and sustained effects by targeting PKMYT1 for complete degradation through the ubiquitin-proteasome system, with activity maintained for at least 24 hours after drug removal. Additionally, D16-M1P2 offers a dual mechanism of action: it primarily degrades PKMYT1 but also directly inhibits residual kinase activity at higher concentrations, ensuring comprehensive pathway suppression.

"The dual-mechanism of D16-M1P2, combining potent degradation with kinase inhibition, offers a multi-pronged attack on a critical cell cycle regulator in cancer," said Feng Ren, PhD, co-CEO and Chief Scientific Officer of Insilico Medicine. "Its high selectivity and sustained pharmacodynamic effects observed in preclinical studies suggest it could overcome the safety and efficacy limitations of previous PKMYT1 inhibitors. This molecule serves as both a powerful chemical probe to study PKMYT1 biology and a promising new therapeutic candidate."

The research team has now advanced D16-M1P2 to the Pre-Candidate (Pre-PCC) validation stage. Previously, Insilico published the design and optimization process of the PKMYT1 inhibitor series from this program in the JMC in February 2025. Building on this foundation, the new research upgrades the modality from small molecules to PROTACs, achieving further improvements in selectivity, safety, and efficacy. This study also exemplifies how AI tools can adeptly navigate the complexities of PROTAC design—spanning inhibitor design to linker optimization —pioneering new directions in AI-driven drug discovery.

"This paper is a clear demonstration of our AI platform's ability to innovate beyond conventional small molecules and tackle next-generation therapeutic modalities like PROTACs," said Alex Zhavoronkov, PhD, founder and co-CEO of Insilico Medicine. "By generating both the novel warhead and the optimal linker, we have shown that AI can be an invaluable partner in designing highly specific, multi-functional drugs for challenging cancer targets."

Since its inception, Insilico has published over 200 peer-reviewed papers. This marks the sixth publication by the company in Nature Portfolio journals since 2024. Leveraging sustained scientific breakthroughs at the intersection of biotechnology, artificial intelligence, and automation, Insilico ranked Top 100 global corporate institutions in Nature Index's "2025 Research Leaders: global corporate institutions for biological sciences and natural sciences publications".

Harnessing state-of-the-art AI and automation technologies, Insilico has significantly improved the efficiency of preclinical drug development, setting a benchmark for AI-driven drug R&D. While traditional early-stage drug discovery typically requires 2.5 to 4 years, Insilico has nominated 20 preclinical candidates with an average timeline—from project initiation to preclinical candidate (PCC) nomination—of just 12 to 18 months per program, with only 60 to 200 molecules synthesized and tested in each program.

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 extends 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.

SOURCE Insilico Medicine