AI-driven Molecular Glue Innovation: Insilico Nominates ISM9546, an Oral, Peripheral-Restricted VAV1 Degrader as PCC for Autoimmune Diseases

• Sustained Boost in AI-Driven R&D Productivity: ISM9546 marks Insilico Medicine's 35th preclinical candidate (PCC) nominated since 2021 and its 11th PCC within the first 10 months of 2026 alone, setting a new record for the company's annual pipeline output efficiency.
• AI-Enabled Molecular Glue Design for Undruggable Targets: Designed and optimized with AI, ISM9546 features a peripherally restricted profile that reduces central nervous system (CNS) risks through minimal brain exposure, while demonstrating favorable tolerability and broad safety margins.
• Robust Preclinical Efficacy: ISM9546 demonstrated sub-nanomolar degradation potency in cellular assays and achieved a significant reduction in Disease Activity Index (DAI) within days of treatment in disease models; histopathological analysis further confirmed its anti-inflammatory effects, reducing pathology scores by approximately 60%.

CAMBRIDGE, Mass., Oct. 13, 2026 /PRNewswire/ -- VAV1 (Vav guanine nucleotide exchange factor 1) plays a key role in immune cell signaling pathways, holding immense potential in autoimmune disease intervention by controlling immune cell activation, proliferation, cytoskeletal dynamics, and downstream cytokine secretion. However, due to challenges including the lack of a classic small-molecule binding pocket, VAV1 has long been considered "undruggable", until molecular glue therapies emerge as a new-modality solution.

Insilico Medicine ("Insilico", HKEX: 3696), a clinical-stage drug discovery company powered by generative artificial intelligence (AI), today announced the nomination of ISM9546, an orally bioavailable, peripheral-restricted VAV1 molecular glue degrader for the potential treatment of autoimmune diseases including IBD (inflammatory bowel disease) and RA (rheumatoid arthritis). Empowered by Insilico's proprietary Pharma.AI solution, ISM9546 not only marks the 35^th PCC nomination of the company since 2021, but also strikes a balance between efficacy and safety, with nanomolar activity validated across cell assays, and peripherally restricted trait to alleviate risks related to the CNS (central nervous system).

"The potential of AI reaches far beyond conventional small molecules, as multiple emerging therapeutic modalities and even our whole exploration into the chemical space could benefit," says Feng Ren, PhD, Co-CEO and Chief Scientific Officer of Insilico Medicine. "At Insilico, we have been working on new modalities including PROTACs, peptides, mRNA therapies, and more. The PCC nomination of our molecular glue degrader ISM9546 further broadens the potential of our Pharma.AI platform, proving that generative AI can systematically crack challenging targets and complex mechanisms of action to deliver novel, highly selective and safe treatment options."

Leveraging its proprietary generative chemistry platform, Chemistry42, the research team at Insilico Medicine carried out the design and optimization of novel VAV1 degraders. This platform integrates more than 40 generative models and multiple predictive modules, enabling an end-to-end drug design workflow spanning molecular generation, property prediction, and multi-parameter optimization. Based on the structure of the target–ligand complex and its key interaction patterns, the team defined a pharmacophore according to the ligand structure and key binding-pocket residues, and employed Chemistry42 to focus the design on de novo fragment growing. By reinforcing key interactions with the protein while balancing improved potency with reduced CNS exposure, the platform achieved multi-objective molecular optimization. Through multiple rounds of design–make–test–analyze (DMTA) iterations, ISM9546 ultimately emerged as the PCC compound.

In preclinical studies, ISM9546 exhibited sub-nanomolar VAV1 degradation potency across multiple cell-based assays. Oral administration of ISM9546 also demonstrated robust and consistent efficacy across several animal models of inflammatory bowel disease (IBD).

In an animal model of acute colitis, ISM9546 demonstrated a significant reduction in disease activity, as measured by the Disease Activity Index (DAI), was observed within just a few days of treatment initiation and was sustained throughout the study period. Compared with a reference VAV1 degrader, ISM9546 exhibited superior disease control, resulting in significantly lower cumulative DAI scores. Histopathological analysis further showed substantial reductions in inflammatory cell infiltration and intestinal tissue injury, with histopathology scores improved by approximately 60%. Collectively, these findings support the further advancement of this ISM9546 for the treatment of IBD.

Moreover, extensive in vitro & in vivo evaluations confirm that ISM9546 possesses a well-differentiated safety and pharmacokinetic profile. Both in vitro MDCKII-MDR1 assays and in vivo tissue distribution studies demonstrated low brain exposure, a signal for lower CNS safety risks, while 14-day rodent and non-human primate toxicity evaluations demonstrated favorable tolerability and broad safety margins, supported by proteomics profiling showing a clean degradation profile with no off-target protein depletion observed.

The candidate also displays a balanced elimination half-life, providing sustained peripheral target engagement while allowing for prompt recovery of adaptive immune responses in the event of acute infection.

"From fibrosis to inflammation and immune disorders, and into metabolism, Insilico is cracking the hallmarks of aging, one after another, with generative AI," says Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. "By developing therapies at record speed, with enhanced profiles, we are tackling the underlying drivers of chronic illness, and in the end, the aging process itself. Insilico's AI-driven pipelines are providing more options for various disease areas with reduced cost, and we might already have the first therapy to extend healthy longevity at scale today, just that no one has proved or noticed it."

To date, Insilico announced the nomination of 11 preclinical candidate compounds (PCCs) in the first 10 months of 2026, breaking the company's historical record for annual pipeline output pushing the total number of PCCs nominated since 2021 to 35, validating the R&D efficiency of generative AI through reproducible, real-world examples. According to the 2026 interim report, as of the middle of August, Insilico has achieved 8 clinical milestones across its internal and partnered pipelines. Leading these R&D advances is Rentosertib (ISM001-055), the world's first potential first-in-class drug candidate enabled by generative AI. Rentosertib has officially entered Phase III clinical trials for the treatment of idiopathic pulmonary fibrosis (IPF), taking a crucial step toward clinical validation and commercialization.

Since launching the MMAI Gym model training and evaluation ecosystem in 2026, Insilico Medicine has established AI co-development collaborations with Liquid AI (focused on liquid foundation models), Human Longevity (focused on precision health and longevity research), and others. Leveraging the MMAI Gym evaluation ecosystem, Insilico established and published benchmark leaderboard portals evaluating general-purpose model capabilities across specialized domains such as scientific reasoning, longevity research, and drug discovery, making evaluation results publicly accessible online. Notably, the Longevity benchmark focusing on the biology of aging was recently featured on the cover of a Cell special issue.

Additionally, in July, Insilico released the industry's first "Drug Discovery Benchmark Evaluation" dataset, aiming to systematically assess the comprehensive performance of foundation models in the field of drug discovery. Recently, the company further announced the launch of a series of cutting-edge chemistry and biology expert models trained and driven by MMAI Gym for Science. These models have demonstrated State-of-the-Art (SOTA) performance across over 50 benchmark tasks. Backed by this novel capability, Insilico is poised to drive scaled innovation, explore new modalities, and expand into diversified indications, further accelerating the discovery and development of "longevity drugs".

Driven by broad global recognition of its AI platform and pipeline assets, Insilico recently announced total revenue of approximately $106 million for the first half of 2026, representing a year-over-year increase of 287%, alongside an adjusted net profit exceeding $51 million—marking its first profitable half-year since listing. This financial milestone was primarily propelled by a series of out-licensing, co-development, and R&D collaborations with leading global partners, including Eli Lilly, Servier, Takeda, SK Biopharmaceuticals, Qilu Pharmaceutical, Hygtia Therapeutics, China Medical System (CMS), and Tenacia Biotechnology. According to the 2026 interim report, as of the middle of August, Insilico's disclosed deal value for signed collaborations in 2026 alone has reached approximately $7.3 billion, bringing the company's cumulative total signed deal value since 2021 to nearly $11 billion.

About Insilico Medicine
Insilico Medicine is a pioneering global biotechnology company dedicated to integrating artificial intelligence and automation technologies to accelerate drug discovery, drive innovation in the life sciences, and extend healthy longevity to people on the planet. The company was listed on the Main Board of the Hong Kong Stock Exchange on December 30, 2025, under the stock code 03696.HK.

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