image: Discovery and Development of ISM5939
Credit: Insilico Medicine
- Publication showcases the capabilities of Insilico's advanced generative AI platform and integrated workflow in facilitating the rapid development of ISM5939, further demonstrating the potential of AI in drug discovery.
- Unlike direct STING agonists, ISM5939 precisely modulates the STING pathway within tumor tissues by targeting ENPP1, thereby restoring local immune activation and enhancing anti-tumor immune responses.
- For the first time, ENPP1 inhibitors have been shown to overcome dual resistance to immune checkpoint inhibitors and chemotherapy, offering a new therapeutic hope for patients with refractory tumors.
- Since the start of 2025, this marks Insilico Medicine’s third AI-driven drug discovery study published in a Nature sub-journal.
Immune checkpoint inhibitors have transformed cancer treatment, providing clinical benefits for a wide range of malignancies. However, only ~10-35% of patients on these treatments achieve a meaningful and durable response, underscoring the urgent need for innovative therapeutic strategies.
Insilico Medicine (“Insilico”), a clinical-stage generative artificial intelligence (AI)-driven biotechnology company, recently unveiled a groundbreaking study developing small molecule inhibitors targeting ENPP1 to effectively modulate the STING pathway and enhance tumor immunity. Published in Nature Communications, the study showcases Insilico's advanced generative AI platform and integrated workflow which identified and validated ENPP1 as a critical immune checkpoint among multiple solid tumors and assisted in developing a highly specific oral ENPP1 inhibitor, ISM5939.
In the field of cancer immunotherapy, the activation of the STING (Stimulator of Interferon Genes) pathway is considered an effective strategy to enhance anti-tumor immune responses. However, clinical applications of direct STING agonists face two major challenges: First, STING agonists typically have low bioavailability and require intertumoral injection, making them difficult to use for inaccessible or widely metastatic tumors. Second, STING agonists commonly induce toxic systemic inflammatory responses and T-cell apoptosis, which limits their clinical efficacy. To overcome these challenges, Insilico Medicine chose to focus on targeting ENPP1 (ectonucleotide pyrophosphatase/phosphodiesterase 1) as a breakthrough approach.
ENPP1 plays a key role in various essential physiological processes, such as cardiovascular, neurological, and immune regulation, and is highly expressed in multiple types of tumors. Research has shown that ENPP1 is closely associated with tumor metastasis, immune evasion, and poor prognosis in malignant tumors. Mechanistically, ENPP1 degrades cellular cyclic GMP-AMP (cGAMP), thereby blocking activation of the STING pathway and suppressing anti-tumor immune activity in the tumor microenvironment. Targeting ENPP1 is therefore expected to precisely modulate the STING signaling pathway within tumor tissue, restore local immune activation, and enhance anti-tumor immune responses. This provides a novel and promising strategy for cancer immunotherapy.
In this published study, the research team utilized Insilico's AI-driven target discovery, PandaOmics, alongside multi-omic patient data to screen and rank indications most likely to respond to ENPP1 inhibitors. Key cancer types found to likely be susceptible to ENNP1 inhibition include triple-negative breast cancer (TNBC), hepatocellular carcinoma (liver cancer), acute myeloid leukemia, ovarian cancer, colorectal adenocarcinoma, breast cancer, head and neck cancer, and ER-negative breast cancer.
Using single-cell sequencing data and spatial transcriptomics, it was further confirmed that elevated ENPP1 expression is associated with an immunosuppressive tumor microenvironment across tumor types, suggesting ENPP1 inhibition can remodel “immune desert”-like tumor microenvironments into more highly immune-infiltrated and inflammatory microenvironments.
Researchers then leveraged Chemistry42, Insilico's generative chemistry AI-based drug design engine to facilitate the design of novel ENPP1 inhibitors. The researchers employed the structure-based drug design approach of Chemistry42 to generate new compounds from scratch selected for features like predicted activity, synthetic accessibility, and structural novelty, efficiently obtaining hit molecules within 3 months.
The top candidate compounds were subsequently optimized through Chemistry42’s integrated features, including Alchemistry, which prioritizes compounds with lower calculated binding energy, and ADMET prediction modules. Through iterative refinement, ISM5939 emerged as a promising compound with drug-like properties, demonstrating high selectivity and potency for ENPP1 inhibition.
Preclinical data indicates that ISM5939 functions effectively in combination with multiple therapies, potentiating the effects of existing cancer treatments by modulating immune responses and enhancing therapeutic efficacy.
When combined with anti-PD-1 therapy, ISM5939 synergistically amplifies T-cell activity and boosts antitumor immunity. In combination with chemotherapy, ISM5939 increases cGAMP accumulation in the tumor microenvironment, thereby activating the STING pathway in antigen-presenting cells (APCs) and improving chemotherapy efficacy. Similarly, when used alongside PARP inhibitors, ISM5939 further enhances STING activation, driving stronger antitumor immune responses. Moreover, ISM5939 exhibits a higher safety margin compared with direct STING agonists, with no significant induction of pro-inflammatory cytokines in the peripheral blood and no triggering of effector T cell death within the tumor microenvironment.
“This is our third Nature Portfolio journal paper published this year,” said Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine. “I am pleased to see our team’s research once again recognized by a leading academic journal. The discovery and design process of ISM5939 demonstrates the potential of AI-powered drug discovery technology and workflows to overcome the challenges of traditional drug development. By targeting ENPP1, we are paving the way for safer and more effective cancer treatments.”
“In this study, Insilico Medicine fully showcased the deep integration of biology, computational science, and AI-driven drug discovery and design, providing entirely new possibilities for cancer immunotherapy,” said Feng Ren, Co-CEO and Chief Scientific Officer of Insilico Medicine. “We hope the publication of the ISM5939 discovery process in Nature Communications will inspire the industry, accelerate the discovery of next-generation innovative drugs, unleash the potential of STING-targeted therapies, and bring more new options to immunotherapy.”
Since 2024, Insilico has published five AI drug pipeline-related papers in Nature Portfolio journals. Among them, two studies published in Nature Biotechnology in March and December 2024 reported small-molecule inhibitors: Rentosertib targeting TNIK for idiopathic pulmonary fibrosis, and ISM5411 targeting PHD1/2 for inflammatory bowel disease, respectively. In addition, in January 2025, Insilico, in collaboration with the University of Toronto, published a study in Nature Biotechnology on the design of novel KRAS inhibitors using a quantum-classical hybrid model.
By integrating advanced AI and automation technologies, Insilico Medicine has demonstrated significant efficiency improvements in practical applications, setting a benchmark for AI-driven drug research and development. Compared to the typical 2.5–4 years required in traditional drug discovery, Insilico’s 22 nominated candidate drugs from 2021 to 2024 took only 12–18 months on average to progress from project initiation to nomination of preclinical candidates (PCCs), with each project requiring synthesis and testing of only about 60–200 molecules. The success rate from PCC to IND-enabling stage reached 100%.
[1] Pu, C., Cui, H., Yu, H. et al. Oral ENPP1 inhibitor designed using generative AI as next generation STING modulator for solid tumors. Nat Commun 16, 4793 (2025). https://doi.org/10.1038/s41467-025-59874-0
About Insilico Medicine
Insilico Medicine, a global clinical stage biotechnology company powered by generative AI, is connecting biology, chemistry, medicine and science research 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, central nervous system diseases, infectious diseases, autoimmune diseases, and aging-related diseases. www.insilico.com
Journal
Nature Communications