AI-driven discovery unveils TNIK inhibition as anti-aging strategy

A groundbreaking study led by researchers at Insilico Medicine has revealed the potential of TNIK inhibition as an innovative anti-aging strategy. Using an AI-driven robotics laboratory , the team identified INS018_055 (Rentosertib) -a potent small-molecule TNIK previously developed by Insilico Medicine, which has already advanced into clinical trials for idiopathic pulmonary fibrosis (IPF)-as a highly effective senomorphic agent capable of mitigating cellular senescence. The findings were published in Aging and Disease（IF=7.843). 

Generative AI has already showcased extraordinary potential in transforming healthcare and advancing longevity research. This study exemplifies how AI can uncover dual-purpose therapeutic opportunities, addressing both disease-specific indications like IPF and broader systemic biological aging processes. Additionally, it underscores the powerful capabilities of our robotics lab in validating preclinical experiments with unprecedented efficiency, reproducibility, and unbiased analyses."

Qiuqiong Tang, PhD, biologist at Insilico Medicine and first author of the paper

Previous studies have shown that TNIK (Traf2- and Nck-interacting kinase) plays an essential role in the cellular senescence process by orchestrating key signaling pathways tightly linked to both cell senescence and fibrosis. In this recent publication, the researchers assessed the potential of Rentosertib as a senomorphic agent by employing a comprehensive approach that combined in vitro senescence models , multi-omics data analysis, and mechanistic evaluations.

Notably the study was conducted exclusively in Insilico's state-of-art, AI-driven robotics laboratory, leveraging advanced AI-agent workflow across multiple stages, including sample processing and quality control, high-throughput screening, imaging, next-generation sequencing, and AI-powered analysis. The AI-agent workflow not only enhances efficiency but also ensures consistent, reproducible results while minimizing biases commonly associated with manual handling. Furthermore, it enables the creation of a dynamic feedback loop, where experimental outcomes continuously refine AI models, thereby improving further precision of target discovery and indication prediction.

The result demonstrates that Rentosertib significantly reduces aging-related markers such as the senescence-associated secretory phenotype (SASP) and extracellular matrix remodeling in various senescence models. Mechanistically, the study reveals that TNIK inhibition alleviates TGF-β and Wnt signaling, pathways strongly implicated in senescence, fibrosis, and aging. Impressively, Rentosertib as a potential senomorphic drug showcased safe and robust senescence attenuation while preserving healthy cell viability.This study paves the way for further exploration of Rentosertib in broader indications,especially in idiopathic aging-related degenerative conditions. 

As of the paper's publication, Rentosertib is undergoing a Phase 2 clinical trial in the U.S. and has successfully completed a Phase 2a trial in China, delivering promising results in improving lung function in patients with idiopathic pulmonary fibrosis (IPF). The development of Rentosertib was enabled by Insilico's proprietary AI platform, which played a key role in identifying its therapeutic target and designing the molecule. This process was detailed in a March 2024 Nature Biotechnology paper, which highlighted the identification of TNIK as a novel therapeutic target for IPF and the subsequent design of Rentosertib.

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 22 developmental/preclinical candidates (DC/PCC) in its comprehensive portfolio of over 30 assets since 2021, received IND clearance for 10 molecules, and completed multiple human clinical trials for two of the most advanced pipelines, with positive results announced. 

By integrating the technologies of AI and automation, Insilico has demonstrated significant efficiency boost compared to traditional drug discovery methods (often requiring 2.5-4 years), as announced in the recent key timeline benchmarks for internal DC programs from 2021 to 2024: the average time to DC is 12-18 months, with 60-200 molecules synthesized and tested per program, and the success rate from DC stage to IND-enabling stage reaches 100%.