Insilico Medicine Advances AI-Identified Drug for IPF to Phase III Trials
Insilico Medicine is making strides in the field of computational drug discovery by advancing rentosertib, an AI-identified drug, to Phase III human trials for idiopathic pulmonary fibrosis (IPF). This progression marks a significant milestone in demonstrating the potential of AI in drug development, transitioning from early safety assessments to rigorous efficacy validation.
IPF is a debilitating disease characterized by severe scarring of lung tissue, which severely impairs breathing capacity. The median survival rate for patients diagnosed with IPF is typically between two to four years. Rentosertib, identified through advanced AI algorithms, targets the TRAF2 and NCK-interacting kinase, addressing underlying disease mechanisms when administered orally.
Phase II Clinical Trial Insights
A randomized clinical trial involving 71 patients across 22 clinical sites in China assessed the efficacy of rentosertib. Participants were divided into placebo and active treatment groups, receiving either 30 mg or 60 mg daily doses over a 12-week period. Notably, patients on the 60 mg regimen exhibited an average increase in forced vital capacity of +98.4 mL, contrasting sharply with the 20.3 mL capacity loss observed in the placebo group. The safety profile was manageable, with adverse events aligning with expected baseline rates. In February 2023, the U.S. Food and Drug Administration (FDA) granted rentosertib “Orphan Drug Designation.”
Algorithmic Target Prioritization Through Multi-Omics
The development of rentosertib is based on Insilico Medicine’s proprietary Pharma.AI computing pipeline. This workflow encompasses various engines dedicated to specific biological and chemical processes. PandaOmics, the initial phase of target detection, processes extensive biological datasets, genomic information, clinical trial results, scientific literature, and patent data to construct comprehensive biological network models. Causal inference mechanisms within the algorithms reveal new disease associations.
PandaOmics identified TNIK as a primary biological target for IPF interventions, bypassing the receptor tyrosine kinase pathways targeted by existing antifibrotic drugs. The system mapped TNIK as a central node regulating fibrosis and inflammation through Wnt, TGF-β, Hippo/YAP-TAZ, JNK, and NF-κB signaling pathways. The target selection process incorporated an aging framework, evaluating biological targets based on their impact on aging mechanisms, chronic inflammation, and extracellular matrix remodeling.
Feng Ren, PhD, co-CEO, and chief scientific officer of Insilico Medicine, noted: “IPF is one of the clearest clinical examples of an age-related disease where fibrosis, chronic inflammation, extracellular matrix remodeling, and cellular senescence intersect.”
Execution of Generative Molecular Technology
Following target selection, Insilico Medicine’s Chemistry42 engine handles the generative molecule design. Unlike traditional high-throughput screening methods, Chemistry42 employs Generative Tensorial Reinforcement Learning to create molecules that align structurally and pharmacologically with the target protein. This targeted approach reduced the time from project initiation to the nomination of preclinical candidates to just 18 months.
The foundational GENTRL methodology, published in Nature Biotechnology in 2019, supports this approach, allowing for reproducible molecule production systems and minimizing the capital-intensive trial-and-error processes of standard pharmaceutical chemistry.
Validating Biological Impact Through Proteomic Analysis
Insilico Medicine integrates complex proteomic analyses to validate the predicted biological interactions of rentosertib. Internal proteomic aging clock frameworks are used to capture exploratory geroscience results as part of the IPF study.
Proteomic clocks, such as ProtAge, OrganAgechrono, ipfP3GPT, and PAOPAC, track changes in biological age resulting from intervention. Age-related trajectories from the UK Biobank serve as external comparison datasets. Mortality risk-related proteomic clocks, such as PAC and OrganAgemortality, provide additional analytical streams beyond standard clinical endpoints. The clinical teams employ SenMayo and CellAge analyses to assess senescence and senescence-associated secretory phenotypes in cellular models.
Peer-reviewed research in Aging and Disease confirmed that TNIK inhibition results in senomorphic activity, visibly reducing extracellular matrix remodeling indicators.
Documentation of the Computational Pipeline
The advancement of rentosertib through the clinical pipeline offers a documented, peer-reviewed data path essential for verifying AI capabilities in life sciences. The entire discovery-to-clinic pathway has been published in Nature Biotechnology, providing details on TNIK algorithmic target prioritization, generative chemistry outcomes, preclinical efficacy data, and Phase I human pharmacokinetics.
The Journal of Medicinal Chemistry published structural biology validations, while Nature Medicine documented Phase IIa safety and pulmonary function data, empirically validating computational predictions. Alex Zhavoronkov, PhD, founder and CEO of Insilico Medicine, emphasized: “Rentosertib epitomizes our mission to not only accelerate drug development with AI but also to create new biology, chemistry, and therapeutic possibilities.”
Implementing AI in biopharmaceuticals requires verifiable data on human outcomes. The Phase III study will subject the generative algorithms to the ultimate test of clinical effectiveness.
See also: NVIDIA BioNeMo accelerates Anthropic Claude Science
Want to learn more about AI and big data from industry leaders? Check out the AI & Big Data Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and takes place alongside other leading technology events, including the Cyber Security & Cloud Expo. Click here for more information.
AI News is operated by TechForge Media. Discover more upcoming enterprise technology events and webinars here.
Source link: Here
“`
