Insilico Medicine announced the publication of a study in Nature Biotechnology showing that its AI-discovered idiopathic pulmonary fibrosis drug candidate rentosertib produced reductions in predicted biological age across six independently developed proteomic aging clocks.
The research analyzed longitudinal serum proteomic data collected during a Phase IIa clinical trial of rentosertib in idiopathic pulmonary fibrosis, or IPF. The analysis included 42 patients and measurements covering 2,841 proteins.
Researchers applied six independently developed proteomic aging models, including ProtAge, OrganAge, PAC, ipfP3GPT and PAOPAC. Despite differences in model architecture, training data and methodologies, all six indicated a trend toward lower predicted biological age among rentosertib-treated patients compared with placebo.
The strongest signal was observed at Week 4 among participants receiving 30 mg of rentosertib twice daily. The study reported an approximately three- to four-year reduction in predicted biological age across certain measures and as much as six years according to one aging clock.
The findings remain exploratory and do not establish that rentosertib extends lifespan or reverses human aging. The study instead evaluates changes in proteomic biomarkers that have been developed to estimate biological aging.
The work is notable because rentosertib was developed from the outset using artificial intelligence to identify both its therapeutic target and the molecule itself rather than being a previously approved drug repurposed for aging research.
Insilico used its AI-powered target discovery platform to identify TNIK as a target associated with both fibrosis and aging biology. The company said TNIK scored highly across six hallmarks of aging, leading researchers to investigate it as a dual-purpose target for IPF and aging-related biological processes.
Insilico subsequently used its generative chemistry platform Chemistry42 to design rentosertib, also known as ISM001-055, as a small-molecule inhibitor targeting TNIK.
The program progressed from target identification to preclinical candidate nomination in approximately 18 months. Preclinical research on the program was published in Nature Biotechnology, followed by Phase IIa clinical results in Nature Medicine in 2025.
The Phase IIa study met its primary safety endpoint and showed a dose-dependent efficacy trend in forced vital capacity, or FVC, a standard measure of lung function.
Patients receiving 60 mg of rentosertib once daily experienced a mean FVC improvement of 98.4 mL, compared with a mean decline of 20.3 mL in the placebo group. Excluding an outlier, the placebo decline was 62.3 mL.
FVC naturally declines with age, including among otherwise healthy older adults, making it potentially relevant to the broader aging analysis. However, the dose producing the strongest improvement in lung function differed from the dose generating the strongest proteomic age-reversal signal.
Researchers said that difference suggests the observed aging-related effects may not simply be a consequence of improved pulmonary function.
The study also compared the treatment-related protein changes with 55,319 profiles from the UK Biobank. Researchers reported that rentosertib reversed a number of protein-expression patterns normally associated with aging.
Mechanistic analysis suggested that rentosertib may act as a senomorphic agent, meaning it could alter harmful signaling associated with senescent cells without necessarily eliminating the cells themselves.
The study reported reductions in several proteins associated with cellular senescence, including EREG, ESM1, IGFBP4, ITGA2, MMP10, MMP13 and SPP1. Researchers also observed effects on RTK-PI3K and RAS-ERK signaling pathways as well as antioxidant and cholesterol metabolism.
Insilico described the research as a potential framework for incorporating aging biomarkers into conventional disease-focused clinical trials.
Under that approach, drug developers could prospectively collect proteomic and other aging-related biomarkers alongside standard clinical endpoints, potentially identifying medicines with both disease-specific and broader geroprotective effects.
The researchers proposed eventually evaluating such biomarkers through programs including the FDA Biomarker Qualification Program and the FDA-NIH BEST framework.
All research data from the analysis have been deposited with the China National Center for Bioinformation under accession OMIX008341, while the underlying analytical pipeline has been made available as an open-source Python library.
Rentosertib has now advanced into Phase III clinical development in China for idiopathic pulmonary fibrosis.
IPF is a progressive lung disease characterized by scarring and irreversible deterioration of lung function. Insilico said the disease affects approximately 5 million people worldwide and carries a median survival of approximately three to four years.
Current approved therapies can slow progression but generally do not stop or reverse the disease, leaving substantial demand for new disease-modifying treatments.
The rentosertib program also represents a broader test of Insilico’s strategy of identifying targets that may simultaneously address specific diseases and biological mechanisms associated with aging.
The company said more than 40 programs in its pipeline are being developed with a similar dual-purpose approach.
Insilico has also been expanding its AI-driven drug discovery pipeline commercially. The company reported approximately $106 million of revenue during the first half of 2026, representing a 287% year-over-year increase.
It also reported adjusted net profit exceeding $51 million, marking its first profitable half-year since becoming publicly traded.
Insilico said announced transactions during 2026 had reached approximately $7.3 billion in total potential contract value, bringing cumulative contract value from major collaborations since 2021 to approximately $11 billion.
Its partners include Eli Lilly, Servier, Takeda, SK Biopharmaceuticals, Qilu Pharmaceutical, Hygtia Therapeutics, CMS and Tenacia.
On the research side, Insilico nominated nine development candidates during the first nine months of 2026 through late August and reached eight clinical milestones across internally developed and partnered programs.
The company views rentosertib as one of the clearest demonstrations to date of its AI-driven discovery model because both the target and molecule were generated using its technology and have progressed into late-stage clinical development.
KEY QUOTES:
“Six proteomic clocks from six independent groups, applied to the same 42 patients, all reported a younger biological age in the treated arms. What convinces me is not the size of the effect but the agreement, because these models share neither their features nor their training data. This trial cannot yet separate slower aging from a treated lung, and the authors say so plainly. The experiment in healthy volunteers is the one I want to see next.”
Michael Levitt, PhD, 2013 Nobel Prize Laureate in Chemistry
“In this study, we evaluated clinical trial data to compare the blood proteomic profiles of pulmonary fibrosis patients treated with Rentosertib versus placebo. Using six proteomic aging clocks including models our team published in Cell Metabolism, we observed significant reductions in predicted biological age across multiple organ-specific clocks, and further pathway analysis confirmed that Rentosertib’s biological impact extends far beyond merely reducing fibrosis.”
Ludger Goeminne, Research Fellow in Medicine at Harvard Medical School and Co-Author of the Study
“Across the board, these clocks consistently predicted a reduction in biological age within the rentosertib treatment group. This cross-model consistency demonstrates that rentosertib’s effect on aging-related proteomic signals is not a model-specific artifact, but rather a highly robust biological phenomenon.”
Professor Jing-Dong Jackie Han, Peking-Tsinghua Center for Life Sciences, Academy for Advanced Interdisciplinary Studies and Center for Quantitative Biology
