Cambridge, Massachusetts – September 09, 2026 -- Insilico Medicine has published data in Nature Biotechnology showing that its AI-designed idiopathic pulmonary fibrosis (IPF) candidate rentosertib reversed predicted biological age by up to six years in some patients, based on six independently developed proteomic aging clocks.
Six independent aging clocks unanimously agree on age reversal
Researchers from Harvard Medical School, Stanford University, The Broad Institute, RWTH Aachen University, Peking University and Westlake University analyzed 12-week longitudinal Olink proteomic data from 42 IPF patients treated in a Phase IIa trial. Applying six aging clock models -- ProtAge, OrganAge (chronological and mortality variants), PAC, ipfP3GPT and PAOPAC -- across 2,841 proteins, all six independently indicated reduced biological age in rentosertib-treated patients versus placebo. Peak effect occurred at Week 4 in the 30 mg BID group, with roughly three to four years of reversal and up to six years on one clock.
Lung function and biological age improvements moved independently
Forced Vital Capacity (FVC), a standard lung-function measure that also declines with age, showed a dose-dependent improvement of +98.4 mL in the 60 mg once-daily group versus a -20.3 mL decline in placebo, consistent with prior Phase IIa results published in Nature Medicine in June 2025. However, the dose driving the strongest lung-function benefit differed from the dose producing the largest age-reversal signal, indicating the drug's anti-aging activity was not solely a downstream effect of respiratory improvement. Validation against 55,319 UK Biobank profiles showed rentosertib reversed typical age-related protein-expression trajectories, with mechanistic data pointing to suppression of senescence drivers including EREG, ESM1, IGFBP4, ITGA2, MMP10, MMP13 and SPP1.
Target-to-candidate timeline ran approximately 18 months
Insilico's AI platform identified TNIK -- a target scoring highly across six aging hallmarks -- as a dual-purpose driver of both fibrosis and aging biology. Its generative chemistry platform, Chemistry42, then designed rentosertib against TNIK, moving from target identification to preclinical candidate nomination in about 18 months, with preclinical results first published in Nature Biotechnology in 2024. Rentosertib (ISM001-055) has since advanced into a Phase III trial for IPF.
Study proposes a regulatory pathway for dual-purpose aging trials
The paper outlines a stepwise framework for embedding aging and senescence biomarkers as exploratory endpoints in standard disease trials, then pursuing biomarker qualification or composite endpoints under the FDA Biomarker Qualification Program and the FDA-NIH BEST framework. The approach is designed to surface geroprotective candidates years or decades earlier than the conventional route of repurposing approved drugs such as rapamycin or metformin. All trial data were deposited with the China National Center for Bioinformation (CNCB accession OMIX008341), and the analysis pipeline was released as an open-source Python library on GitHub.
Insilico posted $106 million in first-half 2026 revenue, up 287%
Insilico reported total revenue of approximately $106 million for the first half of 2026, a 287% year-over-year increase, and its first profitable half-year since listing, with adjusted net profit exceeding $51 million. The results were driven by licensing and R&D collaborations with Eli Lilly, Servier, Takeda, SK Biopharmaceuticals, Qilu Pharmaceutical, Hygtia Therapeutics, CMS and Tenacia. Total contract value of transactions announced in 2026 reached approximately $7.3 billion, bringing cumulative collaboration value since 2021 to roughly $11 billion. The company nominated nine development candidates in the first nine months of 2026, a company record, alongside eight clinical milestones across its pipeline.
Nobel laureate Michael Levitt, commenting on the study, said the agreement among six clocks built on different features and training data -- rather than the size of the effect -- was what made the result convincing, while noting the trial cannot yet separate slower aging from improved lung tissue itself.