Insilico AI Drug Rentosertib Shows Biological Age Reversal in Trial

An artificial intelligence-discovered lung disease drug developed by Insilico Medicine reduced biological age across six proteomic aging clocks in a mid-stage trial, according to an analysis published in Nature Biotechnology, pointing to potential broader uses for rentosertib in treating age-related biomarkers.

An experimental treatment initially engineered to tackle lung disease has shown unexpected promise in reversing biological markers of aging. Developed using artificial intelligence, the drug rentosertib was evaluated in a mid-stage clinical trial that measured shifts in biological age by examining chemical changes across the human body.

Trial Design and Patient Demographics in China

The phase 2a trial of rentosertib, identified by trial registration NCT05938920, was structured as a randomized, double-blind, placebo-controlled investigation. Conducted between 2023 and 2024 across 21 different locations in China, the study enrolled male and female patients older than 40 who carried a confirmed diagnosis of idiopathic pulmonary fibrosis and remained in stable clinical condition.

Out of 128 individuals initially screened for the study, 71 participants met the criteria and were selected to receive specific treatment regimens or a dummy pill. Out of 128 patients screened, 71 were selected to receive 30 mg rentosertib once daily (QD, N = 18), 30 mg rentosertib twice daily (BID, N = 18), 60 mg QD (N = 18) or placebo (N = 17). By the conclusion of the study protocol, 16 patients had discontinued treatment. Investigators recorded lung forced vital capacity at the start and conclusion of the 12-week trial, alongside blood collections at baseline, the second and fourth weeks after the start, and the end of the trial. A total of 43 participants consented to serum proteomic screening, 1 of whom was excluded due to a missing measurement at the end of trial, resulting in a cohort of 42 Asian people with a mean age of 67.1 years.

Evaluating Proteomic Aging Clocks at Baseline

To measure biological age shifts, researchers evaluated six published proteomic aging clocks on baseline serum samples taken from 42 participants: Argentieri 2024, Kuo 2024, Han 2026, Galkin 2025, and two variants from Goeminne 2025, one trained to predict chronological age and one trained on mortality risk.

The four chronological clocks (OrganAgechrono, ProtAge, ipfP3GPT, PAOPAC) correlated well with actual age (Spearman’s r ∈ 0.70–0.84) and, after ordinary least squares correction for systematic offset, achieved root mean square errors below 4 years. Conversely, the two mortality-based clocks (PAC, OrganAgemortality) showed weaker correlation with chronological age (r ∈ 0.16 − 0.23), consistent with their training objective and the high disease burden of our cohort, which mortality trained models are expected to capture as elevated biological age regardless of calendar age. Bland–Altman analysis confirmed that chronological clocks carried a correctable constant bias, whereas mortality clocks exhibited a proportional bias that overestimated the age of younger participants, which could not be corrected by ordinary least squares.

Rentosertib Treatment Effects and Statistical Signatures

Despite methodological differences in training objectives, all six clocks detected proteomic shifts in response to rentosertib treatment in subsequent analyses, suggesting that the drug may modulate complementary dimensions of biological aging. Across all six clocks, treatment arms showed consistent reduction in biological age relative to baseline, whereas the placebo group showed minimal change or slight increases over the 12-week period.

When researchers quantified these shifts as the change in predicted biological age from baseline (ΔBioAge) and compared each treatment arm to placebo at weeks 2, 4 and 12, yielding 54 comparisons per arm (6 clocks × 3 timepoints × 3 regimens), 21 of these 54 comparisons reached statistical significance (Q value < 0.10). These were concentrated at week 4, where 11 of 18 comparisons registered significantly lower ΔBioAge in treated participants. A permutation test with patient-level label shuffling confirmed that 21 significant comparisons far exceeded chance expectation (null mean = 0.15), and similar findings persisted when the six participants with higher-grade adverse events were removed from the analysis.

Implications for Therapeutics and Future Investigation

The findings indicate that rentosertib may modulate complementary dimensions of biological aging in human patients, moving beyond its primary indication as an artificial intelligence-discovered lung disease treatment. Insilico Medicine noted that those who were given a placebo saw little change in their biological age on those same clocks, reinforcing the specificity of the drug-induced shifts highlighted in the published data.