← Founder Notes
Archive

Insilicos rentosertib became the first drug with both an ai-discovered target and an ai-generated…

Yethikrishna ROriginal on Threads

insilicos rentosertib became the first drug with both an ai-discovered target and an ai-generated molecule to reach phase iii, after a phase iia study in nature biotechnology showed six aging clocks shifting younger by 2.7 to 3.5 years in 42 patients. one ai-designed molecule, two firsts, and a phase iii the industry is watching.

the honest question is whether the clocks measure aging or just its blood markers.

Context

Insilico's release of 7 July 2026 says a Phase III trial of rentosertib was initiated, a prospective, randomized, double-blind, placebo-controlled study expected to enroll 320 participants at 47 centers in China, with the annual rate of decline in forced vital capacity as the primary endpoint. It says Phase IIa showed manageable safety and, at 60 mg once daily, a mean FVC improvement of +98.4 mL at 12 weeks, and it describes the drug as potentially first-in-class, discovered and designed with Insilico's AI platform. A Nature Biotechnology paper of 7 September 2026 applies proteomic aging clocks to serum from the published 12-week Phase 2a trial and says all six clocks consistently predicted lower biological age in treated arms, while clocks alone cannot separate aging from disease effects. It reports a biological age reduction of -2.71 to -3.46 years for the 60 mg group across four chronological clocks at week 4, with no significant change in the two mortality clocks, and effects plateau between weeks 4 and 12.

How it compares

The first claim is bounded: potentially first-in-class and first clinical evaluation of the combination are Insilico's own wording, and no independent source for a first to reach Phase III was read. Phase III was initiated in July 2026, with enrollment and outcomes not reported, so this is not an approved drug. The Phase IIa trial was published in Nature Medicine in 2025, and the Nature Biotechnology paper is a post hoc aging-clock analysis of that trial's serum data, so the note conflates the two. The 2.7 to 3.5 year range applies to four clocks in one arm at week 4, not six clocks. Forty-two patients is from Insilico's release and was not checked against the paper's per-arm counts. Exploratory biomarker results are not clinical efficacy. The note's closing question matches the paper's own limit.

Related work

Watch next

  • Phase III enrollment and FVC results, and independent replication of the clock analysis.

Sources

  1. Insilico initiates Phase III trial (Insilico, 7 Jul 2026)insilico.com
  2. Proteomic aging clocks in rentosertib trial (Nature Biotechnology, 7 Sep 2026)nature.com

Provenance

The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 21:03 IST. Sources are the papers and datasets the note draws on.

View the original post
Embed this note
<iframe src="https://founder.myndlabs.tech/notes/embed/insilicos-rentosertib-became-the-first-drug-with-both-DdbxHt-DW4E" width="480" height="420" style="border:0;max-width:100%" loading="lazy" title="Insilicos rentosertib became the first drug with both an ai-discovered target and an ai-generated…"></iframe>

More notes