Insilico Medicine (HKEX: 3696) has initiated a Phase III clinical trial for rentosertib (formerly ISM001-055 / INS018_055), its first-in-class oral TNIK inhibitor for idiopathic pulmonary fibrosis, marking the first time a drug whose target was identified by AI, whose structure was generated by generative AI, and whose clinical development was guided by AI-based outcome prediction has reached late-stage pivotal testing. For investors and scientists tracking AI-driven drug discovery, the question is no longer whether AI can identify a target and design a molecule — the Phase IIa GENESIS-IPF trial answered that — but whether the clinical signal observed over 12 weeks in 71 patients will hold across 320 patients over a full year.
The rentosertib clinical trial is a prospective, randomized, double-blind, placebo-controlled, parallel-group study enrolling 320 patients with IPF across 47 centers in China. Patients will receive once-daily rentosertib over 52 weeks. The primary endpoint is the annual rate of decline in forced vital capacity (FVC), the standard registrational measure in IPF. The key secondary endpoint is time to first disease progression event. The design mirrors the structure of Boehringer Ingelheim's pivotal FIBRONEER-IPF trial, which supported US FDA approval of Boehringer's PDE4B inhibitor Jascayd (nerandomilast) in October 2025.
The confidence to advance rentosertib came from the GENESIS-IPF Phase IIa results, published in Nature Medicine in June 2025 and presented at the American Thoracic Society 2025 International Conference. In the 60 mg once-daily arm, patients demonstrated a mean FVC change of +98.4 mL at 12 weeks, compared with -20.3 mL in the placebo group. The study met its primary safety and tolerability endpoint, with treatment-emergent adverse event rates similar across all treatment arms
Mechanism and competitive differentiation
TNIK — TRAF2- and NCK-interacting kinase — is a serine/threonine kinase implicated in fibrosis-driving and inflammation-related pathways including Wnt, TGF-β, Hippo/YAP-TAZ, JNK, and NF-κB signaling. Insilico identified TNIK as a high-priority fibrosis target using its PandaOmics platform, which integrates multi-omics data from fibrotic tissues with aging-relevant target scoring. The mechanism is distinct from all three currently approved IPF agents: Boehringer's Ofev (nintedanib) inhibits receptor tyrosine kinases; Genentech's Esbriet (pirfenidone) modulates TGF-β and exerts pleiotropic antifibrotic effects; and nerandomilast inhibits PDE4B to elevate intracellular cAMP. None of these agents target the serine/threonine kinase biology of TNIK, placing rentosertib in a mechanistically differentiated position.
That differentiation matters commercially as well as scientifically. The IPF market is entering a period of expansion following nerandomilast's approval, and there is growing clinical interest in combination strategies. A mechanistically orthogonal agent with a tolerable safety profile could, in principle, be combined with an approved antifibrotic — though rentosertib's Phase III is a monotherapy program, and no combination data have been disclosed.