AI vs. Fibrosis: Hope & Breakthrough 🚀🧬

AI-DRIVEN DRUG DISCOVERY FOR IDIOPATHIC PULMONARY FIBROIS
The Insilico Medicine team is advancing to Phase III human trials for a novel drug identified through artificial intelligence, targeting idiopathic pulmonary fibrosis (IPF). This represents a significant step forward for the computational drug discovery sector, moving AI-based medicine beyond initial safety assessments into late-stage efficacy validation. IPF, characterized by severe lung tissue scarring, dramatically reduces respiratory capacity and typically results in a median survival rate of two to four years post-diagnosis.

RENTOSERTIB: A TARGETED APPROACH
The AI-identified drug, rentosertib, functions by inhibiting the TRAF2- and NCK-interacting kinase, addressing the underlying disease mechanisms when administered orally. A randomized clinical trial involving 71 patients across 22 Chinese clinical sites utilized a placebo and active treatment approach, administering 30 mg or 60 mg daily doses over a 12-week period. The 60 mg regimen demonstrated a mean forced vital capacity gain of +98.4 mL, in stark contrast to the 20.3 mL capacity loss observed in the placebo group. Adverse events were manageable, mirroring expected baseline rates across all treatment arms.

REGULATORY VALIDATION AND EARLY SUCCESS
The U.S. Food and Drug Administration (FDA) granted ‘Orphan Drug Designation’ to rentosertib in February 2023, recognizing the drug’s potential significance for patients with IPF. This designation provides several benefits, including tax credits and market exclusivity, accelerating the development process.

THE PHARMA.AI PLATFORM: A COMPUTATIONAL ECOSYSTEM
The development of rentosertib is entirely reliant on Pharma.AI, Insilico Medicine’s proprietary computational pipeline. This platform segments into distinct engines, handling specific biological and chemical engineering tasks. PandaOmics, a key component, executes the initial target discovery phase by ingesting vast biological datasets, including genomics, clinical trial outcomes, academic literature, and patent intelligence.

PANDAOMICS: CAUSAL INFERENCE AND TARGET PRIORITIZATION
PandaOmics isolates TNIK as the primary biological target, bypassing existing antifibrotic medication pathways. The system maps TNIK as a central node regulating fibrosis and inflammation via multiple signaling channels – Wnt, TGF-β, Hippo/YAP-TAZ, JNK, and NF-κB – integrating a “hallmarks-of-aging” framework to score biological targets based on their implication in aging, chronic inflammation, and extracellular matrix remodeling. Feng Ren, Co-CEO and Chief Scientific Officer of Insilico Medicine, highlighted the clinical relevance: “IPF is one of the clearest clinical examples of an age-related disease in which fibrosis, chronic inflammation, extracellular matrix remodeling, and cellular senescence intersect.”

GENERATIVE CHEMISTRY: DESIGNING THE DRUG
Rentosertib was not discovered through conventional screening; it emerged from a biology-first, ageing-informed AI workflow. Generative molecular engineering, executed by Chemistry42, departs from traditional high-throughput screening. The system applies Generative Tensorial Reinforcement Learning to build molecules that physically align with the target protein pocket, balancing structural fit against required pharmacological properties. This algorithmic process synthesized 79 molecules, with the 55th iteration advancing to preclinical testing, reducing the timeline from project initiation to preclinical candidate nomination to 18 months.

REPRODUCIBLE SYSTEMS AND VALIDATION
The 2019 publication of the company’s GENTRL methodology in Nature Biotechnology establishes reproducible systems regulating molecular generation, avoiding capital-intensive trial-and-error processes. Validating biological impact through proteomic analysis is integral, utilizing internal aging-clock frameworks within the IPF trial to capture geroscience readouts.

PROTEOMIC VALIDATION AND CLINICAL ASSESSMENT
Researchers employ UK Biobank age-associated trajectories as external comparison datasets, contextualizing treatment-responsive proteins against broad population data. Mortality-risk-related proteomic clocks – including PAC and OrganAgemortality – provide orthogonal analytical streams alongside standard clinical endpoints. SenMayo and CellAge signature analyses evaluate senescence and senescence-associated secretory phenotype biology within cellular models. Peer-reviewed research published in Aging and Disease confirmed that pharmacological TNIK inhibition produces senomorphic activity, generating observable reductions in extracellular matrix remodeling indicators.

DOCUMENTING THE PIPELINE AND VALIDATING AI CAPABILITIES
The transition of rentosertib through the clinical pipeline provides a documented, peer-reviewed data trail essential to verifying AI capabilities in life sciences. Nature Biotechnology published the complete discovery-to-clinic progression, detailing the algorithmic TNIK target prioritization, generative chemistry outputs, preclinical efficacy data, and human Phase I pharmacokinetics. The Journal of Medicinal Chemistry published the structural biology validation, detailing the discovery of the novel TNIK inhibitor chemotypes and supplying structural backing via the TNIK kinase domain co-crystal structure. Nature Medicine documented the Phase IIa safety and lung-function data, providing empirical validation of the computational predictions.

A NEW ERA IN THERAPEUTICS
Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine, commented: “Rentosertib is a defining program for Insilico because it represents the full arc of our mission: using AI not only to move faster, but to originate new biology, new chemistry, and new therapeutic opportunities.” This program began with the hypothesis that ageing biology could help identify powerful targets for major diseases.