AI system
- System
-
Insilico Medicine generative-AI drug discovery platform (target discovery and generative chemistry) that produced rentosertib (ISM001-055)
- Model
-
Not assessed
- Release
-
Exact release not established.
- Application developer
-
Insilico Medicine - Role
-
The tools identified a drug target and designed a candidate molecule.
- Configuration
-
PandaOmics supported target discovery. Chemistry42 supported molecular design within Insilico Medicine’s Pharma.AI platform.
- Inputs and outputs
-
Not assessed
- Autonomy
-
Not assessed
- Workflow
-
Generative-AI target identification (TNIK) and molecule design by the sponsor. Sponsor-run 12-week, double-blind phase 2a trial at Chinese centers with safety as the primary endpoint.
- Human oversight
-
Not assessed
- Relation to AI
-
The AI role is upstream: generative-AI tools identified TNIK as a target and designed the molecule. Any clinical effect is pharmacological. The trial was not powered for efficacy and FVC was not the primary endpoint. An independent network meta-analysis ranks rentosertib favorably on FVC decline but reports a non-significant trend toward more serious adverse events.
- AI contribution
-
The AI role is upstream: generative-AI tools identified TNIK as a target and designed the molecule. Any clinical effect is pharmacological. The trial was not powered for efficacy and FVC was not the primary endpoint. An independent network meta-analysis ranks rentosertib favorably on FVC decline but reports a non-significant trend toward more serious adverse events.
Benefits
- Outcome identifiers
-
Not assessed
- Benefit
-
mean forced vital capacity change of +98.4 mL versus -20.3 mL on placebo over 12 weeks
- Category
-
Improved Physical Health
- Status
-
Not assessed
- Beneficiary groups
-
People. Society.
- Beneficiaries
-
Not assessed
- Reach
-
Not assessed
- Distribution and access
-
Not assessed
- Duration
-
Not assessed
- Expected?
-
Yes
- Costs and harms
-
Not assessed
Measurement
- Studies
-
Not assessed
- Study design
-
Not assessed
- Measurement
-
Not assessed
- Setting and sample
-
Not assessed
- Measures
-
mean forced vital capacity change of +98.4 mL versus -20.3 mL on placebo over 12 weeks
- Comparison
-
placebo
- Results
-
Reference: −20.3 ml (95% confidence interval −116.1 to 75.6) for the placebo group. Result: +98.4 ml (95% confidence interval 10.9 to 185.9) for patients in the 60 mg rentosertib QD group.
- Additional value from AI
-
Not assessed
- Limitations
-
Not assessed
- Denominators
-
Not assessed
- Materials for replication
-
Not assessed
Money
- Kind of value
-
Not assessed
- Amount
-
Not assessed
- Currency and prices
-
Not assessed
- Period and unit
-
Not assessed
- Realization
-
Not assessed
- Recipients and payers
-
Not assessed
- Gross or net
-
Not assessed
- Included costs
-
Not assessed
- Comparison
-
Not assessed
- Method
-
Not assessed
- Return and payback
-
Not assessed
People and places
- Participants
-
Developer:
Insilico Medicine. Operator: Insilico Medicine (trial sponsor) with 21 clinical centers in China. - Jurisdictions
-
Developer:
United States. Operator: United States. - Ownership and control
-
Not assessed
- Dependencies
-
Not assessed
- Cross-border connections
-
Not assessed
- Geopolitical implications
-
Not assessed
Follow-up
- Conditions for replication
-
The FVC signal must be confirmed in a larger, longer, geographically diverse phase 3 trial. Hepatic adverse events and the serious-adverse-event trend must remain acceptable.
- Replication attempts
-
Not assessed
- Later findings
-
7 July 2026. Insilico announced a 320-patient, 47-center, 52-week phase III trial of rentosertib in China on 7 July 2026, moving the drug past the 71-patient phase 2a stage.
- Availability
-
Not assessed
- Institutional decision
-
Not assessed
- Grounds
-
Not assessed
- Action and result
-
Not assessed
- Success criterion
-
Not assessed
Evidence
- Source numbers
-
AIBD-0006-source-0001–0007
- Citations
-
Numbered references below.
- Language
-
Not assessed
- Source relationships
-
Insilico sponsored the trial and supplied the ClinicalTrials.gov entry and results. The registry is not an independent regulator’s finding. The paper discloses the company’s role and employee authors. [1] [2]
- Original evidence
-
Insilico sponsored the trial and supplied the ClinicalTrials.gov entry and results. The registry is not an independent regulator’s finding. The paper discloses the company’s role and employee authors. [1] [2]
- Access and versions
-
Not assessed
- Supported findings
-
Not assessed
- Evidence links
-
Not assessed
- Evidence strength
-
Not assessed
- Missing evidence
-
Not assessed
Grades
- Assessed benefits
-
People. Society.
- Depth
-
Not assessed
- Reasons
-
People: The FVC improvement is a cohort mean from a 71-patient, 12-week, sponsor-run phase 2a trial with safety as the primary endpoint. Society: Any wider benefit depends on confirmation in larger, longer trials, which the authors themselves say are warranted.
- Observed or intended
-
Not assessed
- Rubric
-
Not assessed
- Assessor and date
-
Not assessed
- Alternative assessments
-
Not assessed
- Fill
-
Independently studied
Entry details
- Kind
-
Not assessed
- Related entries
-
Not assessed
- Field
-
Pharmaceutical R&D / respiratory medicine. Idiopathic pulmonary fibrosis.
- Purpose
-
Rentosertib was designed as an antifibrotic treatment for idiopathic pulmonary fibrosis. The trial tested the safety and preliminary efficacy of exactly that intended benefit.
- Dates
-
Date basis unassessed: 2024 (precision unassessed). Updated: 25 October 2026.
- Stage
-
Not assessed
- Version
-
SHA-256: 4feab4514c12…
References
- Other identifiers
-
Not assessed
- Category mappings
-
Not assessed
- Brief
-
Not assessed
- Revisions
-
7 revisions. Latest: 25 October 2026.
Sources
-
Peer-reviewed study Developer
Xu Z et al. (2025). A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial. Nature Medicine 31:2602–2610. doi:10.1038/s41591-025-03743-2. Insilico Medicine sponsored the trial; eleven authors were employees, and sponsor-employed authors participated in trial design, collection, analysis, and interpretation.
Establishes sponsorship and employee involvement in the trial. Competing interests and Author contributions.
Original sponsor-funded study.
We observed increased forced vital capacity at the highest dosage with a mean change of +98.4 ml (95% confidence interval 10.9 to 185.9) for patients in the 60 mg rentosertib QD group, compared with −20.3 ml (95% confidence interval −116.1 to 75.6) for the placebo group.
-
Registry label Developer
Sponsor-supplied registration and results hosted by the U.S. National Library of Medicine. Identifies the sponsor/responsible party and the posted outcomes. protocolSection.sponsorCollaboratorsModule; resultsSection.outcomeMeasuresModule; statusModule.
Sponsor-supplied registration and results hosted by the U.S. National Library of Medicine.
Percentage of Participants Who Had at Least 1 Treatment-emergent Adverse Event (TEAE)
-
Peer-reviewed study Independent author
Xu J, Liu X, Liang X, Cai X, Qian W (2026). Comparative efficacy and safety of monotherapy and combination pharmacotherapies for idiopathic pulmonary fibrosis: a network meta-analysis of randomized controlled trials. BMC Pulmonary Medicine.
Rentosertib exhibited a non-significant trend toward a higher risk of SAEs compared with placebo (OR = 1.42, 95% CI: 0.72–2.77).
-
Peer-reviewed study Independent author
Khairil L, Benny KHS, Jerry J, Khatib FM, Che Ramli MD, Kumar S (2026). AI in Drug Discovery: Clinical Failures, Regulatory Reality, and the Validation Crisis Behind the Hype. Pharmaceuticals.
AI-discovered TNIK inhibitor showed dose-dependent FVC improvement (~trend up to ~100 mL) with acceptable safety.
-
Peer-reviewed study Independent author
Magrì T, Richeldi L (2026). Contemporary Concise Review 2025: Interstitial Lung Disease. Respirology.
Rentosertib, a first-in-class AI-generated small-molecule inhibitor of TNIK, a first-in-class target in idiopathic pulmonary fibrosis (IPF) discovered using generative AI.
-
News report Independent author
Hornick I (2025). Q&A: AI-established drug 'breakthrough in the treatment of IPF'. Healio. (Interviewees: Zuojun Xu, Peking Union Medical College; Alex Zhavoronkov, Insilico CEO.)
The current phase 2a clinical results are encouraging, but they are based on a small sample size, and we look forward to seeing how it performs in phase 3 clinical trials.
-
Press release Developer
Insilico Medicine. Insilico Initiates Phase III Clinical Trial for Rentosertib, Its AI-Empowered TNIK Inhibitor for Idiopathic Pulmonary Fibrosis. 7 July 2026.