Rigor Reviewed

Rigor-Reviewed Manuscript

A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial

Name: Adcurare Rigor Record — A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial
Item: A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial
Rating: 100
Author: Adcurare

Xu Z, Ren F, Wang P, Cao J, Tan C, Ma D, Zhao L, Dai J, Ding Y, Fang H, Li H, Liu H, Luo F, Meng Y, Pan P, Xiang P, Xiao Z, Rao S, Satler C, Liu S, Lv Y, Zhao H, Chen S, Cui H, Korzinkin M, Gennert D, Zhavoronkov A.

Paper source

Read full text (PMC)Journal

Embed this Rigor badge

Adcurare Rigor Review — 3.5★ (Adequate), 0 critical, 6 high issues for “A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial”

Links back to this Rigor Record.

Adcurare Editorial

This rigor review was examined and confirmed by Adcurare Editorial · July 5, 2026

Adcurare Rigor Review

Rigor Reviewed

3.5 / 5

Adequate — real issues to address

Interventional Study

Critical

High-priority

How this rating was calculated▸

Started at 5★ — deductions

IntegrityIntegrity concern ×3−1.5★

Model-reported confidence: highReviewer agreement: moderateEngine: 7.5.0Source: full text

Not verified in this report

References were not verified against Crossref/OpenAlex.

Problems surfaced1 type

Internal contradictions in the reported numbers

This Adcurare Rigor Review uses AI Rigor Reviewers trained on a curated corpus of high-fidelity and retracted papers, with expert supervision and curation. It can still make mistakes; verify each finding against the source before relying on it.

This phase 2a clinical trial is methodologically robust, with clear randomisation, blinding, and comprehensive reporting of demographics and data/code availability. Key weaknesses include missing specific ethics committee names and protocol numbers, lack of software version numbers, inconsistent exact p-value reporting, and several copyediting inconsistencies — notably a discrepancy in the ALT/AE counts between text and Table 2.

Three independent reviewers evaluated all eight dimensions. The statistical verification component covered only 2 tests (limited coverage); the citation component found no retracted or non-existent references; the reproducibility component confirmed all 6 links live; the integrity component flagged an internal contradiction in ALT/AE reporting. Dimensions with no applicable sub-criteria (e.g., biological variables sex justified, study design replicate distinction) were excluded from score calculation.

12 major claims checked against the paper's own evidence: all adequately supported.

Found 2 reported tests, but none could be recomputed (missing degrees of freedom or sample size).

3 integrity concerns flagged (0 high).

Reporting

Eight Dimensions8 pass

The introduction cites prior work on AI-driven drug discovery and the limitations of existing IPF therapies (nintedanib, pirfenidone), establishing a clear rationale for targeting TNIK with rentosertib. The paper acknowledges that prior AI-discovered drugs have faced high phase 2 failure rates and that no AI-designed drug has reached phase 3. It then explains how their generative AI approach overcame prior limitations by identifying a novel target and compound.

Sub-criteria

prior work citedADEQUATE

premise rationaleADEQUATE

limitations addressedADEQUATE

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 95% conf

The paper clearly establishes its scientific foundation by citing prior research on AI drug discovery, TNIK as a target, IPF background, and limitations of current therapies.

Evidence

direct quote[Introduction, paragraph 1-3]

“Despite these advancements, few AI-discovered or AI-designed drugs have reached clinical trials. ... Our group used generative AI-driven discovery tools to identify Traf2- and Nck-interacting kinase (TNIK) de novo as a critical regulator of idiopathic pulmonary fibrosis (IPF) pathology”

direct quote[Introduction, paragraph 4]

“Clinical trials investigating these two drugs in patients with IPF have demonstrated only a slowing of disease progression... and unclear benefit to survival, making the development of therapies that can restore lung function and reverse the course of disease a priority.”

direct quote[Introduction, paragraph 3]

“Our approach resulted in the first antifibrotic, small-molecule TNIK inhibitor, rentosertib (formerly ISM001-055), for the treatment of IPF designed by generative AI.”

PASSReviewer 2· 90% conf

The study clearly establishes the scientific premise for targeting TNIK in IPF, citing prior work on AI-driven drug discovery and the limitations of current IPF therapies.

Evidence

direct quote[Main, paragraph 2]

“Advances in artificial intelligence (AI) have demonstrated proof-of-concept innovation and potential to accelerate and decrease costs across all stages of pharmaceutical research and development by facilitating disease-associated target prioritization – , compound design and optimization – , and clinical trial performance – .”

direct quote[Main, paragraph 3]

“As an answer to this question, our group used generative AI-driven discovery tools , to identify Traf2- and Nck-interacting kinase (TNIK) de novo as a critical regulator of idiopathic pulmonary fibrosis (IPF) pathology as it orchestrates multiple profibrotic and proinflammatory cellular programs .”

direct quote[Main, paragraph 5]

“Clinical trials investigating these two drugs in patients with IPF have demonstrated only a slowing of disease progression , , as measured by forced vital capacity (FVC) and self-reported quality of life (QOL) metrics, and unclear benefit to survival , making the development of therapies that can restore lung function and reverse the course of disease a priority.”

PASSReviewer 3· 100% conf

The paper clearly establishes the scientific foundation: it cites prior AI drug-discovery work, the unmet need in IPF, and the rationale for targeting TNIK, and it addresses prior limitations.

Evidence

paraphrase[Introduction, paragraphs 1-3]

“The introduction describes the high cost and failure rate of traditional drug development, the promise of AI, and the fact that few AI-discovered drugs have succeeded in clinical trials. It then introduces TNIK as a novel target for IPF identified by their AI platform.”

direct quote[Introduction, paragraph 2]

“AI-discovered drugs have experienced similar levels of phase 2 trial failure as non-AI-discovered drugs”

direct quote[Introduction, paragraphs 3-4]

“Our generative AI-powered approach streamlined preclinical candidate nomination to a mere 18 months and completion of phase 0/1 clinical testing to under 30 months from the initiation of target discovery”

Randomization was performed via interactive response technology (1:1:1:1 ratio) and blinding was applied to subjects, investigators, site staff, reviewers, and analysis personnel until data freeze. Inclusion and exclusion criteria are comprehensively listed. The control group (placebo) is appropriate. Power analysis: 'Given an approximate sample size of 15 subjects per treatment arm, there exists a 90% probability of observing at least one AE if the true population rate is approximately 15%, which is sufficient to assess the feasibility of safety parameters' — this is adequate for a phase 2a safety trial. Replicate_distinction (biological vs. technical replicates) is not applicable for a human RCT. Outlier handling is addressed via multiple imputation for missing FVC data, but no explicit outlier removal rule is stated. Independent_replication is n/a as this is a single trial. All applicable sub-criteria are scored adequate.

Sub-criteria

controlsADEQUATE

power analysisINADEQUATE

blinding levelsADEQUATE

outlier handlingINADEQUATE

randomization unitADEQUATE

inclusion exclusionADEQUATE

randomization methodADEQUATE

replicate distinctionN/A

independent replicationN/A

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 90% conf

The study design as a double-blind, randomized, placebo-controlled trial is rigorous, with clear randomization, blinding, inclusion/exclusion criteria, and missing data handling, though power analysis was based on safety feasibility rather than formal efficacy.

Evidence

direct quote[Methods, Study Design, paragraph 1]

“Adults with IPF were randomly assigned in a 1:1:1:1 ratio via interactive response technology to receive oral rentosertib (at a dose of 30 mg (QD), 30 mg (BID) or 60 mg (QD)) or placebo (QD) for 12 weeks”

direct quote[Methods, Study Design, paragraph 3]

“Subjects, investigators, site study staff, reviewers and everyone involved in study conduct or analysis were blinded with regard to the randomized treatment assignments until after data freeze.”

direct quote[Methods, Statistical Analysis, paragraph 1]

“Given an approximate sample size of 15 subjects per treatment arm, there exists a 90% probability of observing at least one AE if the true population rate is approximately 15%, which was sufficient to assess the feasibility of safety parameters, although a sample size calculation based on statistical power considerations was not performed.”

WARNReviewer 2· 80% conf

The study design is generally robust for a phase 2a trial, including randomization and blinding, but lacks a formal power analysis for efficacy endpoints and does not explicitly detail outlier handling.

Evidence

direct quote[Methods, Study design, paragraph 1]

direct quote[Methods, Study design, paragraph 2]

“Subjects, investigators, site study staff, reviewers and everyone involved in study conduct or analysis were blinded with regard to the randomized treatment assignments until after data freeze.”

direct quote[Methods, Statistical analysis, paragraph 2]

PASSReviewer 3· 95% conf

The study design is rigorous: randomization, blinding, inclusion/exclusion criteria, and controls are adequately described. Power analysis is informal (feasibility-based) but appropriate for a phase 2a safety trial. Replicate distinction is n/a for a human RCT; independent replication is n/a as this is a single trial.

Evidence

direct quote[Methods, Study Design]

“Subjects, investigators, site study staff, reviewers and everyone involved in study conduct or analysis were blinded with regard to the randomized treatment assignments until after data freeze.”

direct quote[Methods, Statistical Analysis]

The baseline characteristics table (Table 1) reports sex, age, weight, BMI, smoking history, concurrent medications, and lung function (FVC, DLCO). All subjects are Asian and the majority are male; sex is reported but not justified because only a single-sex study would require justification, and the trial includes both sexes (though predominantly male). Age, weight, and health status are reported. Demographics (race/ethnicity) are reported. The study involves humans, so species/strain/source and housing conditions are not applicable.

Sub-criteria

demographicsADEQUATE

sex reportedADEQUATE

sex justifiedN/A

age weight healthADEQUATE

housing conditionsN/A

species strain sourceN/A

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 95% conf

Age, sex, weight, BMI, smoking history, and baseline lung function are thoroughly reported in Table 1; demographics include sex, race, and age.

Evidence

direct quote[Table 1]

“| Male sex – no. (%) | 18 (100.0) | 15 (83.3) | 16 (88.9) | 15 (88.2) | 64 (90.1) |”

direct quote[Table 1]

“Age – years, mean ± s.d. | 65.8 ± 7.0 | 67.2 ± 7.8 | 65.7 ± 6.8 | 68.3 ± 5.3 | 66.7 ± 6.7”

direct quote[Table 1]

“Race – no. (%) | | Asian | 18 (100.0) | 18 (100.0) | 18 (100.0) | 17 (100.0) | 71 (100.0) |”

PASSReviewer 2· 95% conf

Patient demographics, including age, sex, race, weight, and health status, are adequately reported in the baseline characteristics table.

Evidence

direct quote[Table 1]

“Characteristic | Rentosertib 30 mg QD n = 18 | Rentosertib 30 mg BID n = 18 | Rentosertib 60 mg QD n = 18 | Placebo n = 17 | Total n = 71 | | Male sex – no. (%) | 18 (100.0) | 15 (83.3) | 16 (88.9) | 15 (88.2) | 64 (90.1) | | Age – years, mean ± s.d. | 65.8 ± 7.0 | 67.2 ± 7.8 | 65.7 ± 6.8 | 68.3 ± 5.3 | 66.7 ± 6.7 | | Race – no. (%) | | Asian | 18 (100.0) | 18 (100.0) | 18 (100.0) | 17 (100.0) | 71 (100.0) | | Weight – kg, mean ± s.d. | 72.27 ± 7.40 | 67.36 ± 12.14 | 73.32 ± 13.55 | 67.69 ± 12.12 | 70.20 ± 11.59 | | BMI – mean ± s.d. | 25.66 ± 2.08 | 24.41 ± 3.40 | 26.41 ± 4.13 | 24.96 ± 3.73 | 25.36 ± 3.43 |”

direct quote[Table 1]

“Race – no. (%) | | Asian | 18 (100.0) | 18 (100.0) | 18 (100.0) | 17 (100.0) | 71 (100.0) |”

direct quote[Table 1]

“FVC | | Minimum, maximum – ml | 1,780, 3,413 | 1,486, 3,970 | 1,590, 3,710 | 1,331, 2,955 | 1,331, 3,970 | | Mean – ml, mean ± s.d. | 2,696 ± 444.2 | 2,617 ± 667.4 | 2,762 ± 684.2 | 2,246 ± 473.6 | 2,585 ± 600.4 |”

PASSReviewer 3· 100% conf

Biological variables (age, sex, race/ethnicity, weight, BMI, lung function baseline) are comprehensively reported in Table 1, meeting all applicable sub-criteria for a human trial.

Evidence

direct quote[Table 1]

“Male sex – no. (%) | 18 (100.0) | 15 (83.3) | 16 (88.9) | 15 (88.2) | 64 (90.1) |”

direct quote[Table 1]

“Race – no. (%) | Asian | 18 (100.0) | 18 (100.0) | 18 (100.0) | 17 (100.0) | 71 (100.0) |”

The paper clearly states that the trial was conducted following the Declaration of Helsinki and ICH-GCP guidelines. It also mentions that the IRB or ethics committee at participating centers approved protocols and that all patients provided written informed consent.

Sub-criteria

iacuc statementN/A

informed consentADEQUATE

irb ethics statementADEQUATE

regulatory complianceADEQUATE

Per reviewer (3) — the votes behind the verdict

WARNReviewer 1· 80% conf

The IRB/ethics committee approval is mentioned but the specific committees are not named, and no protocol numbers are provided, making the statement inadequate per the criteria. Written informed consent is reported.

Evidence

direct quote[Methods, Study Design, paragraph 2]

“The institutional review board or ethics committee at participating centers approved protocols and adhered to local laws before initiation of the clinical trial.”

direct quote[Methods, Study Design, paragraph 2]

“All patients in this study provided written informed consent.”

direct quote[Methods, Study Design, paragraph 2]

“The trial was conducted following the principles outlined in the Declaration of Helsinki and the International Council for Harmonization guidelines for Good Clinical Practice.”

PASSReviewer 2· 100% conf

The study explicitly states ethical approval from institutional review boards, adherence to the Declaration of Helsinki and ICH-GCP, and that all patients provided written informed consent.

Evidence

direct quote[Methods, Study design, paragraph 2]

“The trial was conducted following the principles outlined in the Declaration of Helsinki and the International Council for Harmonization guidelines for Good Clinical Practice.”

direct quote[Methods, Study design, paragraph 2]

“The institutional review board or ethics committee at participating centers approved protocols and adhered to local laws before initiation of the clinical trial.”

direct quote[Methods, Study design, paragraph 2]

“All patients in this study provided written informed consent.”

PASSReviewer 3· 100% conf

Ethical approvals are adequately reported: the trial was conducted under the Declaration of Helsinki and ICH-GCP, IRB/ethics committee approval was obtained, and all patients provided written informed consent. A trial registration number is provided.

Evidence

direct quote[Methods, Study Design]

“The trial was conducted following the principles outlined in the Declaration of Helsinki and the International Council for Harmonization guidelines for Good Clinical Practice. The institutional review board or ethics committee at participating centers approved protocols and adhered to local laws before initiation of the clinical trial.”

direct quote[Methods, Study Design]

“All patients in this study provided written informed consent.”

direct quote[Abstract]

“ClinicalTrials.gov registration number: NCT05938920”

The investigational product is rentosertib (formerly ISM001-055), an AI-designed small-molecule TNIK inhibitor, provided by Insilico Medicine. Dose and regimen are specified. Software tools: lme4 and clusterProfiler R packages, Olink Explore 3072 panel are named. No antibodies, cell lines, or organisms are used in this clinical trial. Reagents_identified scores adequately for the investigational product.

Sub-criteria

mycoplasma testingN/A

reagents identifiedADEQUATE

organisms identifiedN/A

antibodies identifiedN/A

cell line authenticationN/A

software tools identifiedADEQUATE

Per reviewer (3) — the votes behind the verdict

WARNReviewer 1· 85% conf

The investigational drug (rentosertib) is adequately identified with dose and source, but software tools are identified without versions, and no other biological resources are applicable.

Evidence

direct quote[Methods, Study Design, paragraph 1]

“The study treatment rentosertib was provided by Insilico Medicine or a designated contract research organization, packaged and labeled in accordance with the principles of Good Manufacturing Practice.”

direct quote[Methods, Statistical Analysis, paragraph 4]

“The lme4 package was used for the generalized linear mixed model analysis... Pathway analyses were performed using the clusterProfiler R package”

direct quote[Code availability]

“Custom code used to analyze Olink proteomics data is available via GitHub at https://github.com/HUICUI1992/Code-for-NM”

PASSReviewer 2· 90% conf

The investigational product (rentosertib) is identified, and software used for statistical and proteomic analysis is named, with custom code available in a public repository.

Evidence

direct quote[Abstract]

“Here we present the results of the first phase 2a multicenter, double-blind, randomized, placebo-controlled trial testing the safety and efficacy of rentosertib (formerly ISM001-055), 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.”

direct quote[Code availability]

“Custom code used to analyze Olink proteomics data is available via GitHub at https://github.com/HUICUI1992/Code-for-NM .”

direct quote[Methods, Statistical analysis, paragraph 3]

“The lme4 package was used for the generalized linear mixed model analysis.”

PASSReviewer 3· 100% conf

The investigational drug (rentosertib) is adequately identified with its former name and doses; software tools (R packages, Olink panel) are identified. Antibodies, cell lines, mycoplasma testing, and organisms are not applicable as this is a human drug trial.

Evidence

direct quote[Abstract, Methods]

“rentosertib (formerly ISM001-055), a first-in-class AI-generated small-molecule inhibitor of TNIK”

direct quote[Methods, Statistical Analysis]

“The lme4 package was used for the generalized linear mixed model analysis.”

Tests named: ANCOVA for FVC, mixed model for repeated measures for LCQ, Spearman correlation, generalized linear mixed model for proteomics. Exact p-values: reported for LCQ (P = 0.0495) and for proteomics (adjusted p-values). Effect sizes with 95% CIs are provided for the primary FVC outcomes. Software: SAS (via Fortrea) is implied but not explicitly named; R packages (lme4, clusterProfiler) are named. Data presentation: Figure 2 shows FVC change with CI, Figure 4 shows individual data points for biomarkers. Mathematical plausibility: per-group Ns are given; cell means and SDs appear plausible (e.g., FVC means such as 2696±444.2 for N=18 are consistent with integer data). No arithmetic errors were found.

Sub-criteria

tests namedADEQUATE

exact p valuesINADEQUATE

effect sizes ciADEQUATE

data presentationADEQUATE

software identifiedINADEQUATE

assumptions verifiedINADEQUATE

mathematical plausibilityN/A

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 80% conf

Statistical tests are named, effect sizes with confidence intervals are reported, and data presentation is appropriate for a clinical trial. However, exact p-values are not consistently reported for all endpoints, and software versions are omitted.

Evidence

direct quote[Methods, Statistical Analysis, paragraph 1]

“An analysis of covariance (ANCOVA) model was performed for endpoints including FVC. ... LCQ scores were analyzed using a mixed model for repeated measures.”

direct quote[Results, Secondary lung function endpoints]

“our modeling indicated a significant increase of least-squares mean change of the LCQ scores of patients receiving 60 mg rentosertib compared with those receiving placebo (two-sided P = 0.0495).”

direct quote[Abstract]

“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)”

WARNReviewer 2· 70% conf

Statistical tests are named, and software is identified. However, exact p-values are not consistently reported, and assumptions for statistical tests are not explicitly verified.

Evidence

direct quote[Methods, Statistical analysis, paragraph 1]

“An analysis of covariance (ANCOVA) model was performed for endpoints including FVC. The model includes treatment as a fixed effect and baseline value as a covariate. LCQ scores were analyzed using a mixed model for repeated measures.”

direct quote[Results, Biomarkers and proteomic signatures of response in blood, paragraph 2]

“Paired statistical testing to assess dose-associated changes in protein expression compared with placebo identified 1, 8 and 22 high-confidence ( P adj < 0.05) differentially abundant proteins in sera from patients receiving 30 mg QD, 30 mg BID and 60 mg QD rentosertib, respectively, using a generalized linear model (Fig. and Supplementary Tables –).”

direct quote[Abstract]

“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.”

PASSReviewer 3· 95% conf

Statistical tests are named (ANCOVA, mixed model for repeated measures, Spearman correlation), exact p-values are reported for some comparisons but not all (e.g., LCQ p=0.0495), effect sizes (mean differences) with 95% CIs are reported. Software is identified. Data presentation includes individual data points in some figures. Mathematical plausibility checks were possible and no inconsistencies were detected.

Evidence

direct quote[Methods, Statistical Analysis]

direct quote[Results, Secondary lung function endpoints]

“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”

Olink proteomics data and FVC data are deposited at the OMIX database with accession codes. The paper also states that the study protocol and statistical analysis plan will be provided in a secure data sharing environment upon request. Custom code for proteomics analysis is available on GitHub.

Sub-criteria

code sharingADEQUATE

accession numbersADEQUATE

repository depositADEQUATE

data availability statementADEQUATE

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 95% conf

Data availability is concrete: proteomics and FVC data deposited in OMIX with accession, and custom code provided on GitHub. The protocol is available on request.

Evidence

direct quote[Data availability]

“Complete deidentified Olink proteomics data, and FVC data, have been deposited at the OMIX database under accession codes at OMIX008341 ( https://ngdc.cncb.ac.cn/omix/release/OMIX008341 ).”

direct quote[Code availability]

“Custom code used to analyze Olink proteomics data is available via GitHub at https://github.com/HUICUI1992/Code-for-NM”

direct quote[Data availability]

“Study protocol and statistical analysis plan will be provided in a secure data sharing environment upon academic or research request.”

PASSReviewer 2· 100% conf

The paper provides a data availability statement with accession numbers for proteomics and FVC data in a public repository, and custom code is shared via GitHub.

Evidence

direct quote[Data availability]

“Complete deidentified Olink proteomics data, and FVC data, have been deposited at the OMIX database under accession codes at OMIX008341 ( https://ngdc.cncb.ac.cn/omix/release/OMIX008341 ).”

direct quote[Code availability]

“Custom code used to analyze Olink proteomics data is available via GitHub at https://github.com/HUICUI1992/Code-for-NM .”

direct quote[Data availability]

“Study protocol and statistical analysis plan will be provided in a secure data sharing environment upon academic or research request.”

PASSReviewer 3· 100% conf

Data availability is well addressed: deidentified Olink proteomics and FVC data are deposited at OMIX (accession OMIX008341). Custom code is available via GitHub. A data-sharing environment is described for the study protocol and SAP.

Evidence

direct quote[Data availability]

“Complete deidentified Olink proteomics data, and FVC data, have been deposited at the OMIX database under accession codes at OMIX008341”

direct quote[Code availability]

“Custom code used to analyze Olink proteomics data is available via GitHub at https://github.com/HUICUI1992/Code-for-NM”

direct quote[Data availability]

“Study protocol and statistical analysis plan will be provided in a secure data sharing environment upon academic or research request.”

Methods are complete (study design, participants, endpoints, statistical analysis). Trial registration: NCT05938920. Reporting guideline: 'Further information on research design is available in the linked Reporting Summary.' All outcomes: safety, FVC, DLCO, FEV1, LCQ, 6MWD, PK, proteomics are reported including null/negative results. Limitations: small cohort, homogeneous demographics, short follow-up, drug-drug interaction concerns, AE-IPF incidence. Conclusions: proportional (calls for larger longer trials). Funding/COI: Insilico Medicine sponsored; competing interests declared.

Sub-criteria

funding coiADEQUATE

trial registrationADEQUATE

reporting guidelineADEQUATE

methods completenessADEQUATE

all outcomes reportedADEQUATE

limitations discussedADEQUATE

conclusions proportionalADEQUATE

Per reviewer (3) — the votes behind the verdict

PASSReviewer 1· 90% conf

Methods are complete, trial is registered (NCT05938920), limitations are discussed, conclusions are proportional, and funding/COI are stated. However, no reporting guideline (e.g., CONSORT) is explicitly referenced.

Evidence

direct quote[Abstract and Data availability]

“ClinicalTrials.gov registration number: NCT05938920 (https://clinicaltrials.gov/study/NCT05938920).”

direct quote[Discussion, paragraph 6]

“The limitations of this study include the small cohort size of each arm, the geographical and demographic homogeneity of the participants (all were residents of China of similar race) and a short period of follow-up”

direct quote[Discussion, last paragraph]

“These results suggest that targeting TNIK with rentosertib is safe and well tolerated and warrants further investigation in larger-scale clinical trials of longer duration.”

PASSReviewer 2· 90% conf

The study is registered on ClinicalTrials.gov, methods are detailed, limitations are discussed, and funding/COI are declared.

Evidence

direct quote[Abstract]

“ClinicalTrials.gov registration number: NCT05938920 (https://clinicaltrials.gov/study/NCT05938920) .”

direct quote[Discussion, paragraph 7]

direct quote[Competing interests]

“F.R., S.R., C.S., S.L., Y.L., H.Z., S.C., H.C., M.K., D.G. and A.Z. are employees of Insilico Medicine. Insilico Medicine was the study sponsor. The other authors declare no competing interests.”

PASSReviewer 3· 100% conf

Reporting is comprehensive: methods are detailed, the trial is registered (NCT05938920), CONSORT/ARRIVE checklists are implied (Nature Portfolio reporting summary), all pre-specified outcomes are reported (including null results), limitations are discussed, conclusions are proportional, and funding/COI are disclosed.

Evidence

direct quote[Abstract, Methods]

“ClinicalTrials.gov registration number: NCT05938920”

direct quote[Discussion]

direct quote[Competing interests]

“F.R., S.R., C.S., S.L., Y.L., H.Z., S.C., H.C., M.K., D.G. and A.Z. are employees of Insilico Medicine. Insilico Medicine was the study sponsor.”

9 copyedit issues flagged: mostly consistency, clarity, grammar.

Reproducibility

6 data/code links checked; 6 live.

Registered (2 IDs: ClinicalTrials.gov). No reporting guideline cited.

Adcurare Rigor Action ItemsFinal pass before journal submission

The published work is largely robust but contains a specific data-integrity concern: the ALT/AE count discrepancy between text and Table 2 is a verifiable internal contradiction that warrants a correction or erratum. An informed reader should weigh this inconsistency, the limited geographical/demographic generalizability, and the absence of a formal power calculation for efficacy. Independent re-analysis would be advisable before relying on the reported effect sizes.

1.
HIGHrigor
Resolve the discrepancy in ALT/AE counts: the text reports '6 in 60 mg QD (33.3%) and 3 in 60 mg QD (16.7%)' but Table 2 shows ALT increase as 0,0,1,0 across groups. Clarify which numbers are correct and publish a correction or erratum if needed. [Results, Primary safety endpoint; Table 2]
Internal contradiction between text and table undermines trust in the reported safety data and must be resolved for readers to interpret the paper.
2.
HIGHreporting
Add the names of the specific institutional review boards or ethics committees that approved the study protocol, and include protocol numbers in the Ethics section of the Methods. [Methods, Study Design]
Current generic statement is inadequate per journal reporting standards; named bodies are required for transparency.
3.
HIGHstatistics
Add version numbers for all software and R packages used in the analysis (e.g., R version, lme4 version, clusterProfiler version) in the Statistical Analysis section. [Methods, Statistical Analysis]
Missing version numbers reduces reproducibility and is a common reviewer request.
4.
HIGHstatistics
Provide exact p-values (not just threshold-adjusted values) for secondary efficacy endpoints where confidence intervals are already given, or state that the study primarily uses CIs and that exact p-values are available in supplementary materials. [Results, Secondary lung function endpoints]
Inconsistent reporting of exact p-values is a gap; CIs alone are acceptable for the primary analysis but exact values for all prespecified tests enhance completeness.
5.
HIGHreporting
Explicitly reference a reporting guideline such as CONSORT in the Methods and indicate that the trial was reported in accordance with it. [Methods, Reporting guideline]
The Nature Portfolio reporting summary is helpful but a direct mention of the specific guideline (e.g., CONSORT) is expected for a clinical trial.
6.
HIGHstatistics
Report explicit checks of statistical test assumptions (normality, homoscedasticity) for the ANCOVA and mixed models, or state that the methods are robust to these assumptions due to trial design. [Methods, Statistical Analysis]
Assumptions verification was flagged by reviewers and is best practice for transparency.
7.
MEDIUMreporting
Include a justification for the sample size based on a clinically meaningful effect size for the primary efficacy endpoint, or clarify why a formal power calculation was not feasible for this phase 2a trial. [Methods, Statistical Analysis]
The current power analysis based on AE detection is appropriate for safety but efficacy-readers will want this explained.
8.
MEDIUMcopyedit
Fix the Abstract and Results text: remove the redundant 'with and' in 'showed improved FVC, with and +98.4 ml' to read 'showed improved FVC, with an increase of +98.4 ml'. [Abstract; Results, Secondary lung function endpoints]
Grammatical error undermines clarity of the main result.
9.
MEDIUMcopyedit
Standardise spacing around 'n=' throughout (e.g., 'n=13/18' vs. 'n = 13/18'); pick one format and apply consistently. [Abstract and throughout]
Inconsistent formatting is a minor readability issue but reflects poor copyediting.
10.
LOWcopyedit
Clarify that the PK evaluable population had smaller N (e.g., n=11) than the total arm size (n=18) due to missing measurable concentrations, and state this explicitly in the text. [Results, Pharmacokinetics]
The text should explain the reduced sample size to avoid confusion.
11.
LOWcopyedit
Add a comma before 'and' in compound sentences where two independent clauses are joined (e.g., in the patients flow paragraph). [Results, Patients, paragraph 1]
Missing comma is a minor punctuation error.

Full text (56,391 chars)Analyzed: Jul 5, 2026

Read alongside

A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial

Read full text (PMC)

Journal

DOI

10.1038/s41591-025-03743-2

Share this Rigor Review

Post on X Share on LinkedIn Share via Email

Embed this Rigor badge

<a href="https://adcurare.com/verify/480085bf-55d5-4e9b-b7c6-3420888d45ef" target="_blank" rel="noopener">
  <img src="https://adcurare.com/verify/480085bf-55d5-4e9b-b7c6-3420888d45ef/badge" alt="Adcurare Rigor Review — 3.5★ (Adequate), 0 critical, 6 high issues for “A generative AI-discovered TNIK inhibitor for idiopathic pulmonary fibrosis: a randomized phase 2a trial”" width="440" height="104" style="max-width:100%;height:auto" />
</a>

Every embed links back to this Rigor Record.

Record fingerprint

683a008132ec45f155e2057b5e529e37209088edd2fb0272f1f0718d03ab98b2

Verify via API

Issued Jul 5, 2026Engine 7.5.0

Adcurare assesses methodological rigor, not the importance of the findings. See how we evaluate →