Early-onset colorectal cancer (EOCRC; <50 years) incidence is increasing most rapidly among Hispanic/Latino (H/L) populations. While the transforming growth factor–beta (TGF-β) pathway influences colorectal cancer (CRC) progression, its prognostic role in FOLFOX-treated EOCRC, particularly in H/L patients, is unclear. We analyzed 2,515 CRC cases (H/L = 266; NHW = 2,249) stratified by ancestry, age at onset, and FOLFOX treatment using Fisher’s exact, chi-square, and Kaplan–Meier analyses. We then applied AI-HOPE and AI-HOPE-TGFβ, conversational artificial intelligence (AI) platforms that integrate clinical, genomic, and treatment data, to perform complex, natural language–driven queries requiring multi-parameter integration. TGF-β pathway alterations occurred in 28–39% of H/L and 23–31% of NHW patients, with SMAD4 as the predominant driver. BMPR1A mutations were enriched in FOLFOX-treated EO H/L patients (5.5% vs. 1.1% EO NHW; p = 0.0272), while late-onset NHW non-FOLFOX cases had higher SMAD2/TGFBR2 mutation rates. In FOLFOX-treated EO H/L patients, TGF-β pathway alterations predicted poorer survival (p = 0.029); no survival impact was seen in other groups. SMAD4 mutations were less frequent in EO H/L than EO NHW receiving FOLFOX (2.74% vs. 13.87%; p = 0.013). TGF-β pathway alterations may serve as an ancestry- and treatment-specific biomarker of poor prognosis in FOLFOX-treated EO H/L CRC. AI-enabled integration accelerated biomarker discovery, supporting precision medicine.

The authors have declared no competing interest.

This study was funded by the National Cancer Institute, NCI, award number U2CCA252971; the City of Hope Cancer Control and Population Sciences program by the National Institutes of Health, NIH, National Cancer Institute, NCI, award number P30CA033572; and the Drug Development and Capacity Building: A UCR/CoH-CCC Partnership project by the National Institutes of Health, NIH, National Cancer Institute, NCI, award number U54 CA285116.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The source data used in this study were publicly available before the initiation of the study and can be accessed through cBioPortal for Cancer Genomics at https://www.cbioportal.org/ and the GENIE Project (AACR Project GENIE cBioPortal) at https://genie.cbioportal.org. Additional data may be provided upon reasonable request to the authors.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All data used in the present study is publicly available at https://www.cbioportal.org/ and https://genie.cbioportal.org. The datasets used in our study were aggregated/summary data, and no individual-level data were used. Additional data can be provided upon reasonable request to the authors.