Early-onset colorectal cancer cases demonstrated lower microbial richness and distinct compositional differences compared with late-onset disease using an AI-guided multi-omic integration approach.
Observational (n=2,715)
Yes
Does AI-integrated analysis identify differences in the gut microbiome between early- and late-onset colorectal cancer?
AI-integrated multi-omic analysis reveals distinct gut microbiome profiles, including lower microbial richness, in early-onset compared to late-onset colorectal cancer.
Abstract Early-onset colorectal cancer (EOCRC) is rising globally and disproportionately affects populations at increased risk. The gut microbiome has been implicated in colorectal cancer development, yet its relationship to early- versus late-onset disease within these communities remains unclear. This study aimed to characterize microbiome differences across age-defined CRC subgroups using an AI-enabled, multi-domain analytical framework.We analyzed 2,715 colorectal cancer (CRC) tumor samples from patients in our NIH Cancer Moonshot COPECC PE-CGS Network and public data repositories. Within this cohort, stool samples were collected from 23 patients diagnosed with CRC. Microbial profiling was performed using 16S rRNA sequencing and complemented by whole-exome sequencing, RNA sequencing, clinical variables, and social determinants of health (SDOH). Mutation frequencies across different populations were evaluated using the AACR Project GENIE database. Conversational artificial intelligence platforms (AI-HOPE) were used to integrate and query multi-omics and SDOH data, enabling identification of patterns associated with age at onset.EOCRC cases demonstrated lower microbial richness compared with late-onset CRC. Distinct differences in microbial composition and relative abundance were observed when stratifying by genetic ancestry, mutation frequency, gene fusions, copy number variation, clinical features, and SDOH factors. AI-guided integration further highlighted age-specific microbial profiles that aligned with multi-omic alterations.These findings reveal notable microbiome differences between early- and late-onset CRC in populations at increased risk. This preliminary work underscores the utility of artificial intelligence-supported integrative analysis and highlights the need for larger comparative studies to determine whether specific microbial signatures contribute to variations in CRC onset and outcomes. Citation Format: Sophia Manjarrez, Francisco Carranza, Brigette Waldrup, Xinran Qi, Antonio L. Cruz Gomes, David O. Garcia, Adriana Maldonado, Jennifer Karmouch, Robert Jenq, PE-CGS Network, Enrique Velazquez-Villarreal. Artificial intelligence-integrated analysis of the gut microbiome in early- and late-onset colorectal cancer among populations at increased risk using clinical, genomic, and social determinants data abstract. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 3993.
Manjarrez et al. (2026) conducted an observational in Colorectal cancer (n=2,715). AI-integrated multi-omic and SDOH analysis vs. Late-onset colorectal cancer was evaluated on Microbiome differences (microbial richness and composition). Early-onset colorectal cancer cases demonstrated lower microbial richness and distinct compositional differences compared with late-onset disease using an AI-guided multi-omic integration approach.