Abstract
Microbial communities within human tissues are increasingly recognized as promising biomarkers for cancer detection. However, leveraging microbiome data for multiclass cancer classification remains challenging due to its compositional structure, high dimensionality, and lack of model interpretability. In this study, we address these challenges by introducing MicroAIbiome, a machine learning-based artificial intelligence (AI) pipeline designed to classify five cancer types such as esophageal carcinoma (ESCA), head and neck squamous cell carcinoma (HNSC), stomach adenocarcinoma (STAD), colon adenocarcinoma (COAD), and rectum adenocarcinoma (READ), using genus-level microbial relative abundances. Our pipeline incorporates zero-replacement, centered log-ratio (CLR) transformation, correlation filtering, and recursive feature elimination (RFE) to enable robust learning from compositional data. Among five evaluated classifiers, XGBoost achieved the highest accuracy of 78.23%, outperforming prior work. We further enhance interpretability using SHapley Additive exPlanations (SHAP)-based feature attribution to uncover class-specific microbial signatures, such as Corynebacterium in ESCA and Bacteroides in COAD. Our results highlight the importance of compositional preprocessing and explainable AI in advancing microbiome-based cancer diagnostics.