The mixOmics R package is designed for the integration and analysis of 'omics data, including transcriptomics, proteomics, and metabolomics. It provides multivariate methods for data exploration, dimension reduction, and visualization, enabling the identification of molecular signatures and the integration of multiple data sets. The package includes methods such as PLS-DA, sPLS-DA, DIABLO, and MINT, which are used for supervised analysis, classification, and prediction. DIABLO integrates data from different 'omics platforms, while MINT integrates data from multiple independent studies. The package supports both supervised and unsupervised analyses, with a focus on identifying biologically relevant molecular signatures. It offers various visualization tools and statistical methods for performance assessment, including ROC curves and AUC. The mixOmics package is user-friendly and efficient, suitable for handling large data sets with high-dimensional features. It has been applied in various biological studies, including proteomics and microbiome research, to identify biomarkers and validate biological hypotheses. The package includes functions for parameter tuning, cross-validation, and visualization, making it a valuable tool for integrative 'omics analysis.The mixOmics R package is designed for the integration and analysis of 'omics data, including transcriptomics, proteomics, and metabolomics. It provides multivariate methods for data exploration, dimension reduction, and visualization, enabling the identification of molecular signatures and the integration of multiple data sets. The package includes methods such as PLS-DA, sPLS-DA, DIABLO, and MINT, which are used for supervised analysis, classification, and prediction. DIABLO integrates data from different 'omics platforms, while MINT integrates data from multiple independent studies. The package supports both supervised and unsupervised analyses, with a focus on identifying biologically relevant molecular signatures. It offers various visualization tools and statistical methods for performance assessment, including ROC curves and AUC. The mixOmics package is user-friendly and efficient, suitable for handling large data sets with high-dimensional features. It has been applied in various biological studies, including proteomics and microbiome research, to identify biomarkers and validate biological hypotheses. The package includes functions for parameter tuning, cross-validation, and visualization, making it a valuable tool for integrative 'omics analysis.