OPLS-based Multiclass Classification and Data-Driven Inter-Class Relationship Discovery

Abstract

Multiclass datasets and large-scale studies are increasingly common in omics sci-ences, drug discovery, and clinical research due to advancements in analytical platforms. Efficiently handling these datasets and discerning subtle differences across multiple classes remains a significant challenge. In metabolomics, two-class OPLS-DA (Orthogonal Projection to Latent Structures Discriminant Analysis) models are widely used due to their strong discrimination capa-bilities and ability to provide interpretable information on class differences. However, these models face challenges in multiclass settings. A common solution is to transform the multiclass comparison into multiple two-class comparisons, which, while more ef-fective than a global multiclass OPLS-DA model, unfortunately results in a manual, time-consuming model-building process with complicated interpretation. Here, we introduce an extension of OPLS-DA for data-driven multiclass classifi-cation: Orthogonal Partial Least Squares-Hierarchical Discriminant Analysis (OPLS-HDA). OPLS-HDA integrates Hierarchical Cluster Analysis (HCA) with the OPLS-DA framework to create a decision tree, addressing multiclass classification challenges and providing intuitive visualization of inter-class relationships. To avoid overfitting and ensure reliable predictions, we use cross-validation during model building. Benchmark results show that OPLS-HDA performs competitively across diverse datasets compared to eight established methods. This method represents a significant advancement, offering a powerful tool to dissect complex multiclass datasets. With its versatility, interpretability, and ease of use, OPLS-HDA is an efficient approach to multiclass data analysis applicable across various fields.