A High-Quality, Batch-Diverse and Small-SampleBenchmark for Probabilistic-Guided MS Classification

After data preprocessing, dimensionality reduction and feature selection, the processed data are obtained. It covers multiple sample types including cells, serum, urine, plasma, gingival crevicular fluid, fecal samples and oil.

The dataset has been split into training and test sets with labels assigned, which can be directly used to evaluate the performance of machine learning and deep learning models for classification tasks in artificial intelligence.