End-to-End Workflows for Liquid Biopsy Biotyping Analysis Using Combined MALDI MS and Machine Learning Approach

Abstract

MALDI MS analysis of liquid biopsy combined with ML enables non-invasive disease screening and monitoring. Here we present an open-source R-based workflow covering all steps from raw data preprocessing to predictive model evaluation. The pipeline is fully customizable and transparent, with validation performed on clinical plasma samples from hemato-oncological patients. This workflow enhances data reproducibility, enables a straightforward end-to-end workflow for liquid biopsy biotyping, and provides a foundation for integrating MALDI MS into routine clinical workflows.