Abstract
Fragmentation patterns of plasma cell-free DNA (cfDNA) are promising biomarkers in cancer diagnosis. Here, we present a protocol to enrich tumor-derived cfDNA molecules through end selection. We describe steps for installing software, aligning plasma cfDNA data to the reference genome, and performing end selection on cfDNA. We then detail procedures for building cancer diagnostic models with artificial intelligence. Overall, we provide commands to align cfDNA whole-genome sequencing data starting from raw reads, then extract fragmentomic features, and finally build diagnostic models with performance evaluations. For complete information on the generation and use of this protocol, please refer to Ju et al.(1).