이전 사이트 이동

This project aims to improve early lung cancer detection using a liquid biopsy approach combined with whole genome sequencing of cell-free DNA (cfDNA). By integrating fragmentomic and genomic features of cfDNA, the study develops a deep learning-based classifier capable of identifying lung cancer. Data from multi-institutional studies were used to train and validate the model, ensuring broad applicability. The classifier leverages unique cfDNA characteristics such as fragment end motif by size (FEMS) and coverage (COV) to enhance detection capabilities. This research highlights the potential of cfDNA-based screening methods to complement or replace traditional lung cancer detection approaches, offering a promising non-invasive solution for early diagnosis.