Zhongwu Lai

The paper presents a machine learning framework to classify variants in cell-free DNA as clonal hematopoiesis or tumor origin, achieving better classification rates than existing methods.

The paper evaluates the feasibility of using TMT-iBAQ to identify tumor-enriched and highly expressed cell surface antigens for cancer therapeutics.

Deep Purity (DePuty) uses convolutional neural networks to predict tumor purity from SNP-based copy number and minor allele frequency data without matched normals, outperforming existing methods with fewer samples.

The paper introduces a tiered prioritisation approach to identify high-impact gene fusions in cancer genomes by improving variant annotation, interpretation, and visualisation.