Zhaoxiang Cai

ProCanFDL uses federated deep learning to subtype cancers using proteomic data while preserving privacy, achieving performance gains over local models.

The paper introduces a deep learning model to augment cancer cell line multi-omic data, increasing the number of profiles and uncovering drug resistance mechanisms.

This paper introduces DeePathNet, a Transformer-based model that integrates cancer pathways with multi-omic data to improve drug response prediction and cancer classification.

The paper presents a pan-cancer proteomic map of 949 cell lines, revealing protein-specific biomarkers of cancer vulnerabilities and showing proteomic data's superior predictive power for drug response.