Wilson Wen Bin Goh

The paper identifies optimal workflow combinations for proteomics differential expression analysis using frequent pattern mining and ensemble inference, improving accuracy across multiple quantification platforms.

This paper demonstrates that conventional ML can achieve high accuracy in virtual screening with proper data and representation, outperforming deep learning methods.

This paper investigates how batch-effect associated missing values (BEAMs) impact missing value imputation performance and highlights the need for improved strategies.

The paper introduces PROSE, a method to recover missing proteins and associate them with phenotypes using proteomic data from the Cancer Cell Line Encyclopedia.