Christopher K. Wong

TRIOPS predicts TCR-MHC restriction from amino acid sequences, achieving high AUC scores and generalizing to unseen alleles and HLA genotypes.

AKLIMATE predicts cancer phenotypes by integrating multi-omic data and pathway knowledge, outperforming existing methods in tasks like microsatellite instability prediction and survival analysis.

The paper introduces LURE, a semi-supervised method to predict cancer drivers using gene expression signatures, and applies it to TCGA data to find new associations with known mutation events.