Hugo Y. K. Lam

This paper introduces HypaCADD, a hybrid classical-quantum workflow for drug design that uses quantum machine learning to predict mutation impacts, showing performance comparable to classical methods.

The paper establishes reference samples with high-coverage whole-genome sequencing to create truth sets for somatic mutation and germline variant detection using NGS technologies.

This paper introduces ecTMB, a statistical framework for estimating and classifying tumor mutational burden, identifying a new TMB subtype associated with patient survival.

NeuSomatic is a convolutional neural network for somatic mutation detection that outperforms existing methods across various sequencing platforms and tumor purities.

svclassify classifies structural variants as true or false positives using multi-technology annotations, achieving high concordance with PCR validation and MetaSV.