Zhijie He

This paper benchmarks sequence-function deep learning models using ATAC-seq data, showing that different models and interpretability methods are better suited to specific tasks.

MetalPrognosis predicts disease-associated mutations in metal-binding sites using a biological language model and convolutional neural network, outperforming existing methods.

MERITS provides a comprehensive database of PE/PPE proteins from Mycobacterium, offering structural and functional information to aid in vaccine and diagnostic development.