Yanjun Qi

EGGNet is a geometric deep learning framework for predicting molecule-protein interactions, achieving competitive performance on binding affinity and interface prediction tasks.

The paper introduces DeepVHPPI, a deep learning framework for predicting virus-host protein interactions for novel virus sequences, showing significant improvements over existing methods for SARS-CoV-2, H1N1, and Ebola.

FastSK improves the speed and scalability of gapped k-mer kernel computations for sequence analysis tasks, outperforming existing methods in both speed and accuracy.

This paper introduces ChromeGCN, a graph convolutional network that improves epigenetic state prediction by integrating DNA sequence and 3D genome data, showing significant performance gains over existing methods.

This paper introduces KDiffNet, a method for estimating sparse differential Gaussian Graphical Models that integrates extra knowledge, achieving competitive performance and scalability.

AttentiveChrome combines hierarchical Long Short-Term Memory networks with two-level attention to predict human gene expression from chromatin marks across 56 cell types while identifying important marks and genomic positions.

GaKCo improves the speed of gapped k-mer string kernels by using cumulative counting, achieving faster performance on DNA, protein, and text classification tasks.

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.