The Hu Lab

Bioinformatics and Statistical Genetics

My research program focuses on developing and applying artificial intelligence (AI, e.g. novel deep learning tools) and large-scale statistical techniques for integrative analysis of big multimodal health data (omics data, imaging data, administrative and electronic medical records) for precision medicine. My group also collaborates very closely with local, national and international life science scientists and clinicians on different omics projects. Current PhD/MSc students' thesis projects are in the research areas: radiogenomics, medical imaging, rare disease diagnosis using facial photos and phenotypes, drug discovery, microbiome, single cell RNA sequencing and omics data integration.

Software Development and Resources

Software Tools Developed in The Hu Lab

Web: Sparse Matrix Proﬁle DenseNet for COVID-19 Diagnosis
Description: A Two-dimensional Sparse Matrix Proﬁle DenseNet for COVID-19 Diagnosis Using Chest CT Images
Citation: Liu et al. 2020, IEEE Access

Web: DTF: Deep tensor factorization for predicting anticancer drug synergy
Description: A new algorithm integrating tensor factorization and deep learning to predict anticancer drug combinations

Citation: Sun et al. 2020, Bioinformatics

Web: An OpenMP based tool for finding LCS of DNA sequence data

Description: This repository contains three parallel implementation of the LCS algorithm in MPI, OpenMP, and hybrid MPI-OpenMP platforms.

Citation: Shikder et al. 2019, BMC Research Notes.

RecurrentCNV: A graph-based tool to recall recurrent copy number variations

Citations: Kanwar et al. 2015, International Journal of Cancer and Chi et al. 2016, Cancer Informatics.

Resources

Deep Learning

Graph Neural Network

Generative adversarial network

Data sets

Allen Brain Atlases