Our Research
Agentic and generative AI for drug discovery
We build AI agents and generative models that reason over molecular structures, protein targets, biological networks, and experimental constraints to propose, evaluate, and refine therapeutic candidates. Our work combines large chemical language models, graph neural networks, diffusion and flow models, reinforcement learning, multimodal foundation models, and closed-loop design for small molecules, antibiotics, antimicrobial peptides, proteins and drug combinations.
Representative work:
• MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design. ICLR 2026
• Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design. NeurIPS 2025
• GraphBAN: An Inductive Graph-Based Approach for Enhanced Prediction of Compound-Protein Interactions. Nature Communications, 2025
Agentic multimodal AI for medical imaging and clinical decision support
We develop multimodal AI agents that integrate medical images, radiomics, clinical records, phenotypes, and molecular data to support diagnosis, prognosis, risk prediction, and treatment planning. Our work emphasizes clinically useful tools, synthetic-data generation for data-scarce diseases, radiogenomics, continual learning, and human-in-the-loop decision support.
Representative work:
• RADx: Hand X-Ray Rheumatoid Arthritis Severity Assessment Tool. CVPR 2026 Demo Track
• RDFace: A Benchmark Dataset for Rare Disease Facial Image Analysis under Extreme Data Scarcity and Phenotype-Aware Synthetic Generation. CVPR 2026 Highlight
• Conditional Probabilistic Diffusion Model Driven Synthetic Radiogenomic Applications in Breast Cancer. PLOS Computational Biology, 2024
AI for single-cell, spatial, and multi-omics data
We design statistical machine learning and deep learning methods to integrate high-dimensional biomedical data across molecular, cellular, tissue, and population scales. Our models aim to identify disease mechanisms, biomarkers, cell types, disease subtypes, and microbiome-host interactions for precision medicine.
Representative work:
• A Copula-infused Graph Neural Network for Cell Type Classification in Single Cell RNA Sequencing Data. Computational and Structural Biotechnology Journal, 2026
• ST-CellSeg: Cell Segmentation for Imaging-Based Spatial Transcriptomics Using Multiscale Manifold Learning. PLOS Computational Biology, 2024
• Integrative Analysis of Taste Genetics and the Dental Plaque Microbiome in Early Childhood Caries. Cell Reports, 2025
Trustworthy and data efficient AI for medicine
We create AI methods that remain robust, interpretable, privacy-aware, and useful when biomedical data are scarce, noisy, biased, heterogeneous, or distributed across cohorts. This cross-cutting theme includes uncertainty quantification, out-of-distribution learning, batch-effect mitigation, interpretable modeling, privacy-preserving learning, and synthetic-data strategies for high-stakes biomedical applications.
Representative work:
• Out-of-Distribution Learning in Multiomics: Advancements and Challenges. Briefings in Bioinformatics, 2025
• Enhanced Interpretable Neural Network Approach for Unified Batch Effect Mitigation and Disease Classification Using Cross-Cohort Microbiome Profiles. Journal of Computational Biology, 2025
• Synthetic Data Alone is Enough? Rethinking Data Scarcity in Pediatric Rare Disease Recognition. CVPR 2026 Workshop on CV4CHL
Collaborative research
Dr. Hu has outstanding experience in collaborating with basic scientists and clinicians. He was one of the major drivers to establish and develop the first statistical facility for omics data analysis (https://tcag.ca/facilities/statisticalAnalysis.html) in Canada when he acted as the facility’s manager in The Centre for Applied Genomics at Sickkids, Toronto. In this position, he consulted for and collaborated with more than 200 national and international basic and clinician scientists.
In the past 9 years, as a health data science lead, Dr. Hu has helped other principal investigators successfully apply for six CIHR project and team grants in human/statistical genetics, microbiome, methylation, proteomics, chemogenetics and single cell analysis.
Our Funding Partners
