Multi‑Modal Data Integration
Predict Alzheimer’s disease onset and progression by combining neuroimaging, omics, and clinical features with deep learning algorithms.
Open project →Research Overview
Our group develops robust machine learning and statistical methods to connect multi‑modal biomedical data (omics, imaging) with clinical outcomes. Current directions include: disease trajectory modeling, multi‑omics integration, foundation models for biomedical systems, and trustworthy AI for healthcare.
- Deep Learning
- AI Surrogate
- Systems Biology
- Multi-Modal Data
Featured Projects
Self-Learning Tutorials →Brain Neural Operator
Design brain neural operators to model tau transport across brain and forecast tau spatio-temporal dynamics under different seeding conditions and biophysical parameters.
Explore the Tool →AI Surrogate for Systems Biology
We build AI-based surrogate models to accelerate complex systems biology simulations. These surrogates reduce computational cost while maintaining predictive accuracy for pathway and regulatory network analysis.
MAMBA Brain Fingerprinting
Develop MAMBAxBrain framework to integrate Mamba with functional connectivity analysis for multi-task fMRI modeling, including brain fingerprinting, cognitive decoding, reaction-time prediction, and schizophrenia diagnosis.
Research Activities
Highlights from our students’ research, presentations, and summer workshops.
Student Presentations
Summer Workshops Organizer
Teaching
-
CSC 111 Introduction to Computer Science (Click to View Undergraduate Course Projects)
Explore interactive games developed by undergraduate student
- CSC 201 Data Structure and Algorithms
- CSC 387/687 Computational Systems Biology
- CSC 790 Advanced Topics: AI for Health
- CSC 790 Advanced Topics: Science-Guided Machine Learning
Selected Publications
- Rao, H., Zhang, J.Z., Gu, Y., Liu, Z., Yu, G., Su, J., Cao, Y., Fan, Y, Chen, M.. (2026). A Regime-Aware Trajectory Prediction Framework for 1000+ Systems Biology Models. International Conference of Machine Learning (ICML), 2026 (Accepted).
- Rahman M., Wang, G., Zhou, K., Chen, M., Fan, Y. (2025). Catastrophic Forgetting in KANs. Proceedings of AAAI Conference on Artificial Intelligence.
- Chen, C., Xu, E., Yang, D., Yan, C., Wei, T., Chen, H., Wei, Y., & Chen, M. (2025). Chemical environment adaptive learning for optical band gap prediction of doped graphitic carbon nitride nanosheets. Neural Computing and Applications.
- Xu, C., Xu, E., Xiao, Y., Yang, D., Wu, G., & Chen, M. (2025). A multiscale model to explain the spatiotemporal progression of amyloid beta and tau pathology in Alzheimer's disease. International Journal of Biological Macromolecules.
- Rao, H., Gu, Y., Zhang, J.Z., Yu, G., Cao, Y., & Chen, M. (2025). Hierarchical Gradient-Based Genetic Sampling for Accurate Prediction of Biological Oscillations. Proceedings of AAAI Conference on Artificial Intelligence.
- Liu, S., Chen, M., Cao, X., Sheng, Z., Sun, J., Zhan, J., Wang, S., Wu, G., & Yang, D. (2025). A Joint Multi-Graph Learning Framework for Dynamic Functional Connectivity Network Estimation Across Multiple Time Scales. IEEE ISBI 2025.
- Yang, D., Shen, H., Chen, M., Wang, S., Chen, J., Cai, H., Chen, X., Wu, G., & Zhu, W. (2024). A novel spatio-temporal hub identification in brain networks by learning dynamic graph embedding on Grassmannian manifolds. IEEE Transactions on Medical Imaging.
- Zhu, W., Du, Z., Xu, Z., Yang, D., Chen, M., & Song, Q. (2024). SCRN: Single-cell Gene Regulatory Network Identification in Alzheimer’s Disease. IEEE/ACM Transactions on Computational Biology and Bioinformatics.
- Yang, D., Shen, H., Chen, M., Xue, Y., Wang, S., Wu, G., & Zhu, W. (2023). Spatiotemporal Hub Identification in Brain Network by Learning Dynamic Graph Embedding on Grassmannian Manifold. MICCAI (Medical Image Computing and Computer-Assisted Intervention).
- Chen, M., Xu, C., Xu, Z., He, W., Zhang, H., Su, J., & Song, Q. (2022). Uncovering the dynamic effects of DEX treatment on lung cancer by integrating bioinformatic inference and multiscale modeling of scRNA-seq and proteomics data. Computers in Biology and Medicine.
- Xu, C., Hollis, H., Dai, M., Yao, X., Watson, L.T., Cao, Y., & Chen, M. (2022). Modeling the temporal dynamics of master regulators and CtrA proteolysis in Caulobacter crescentus cell cycle. PLoS Computational Biology.
- Chen, M., Ahmadian, M., Watson, L.T., & Cao, Y. (2020). Finding acceptable parameter regions of stochastic Hill functions for multisite phosphorylation mechanism. Journal of Chemical Physics.
Team
Current Group Members
Former Students
Yang Xiao, 2025 (Computer Science, University of Pennsylvania)
Johnson Wang, 2024 (Computational Biology, Harvard University)
Ruiwen Yang, 2024 (Data Science, University of Pennsylvania)
Selina Zhang, 2023 (Computer Science, Harvard University)
Ziang Xu, 2023 (Computer Science, Columbia University)
Zhanyang Sun, 2023 (Data Science, University of Southern California)
Enze Xu, 2023 (Computer Science, William & Mary College)
Michelle Dai, 2022 (Computational Biology, Harvard University)
Patrick Fan, 2022 (Computational Finance, Carnegie Mellon University)
Laurent Zhang, 2022 (Data Science, New York University)
Bess Morrell, 2022 (Independent Study)
Hao Lin, 2022 (Summer research, Duke University)
David Ding, 2022 (Computer Science, Rice University)
Henry Hollis, 2021 (Biomedical Engineering, Drexel University)
Alex Wei, 2020 (Computational Biology, Harvard University)