Recognition
Duc Nguyen Among World's Top 2% Most Cited Researchers (2024)
Prof. Duc Nguyen has been recognized in the top 2% of scientists worldwide in the latest Stanford University citation rankings (August 2024 update).
NguyenLab for Math & AI
University of Tennessee, Knoxville
The Nguyen Lab is housed in the Department of Mathematics at the University of Tennessee, Knoxville. We work at the interface of:
- Mathematics (topology, geometry, numerical analysis)
- Artificial Intelligence & Machine Learning
- Computational Chemistry, Biophysics, and Materials Science
Our long-term vision is to develop science-informed AI that enables complex-free virtual screening, efficient protein–ligand scoring, and predictive modeling across scales, from small molecules to biomolecular assemblies.
We collaborate closely with partners in academia, industry, and national laboratories, including Oak Ridge National Laboratory (ORNL) and pharmaceutical companies, including BMS and Pfizer.
Our lab's research is recognized in the top 2% of the world's most cited researchers since 2021.
Research Interests
- Topological Data Analysis (TDA): Biomolecular data representations, Drug repurpose, SARS-CoV-2 inhibitors
- Differential Geometry: Solvation modeling, Differential geometric learning of molecules, Interactive manifolds for drug design
- Graph Theory: Flexibility of protein, Algebraic graph learning for drug discovery, Manifold learning
- Machine Learning: Multiscale manifold regularization, Convolution neural network (CNN), Graph convolution neural network (GNN), Multitask learning, Transfer learning, Autoencoder, Generative network complex (GNC), Generative adversarial network (GAN), Reinforcement learning
- Data Analysis: Low-dimensional mathematical representations, Knowledge based driven data analysis
- Mathematical Models for Bioscience: Differential geometry representations, Multiscale weighted colored algebraic graphs, Topological learning, Flexibility-rigidity index (FRI) for biomolecules, Geometry based solvation modeling
- Drug Discovery: D3R Grand Challenges (pose prediction, drug screening, affinity prediction), Small Molecular Property Predictions, Protein-Protein Binding Free Energy and Protein Thermodynamic Stability Changes Upon Mutation, Drug Repurposing, Drug Generation
- Quantitative Systems Pharmacology: Develop mechanistic system biology model, Investigate potential therapeutic drug targets
- Numerical Methods for PDEs: High order interface methods, Geophysical flow, Electrostatic binding analysis
Meet the Team
Principal Investigators
Duc Nguyen
Associate Professor of Mathematics
PhD Students
Master Students
Undergraduate Students
Heldana Tesera
Undergraduate Student
Alumni
Kyle Cole
Undergraduate Student (18-19)
Jonathon Fleck
Undergraduate Student (16-19), PhD at Math, Utah (now)
Covalent Bond Interactions, Toxicity Predictions
Jason Kenny
Undergraduate Student (18-19)
Cici Mikat
Undergraduate Student (18-19)
Farjana Mukta
Lecturer of Mathematics, Kennesaw State University (Former Nguyen Lab PhD Student)
Graph Neural Networks, Binding Affinity Prediction, Mathematical Graph Theory, Deep Learning
Benjamin Philpot
Undergradaute Student (22-23)
Masud Rana
Assistant Professor of Mathematics, Kennesaw State University (former Nguyen Lab postdoc)
Graph Theory, Differential Geometry, Drug Design, Scientific Machine Learning
Tian Xao
Undergraduate Student (18)
Funding Support
Bristol-Myers Squibb
Industry collaboration supporting computational drug design research.
Pfizer
Industry partnership in AI-driven
pharmaceutical innovation.
pharmaceutical innovation.
News & Highlights
See all ↗Seminar
Duc Nguyen Leads AIcES Seminar Series
Duc Nguyen leads the AI catalyst for Engineering and Science (AIcES) seminar series, fostering interdisciplinary innovation across AI, sciences, and engineering.
Appointment
Duc Nguyen Appointed Associate Editor of JCIM
Prof. Duc Nguyen has been appointed as an Associate Editor for the Journal of Chemical Information and Modeling (JCIM).
News
Trung Nguyen Wins 2nd Place at SIAM UTK Showcase
The showcase features research presentations by graduate students. Trung Nguyen was awarded 2nd place for his presentation.
Conference
Duc Nguyen Co-organizes SIAM-SEAS 2025 Conference
Duc Nguyen serves as a co-organizer for the 2025 SIAM Southeastern Atlantic Section Annual Meeting at UTK.
Announcement
Duc Nguyen co-leads the AI: Foundations and Science-Informed Advancements CoS
Starting Jan 1, 2025, PI Duc Nguyen co-leads the Community of Scholars (CoS) for AI: Foundations and Science-Informed Advancements at UTK.
Online Tools & Software
See all ↗Software
Geometric Graph Learning for Protein–Protein Interactions (GGL-PPI) integrates geometric graph representation and machine learning to forecast mutation-induced binding free energy changes.
Software
A multiscale geometric graph-learning scoring function that uses extended atom-type features to model protein–ligand interactions and predict binding affinities with high accuracy.
Software
Algebraic surface–area–based scoring method that quantifies element-specific protein–ligand interactions for accurate binding affinity prediction and ranking.
Web Server
Online server for algebraic graph theory based protein-ligand binding scoring, ranking, docking and screening.
Web Server
Online server for differential geometry based geometric data analysis of molecular datasets.
Web Server
Online server for geometric graph theory or rigidity index (RI) based scoring function for protein ligand binding affinity prediction.
Latest Publications
When Does Additional Information Improve Accuracy of RNA Secondary Structure Prediction?
TLDR
This research investigates how auxiliary information from suboptimal RNA formations can improve secondary structure prediction accuracy using novel topological features.
Expand
A Geometric Graph-Based Deep Learning Model for Drug-Target Affinity Prediction
TLDR
Introduces DeepGGL, a deep learning model integrating geometric graph learning with attention mechanisms to achieve state-of-the-art drug-target binding affinity prediction.
Expand
Geometric Multi-color Message Passing Graph Neural Networks for Blood-brain Barrier Permeability Prediction
TLDR
Presents GMC-MPNN, a geometric multi-color message-passing graph neural network that outperforms state-of-the-art models in predicting blood-brain barrier permeability.
Expand
The algebraic extended atom-type graph-based model for precise ligand–receptor binding affinity prediction
TLDR
Introduces AGL-EAT-Score, an algebraic graph-based scoring function for ligand–receptor binding affinity prediction; shows strong benchmark performance.
Expand
Orthogonal Gated Recurrent Unit With Neumann-Cayley Transformation
TLDR
This paper proposes the Neumann-Cayley orthogonal GRU (NC-GRU), which utilizes orthogonal matrices to prevent exploding gradients and enhance long-term memory in recurrent neural networks.
Expand