Deok-Joong Lee

Ph.D. Candidate · Artificial Intelligence

Hello. I’m Deok-Joong Lee, a Ph.D. candidate in the Department of Artificial Intelligence at Korea University.

My research focuses on geometric deep learning for protein science, particularly protein–protein interaction modeling, protein docking, and protein design. I also work on drug discovery and biomedical AI, with broader interests in optimization methods and brain imaging.

My long-term goal is to develop geometric and generative AI models that can understand and predict biomolecular interactions and design functional proteins, ultimately contributing to protein engineering and therapeutic discovery.

Research Interests

My research focuses on graph neural networks, optimization, and generative modeling across biomedical and molecular domains. In particular, I am interested in protein interaction and structure modeling.

Geometric Deep Learning for Protein Interactions
Geometric graph neural networks for protein–protein interaction modeling and binding interface prediction
Generative Modeling for Protein Structure and Design
Generative approaches for protein structure modeling, protein docking, and protein design
Optimization and Learning for Biomedical AI
Machine learning and optimization methods for drug discovery and biomedical applications

Education

Korea University · Seoul, Korea
Integrated M.S.-Ph.D., Department of Artificial Intelligence (GPA: 4.33/4.5)
Medical Artificial Intelligence Lab · Advisor: Prof. Tae-Eui Kam
Yonsei University (Mirae Campus) · Wonju, Korea
B.S., Department of Information Statistics (GPA: 4.03/4.5)

Publications

Journal Papers

Population-based Evolutionary Search for Joint Hyperparameter and Architecture Optimization in Brain-Computer Interface
Dong-Hee Shin*, Deok-Joong Lee*, Ji-Wung Han, Young-Han Son, Tae-Eui Kam (*equal contribution)
Expert Systems with Applications · 2025 [Co-first Author]
Source-driven Enhanced Semantic Style Transfer for Addressing BCI Illiteracy in Subject-independent EEG-based Motor Imagery Classification
Ji-Wung Han, Dong-Hee Shin, Chang-Hoon Ji, Deok-Joong Lee, Jun-Mo Kim, WooHyeok Choi, Ji-Hye Oh, Sanghyeon Cho, Young-Han Son, Tae-Eui Kam
Applied Soft Computing · 2025
Spectral Graph Neural Network-based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis
Deok-Joong Lee, Dong-Hee Shin, Young-Han Son, Ji-Wung Han, Ji-Hye Oh, Da-Hyun Kim, Ji-Hoon Jeong, Tae-Eui Kam
IEEE Journal of Biomedical and Health Informatics · 2024 [First Author]
Graph-based Conditional Generative Adversarial Networks for Major Depressive Disorder Diagnosis with Synthetic Functional Brain Network Generation
Ji-Hye Oh, Deok-Joong Lee, Chang-Hoon Ji, Dong-Hee Shin, Ji-Wung Han, Young-Han Son, Tae-Eui Kam
IEEE Journal of Biomedical and Health Informatics · 2023

Conference Papers

Optical Diffraction-based Convolution for Semiconductor Lithography
Young-Han Son, Dong-Hee Shin, Deok-Joong Lee, Hyun Jung Lee, Tae-Eui Kam
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2026
Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies
Dong-Hee Shin, Deok-Joong Lee, Young-Han Son, Tae-Eui Kam
AAAI Conference on Artificial Intelligence (AAAI) · 2026 [Oral Presentation]
Offline Model-based Optimization for Real-World Molecular Discovery
Dong-Hee Shin*, Young-Han Son*, Hyun Jung Lee, Deok-Joong Lee, Tae-Eui Kam (*equal contribution)
International Conference on Machine Learning (ICML) · 2025
Hybrid Local-Global GNN for Protein Binding Interface Prediction via Ensemble Learning
Deok-Joong Lee, Dong-Hee Shin, Young-Han Son, Tae-Eui Kam
International Conference on Electronics, Information, and Communication (ICEIC) · 2025 [First Author]
Designing Selective Drugs: Multi-Objective Optimization to Mitigate Off-Target Effects
Dong-Hee Shin, Young-Han Son, Deok-Joong Lee, Tae-Eui Kam
International Conference on Electronics, Information, and Communication (ICEIC) · 2025
Molecular Optimization with Mamba-Based GFlowNet
Young-Han Son, Dong-Hee Shin, Deok-Joong Lee, Tae-Eui Kam
International Conference on Electronics, Information, and Communication (ICEIC) · 2025
Dynamic Many-Objective Molecular Optimization: Unfolding Complexity with Objective Decomposition and Progressive Optimization
Dong-Hee Shin*, Young-Han Son*, Deok-Joong Lee, Ji-Wung Han, Tae-Eui Kam (*equal contribution)
International Joint Conference on Artificial Intelligence (IJCAI) · 2024

Research Projects

Protein Binding Interface Prediction with Data Augmentation
Developing geometric graph neural networks with data augmentation for protein binding interface prediction.
[Under Revision]
Protein Structure Modeling
Research on generative models for protein structure modeling, with applications to protein docking and cryo-EM.
[In Progress]

Teaching Experience

Introduction to Graph Neural Networks and Statistics
Instructor · Tech University of Korea
Introduction to Artificial Intelligence
Tutor · LG CNS
Advanced Big Data Analysis
Teaching Assistant · Korea University

Awards & Honors

Big Data-Driven Local Business Consulting Competition
KT Corporation · Domestic Award
AGI Idea Hackathon — Idea Award
Domestic Competition

Technical Skills

Python R PyTorch Linux Docker

Academic Service

Reviewer · ICLR 2025 – 2026
International Conference on Learning Representations
Reviewer · NeurIPS 2026
Conference on Neural Information Processing Systems