Seokhyun Moon

About Me

My research focuses on developing advanced computational frameworks for understanding and predicting molecular interactions. Building on PIGNet, a physics-informed graph neural network for binding affinity estimation, I have worked on structure and binding affinity prediction for diverse biomolecular complexes. I am currently developing next-generation foundation models for biomolecular complex structure prediction. In parallel, I am interested in molecular generative models for lead optimization and de novo drug design, and more recently in phenotypic drug discovery using virtual cells, where my previous work can be effectively leveraged.

Publications

FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching

Joongwon Lee*, Seonghwan Kim*, Seokhyun Moon*, Hyunwoo Kim† and Woo Youn Kim†

Under Review

Paper

MoAgent: A Hypothesis-Driven Multi-Agent Framework for Drug Mechanism of Action Discovery

Jun Hyeong Kim*, Seokhyun Moon, Seonghwan Kim, Junhyeok Jeon, Taein Kim, Jisu Seo, Songmi Kim, and Woo Youn Kim†

NeurIPS 2025 workshop: AI4D3,FM4LS

Paper (AI4D3) | Paper (FM4LS)

Discrete Diffusion Schördinger Bridge Matching for Graph Transformation

Jun Hyeong Kim*, Seonghwan Kim*, Seokhyun Moon*, Hyeongwoo Kim*, Jeheon Woo*, and Woo Youn Kim†

ICLR 2025, NeurIPS 2024 workshop: AI for New Drug Modalities

Paper | Code

DeepBioisostere: Discovering Bioisosteres with Deep Learning for a Fine Control of Multiple Molecular Properties

Hyeongwoo Kim*, Seokhyun Moon*, Wonho Zhung, and Woo Youn Kim†

Under Review

Paper | Code

Toward Generalizable Structure-Based Deep Learning Models for Protein-Ligand Interaction Prediction: Challenges and Strategies

Seokhyun Moon*, Wonho Zhung*, and Woo Youn Kim†

WIREs Computational Molecular Science, 2024

Paper

PIGNet2: A Versatile Deep Learning-based Protein-Ligand Interaction Prediction Model for Binding Affinity Scoring and Virtual Screening

Seokhyun Moon*, Sang-Yeon Hwang, Jaechang Lim, and Woo Youn Kim†

Digital Discovery, 2024

Paper | Code

GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising

Hyeonsu Kim*, Jeheon Woo*, Seonghwan Kim*, Seokhyun Moon*, Jun Hyeong Kim*, and Woo Youn Kim†

NeurIPS, 2023

Paper | Code

PIGNet: a physics-informed deep learning model toward generalized drug-target interaction prediction

Seokhyun Moon*, Wonho Zhung*, Soojung Yang*, Jaechang Lim, and Woo Youn Kim†

Chemical Science, 2022

Paper | Code

Scaffold-based molecular design with a graph generative model

Jaechang Lim*, Sang-Yeon Hwang*, Seokhyun Moon, Seungsu Kim, and Woo Youn Kim†

Chemical Science, 2020

Paper | Code

Invited Talks

Developing a generative model of protein-ligand complexations

AI Star Fellowship Workshop (KAIST Graduate School of AI, Seoul, South Korea), Nov 2025

Symposium on AI New Drug Development Using Ultra-High Performance Supercomputing (MOGAM Institute for Biomedical Research, Seoul, South Korea), Oct 2025

Awards

President’s Award, Telecommunications Technology Association (AI-Champion) 2025

Recipient, 10th EDISON Computational Chemistry software application competition 2020

Recipient, KAIST Undergraduate Research Program participaiton prize 2020

Recipient, Qualcomm-KAIST Innovation Awards 2019