Dongmin (Eugene) Bang

Room 541, Bldg. 301

Seoul National University

1 Gwanak-ro, Gwanak-gu

Seoul 08826, Republic of Korea

With a dual background in pharmacy and computational biology, I focus on integrating pharmacological insight with machine learning to tackle a core challenge in drug discovery and precision medicine: extracting actionable knowledge from complex, high-dimensional, and often sparse biomedical data.

My research centers on developing knowledge-aware computational frameworks—including patient-specific gene regulatory modeling, graph-based learning, and multi-modal molecular representation—to improve therapeutic prediction, compound prioritization, and drug-likeness evaluation. These efforts prioritize model interpretability, translational generalizability, and the principled incorporation of domain knowledge into data-driven systems.

You can see my academic CV attached here.

news

Jun 29, 2025	🚀 Redefining Drug-Likeness with AI: ICML & ISMB Presentations Coming Up! 💊
Jun 18, 2025	🎓 Successfully defended my dissertation entitled: “Modeling Multi-Scale Biomedical Interactions via Transfer Learning and Knowledge Integration for Personalized Medicine” 🩺🧬!
May 01, 2025	🎉 One paper accepted to ICML 2025! 🚀🧠
Apr 08, 2025	🎉 Two ISMB/ECCB 2025 Papers Accepted! A Small Win for AI x Drug Discovery 🧪
Jan 15, 2025	🎉 Two Papers on Multi-modal Molecular Representation Learning Accepted!

latest posts

Jul 02, 2025	💊🤖 Insilico's Rentosertib: A Turning Point for AI in Drug Discovery
Jun 29, 2025	🚀 Arc’s Virtual Cell Challenge: Accelerating Drug Discovery with AI Models
Jun 25, 2025	🧬 DeepMind releases AlphaGenome, a New AI Model for Decoding the Genome

selected publications

ICML

BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and EM-like One-Class Boundary Optimization

Dongmin Bang, Inyoung Sung, Yinhua Piao, and 2 more authors

In Forty-second International Conference on Machine Learning, 2025

Bib HTML PDF

@inproceedings{bang2025boundre,
  title = {BounDr.E: Predicting Drug-likeness via Biomedical Knowledge Alignment and {EM}-like One-Class Boundary Optimization},
  author = {Bang, Dongmin and Sung, Inyoung and Piao, Yinhua and Lee, Sangseon and Kim, Sun},
  booktitle = {Forty-second International Conference on Machine Learning},
  year = {2025},
  url = {https://openreview.net/forum?id=Z9Xugry05b},
}

ISMB

Transfer learning of condition-specific perturbation in gene interactions improves drug response prediction

Dongmin Bang^*, Bonil Koo^*, and Sun Kim

Bioinformatics, 2024

Best Paper Award DOI Bib

Received the Best Paper Award in BIOINFO’24, Korean Society for Bioinformatics (KSBi), Korea

@article{bang2024transfer,
  title = {Transfer learning of condition-specific perturbation in gene interactions improves drug response prediction},
  author = {Bang, Dongmin and Koo, Bonil and Kim, Sun},
  journal = {Bioinformatics},
  volume = {40},
  number = {Supplement\_1},
  pages = {i130--i139},
  year = {2024},
  publisher = {Oxford University Press},
  doi = {https://doi.org/10.1093/bioinformatics/btae249}
}

Nat Commun.

Biomedical knowledge graph learning for drug repurposing by extending guilt-by-association to multiple layers

Dongmin Bang, Sangsoo Lim, Sangseon Lee, and 1 more author

Nature Communications, 2023

Best Paper Award DOI Bib

Received the Best Paper Award in BIOINFO’23, Korean Society for Bioinformatics (KSBi), Korea

@article{bang2023biomedical,
  title = {Biomedical knowledge graph learning for drug repurposing by extending guilt-by-association to multiple layers},
  author = {Bang, Dongmin and Lim, Sangsoo and Lee, Sangseon and Kim, Sun},
  journal = {Nature Communications},
  volume = {14},
  number = {1},
  pages = {3570},
  year = {2023},
  publisher = {Nature Publishing Group UK London},
  doi = {https://doi.org/10.1038/s41467-023-39301-y}
}