AI in Chemistry

Artificial Intelligence in Chemistry

물리화학적 성질 예측, 분자 스펙트럼 예측, 화학무기 등 위험 물질의 독성 예측을 위한 머신러닝 및 딥러닝 모델을 개발하고 있습니다. 대규모 화학 데이터셋과 첨단 신경망 구조를 활용하여, 실험적 취급이 어렵거나 불가능한 유해 화합물의 신속한 스크리닝과 평가를 가능하게 하며, 보다 안전한 화학물질 탐색 및 화학 안전성 평가를 가속화하는 연구를 수행하고 있습니다.

We develop machine learning and deep learning models tailored for chemical applications, including the prediction of physicochemical properties, molecular spectra, and toxicity of hazardous substances such as chemical warfare agents. By leveraging large-scale chemical datasets and advanced neural network architectures, our AI-driven approaches enable rapid screening and assessment of dangerous compounds that are difficult or impossible to handle experimentally, accelerating the discovery of safer chemical alternatives and strengthening chemical safety evaluation.

<최근 논문>

 - Advancing chemical safety prediction: an integrated GNN framework with DFT-augmented cyclic compound solution

Seul Lee, Jooyeon Lee, Unghwi Yoon, Jahyun Koo, Young Wook Yoon, Yoonjae Cho, Seung-Ryul Hwang, Keunhong Jeong*

Journal of Cheminformatics (2026)

 - Multimodal Graph Fusion with Statistically Guided Parsimonious Descriptor Selection for Molecular Property Prediction

Yoonsuk Jang, Juyeon Lee, Hwang, Keunhong Jeong*, Jaeoh Kim*

Journal of Cheminformatics (2026)

 - Integrated AI-driven framework for precise prediction of electrolyte additive oxidation potentials in lithium-ion batteries

Sungsoo Kim, Il-Hyung Lee, Yonggoon Jeon, Changjae Lee, Teawoo Lee, Jahyun Koo, Ihnkyung Jung, Janghyuk Moon, Jungwon Park*, Keunhong Jeong*

Journal of Power Sources (2026)