ATOMIC: a graph attention network for atopic dermatitis prediction using human gut microbiome
By identifying key microbial taxa that contributed to the AD classification through its interpretable attention mechanism, ATOMIC provides a foundation for personalized microbiome-based interventions and biomarker discovery. Additionally, to facilitate future research, we publicly released a gut microbial abundance dataset from KNUH. The source code and processed abundance data are available from ATOMIC GitHub repository at https://www.github.com/KU-MedAI/ATOMIC.
Authors
- Minji Jeon
- Young Her (ORCID: https://orcid.org/0000-0002-3778-2371)
- Songhyeon Kim
- Joonhong Min
- Wootaek Lim
- Hyunsu Bong
- Hyunjeong Eom
- Dongyoung Lim
Institutions
- Kangwon National University (KR)
- Korea University (KR)
- Korea University Medical Center (KR)
- Kangwon National University Hospital (KR)
- Chuncheon National Hospital (KR)
Publication Details
- Journal
- Frontiers in Immunology
- Published
- 2026-01-08
- DOI
- https://doi.org/10.3389/fimmu.2025.1670993
- Primary Topic
- Dermatology and Skin Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Kangwon National University
- Korea Health Industry Development Institute
- Kyungpook National University Hospital
- Ministry of SMEs and Startups
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion