MixingDTA: improved drug–target affinity prediction by extending mixup with guilt-by-association
Bioinformatics · 01.07.2025 · 41 (Supplement_1) · i105-i114
DOI: 10.1093/bioinformatics/btaf238 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 15.07.2025. Verfasst von Youngoh Kim und 6 weiteren Autor:innen. Beteiligte Einrichtung: Bio-MAX Institute, Seoul National University, Seoul, 08826, Republic of Korea. Hauptthemen laut MEDLINE: Drug Discovery, Proteins, Computational Biology, Software. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bio & Medical Technology Development, National Research Foundation, Ministry of Science and ICT.
Abstract (Originalsprache)
Summary Drug–target affinity (DTA) prediction is an important regression task for drug discovery, which can provide richer information than traditional drug–target interaction prediction as a binary prediction task. To achieve accurate DTA prediction, quite large amount of data are required for each drug, which is not available as of now. Thus, data scarcity and sparsity is a major challenge. Another important task is “cold-start” DTA prediction for unseen drug or protein. In this work, we introduce MixingDTA, a novel framework to tackle data scarcity by incorporating domain-specific pretrained language models for molecules and proteins with our MEETA (MolFormer and ESM-based Efficient aggregation Transformer for Affinity) model. We further address the label sparsity and cold-start challenges through a novel data augmentation strategy named GBA-Mixup, which interpolates embeddings of neighboring entities based on the guilt-by-association (GBA) principle, to improve prediction accuracy even in sparse regions of DTA space. Our experiments on benchmark datasets demonstrate that the MEETA backbone alone provides up to a 19% improvement of mean squared error over current state-of-the-art baseline, and the addition of GBA-Mixup contributes a further 8.4% improvement. Importantly, GBA-Mixup is model-agnostic, delivering performance gains across all tested backbone models of up to 16.9%. Case studies shows how MixingDTA interpolates between drugs and targets in the embedding space, demonstrating generalizability for unseen drug–target pairs while effectively focusing on functionally critical residues. These results highlight MixingDTA’s potential to accelerate drug discovery by offering accurate, scalable, and biologically informed DTA predictions. Availability and implementation The code for MixingDTA is available at https://github.com/rokieplayer20/MixingDTA.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Bio-MAX Institute, Seoul National University, Seoul, 08826, Republic of Korea.
- Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, 08826, Republic of Korea.
- AIGENDRUG Co., Ltd., Seoul, 08758, Republic of Korea.
- Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, 08826, Republic of Korea.
- Department of Computer Science and Engineering, Seoul National University, Seoul, 08826, Republic of Korea.
ORCID-Profile: Youngoh Kim, Dongmin Bang, Bonil Koo, Jungseob Yi, Changyun Cho, Sun Kim
Förderung
- Bio & Medical Technology Development
- National Research Foundation
- Ministry of Science and ICT
- Republic of Korea
- NRF
- Institute of Information & communications Technology Planning & Evaluation
- MSIT
- Artificial Intelligence Graduate School Program
Zitieren
APA
Kim, Y., Bang, D., Koo, B., Yi, J., Cho, C., Choi, J., & Kim, S. (2025). MixingDTA: improved drug–target affinity prediction by extending mixup with guilt-by-association. Bioinformatics, 41(Supplement_1), i105-i114. https://doi.org/10.1093/bioinformatics/btaf238
Vancouver
Kim Y, Bang D, Koo B, Yi J, Cho C, Choi J, et al. MixingDTA: improved drug–target affinity prediction by extending mixup with guilt-by-association. Bioinformatics. 2025;41(Supplement_1):i105-i114. doi:10.1093/bioinformatics/btaf238
BibTeX
@article{Kim2025,
author = {Kim, Youngoh and Bang, Dongmin and Koo, Bonil and Yi, Jungseob and Cho, Changyun and Choi, Jeonguk and Kim, Sun},
title = {MixingDTA: improved drug–target affinity prediction by extending mixup with guilt-by-association},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {Supplement_1},
pages = {i105--i114},
doi = {10.1093/bioinformatics/btaf238}
}
EUVIMED