Evidential deep learning-based drug-target interaction prediction

Yanpeng Zhao, Yuting Xing, Yixin Zhang, Yifei Wang, Mengxuan Wan, Duoyun Yi, Chengkun Wu, Shangze Li, Huiyan Xu, Hongyang Zhang, Ziyi Liu, Guowei Zhou, Mengfan Li, Xuanze Wang, Zhengshan Chen, Ruijiang Li, Lianlian Wu, Dongsheng Zhao, Peng Zan (), Song He () and Xiaochen Bo ()
Additional contact information
Yanpeng Zhao: Academy of Military Medical Sciences
Yuting Xing: Academy of Military Science
Yixin Zhang: Academy of Military Medical Sciences
Yifei Wang: Academy of Military Medical Sciences
Mengxuan Wan: Academy of Military Medical Sciences
Duoyun Yi: Academy of Military Medical Sciences
Chengkun Wu: National University of Defense Technology
Shangze Li: Academy of Military Medical Sciences
Huiyan Xu: Academy of Military Medical Sciences
Hongyang Zhang: Academy of Military Medical Sciences
Ziyi Liu: Academy of Military Medical Sciences
Guowei Zhou: Academy of Military Medical Sciences
Mengfan Li: Academy of Military Medical Sciences
Xuanze Wang: Academy of Military Medical Sciences
Zhengshan Chen: Academy of Military Medical Sciences
Ruijiang Li: Academy of Military Medical Sciences
Lianlian Wu: Academy of Military Medical Sciences
Dongsheng Zhao: Academy of Military Medical Sciences
Peng Zan: Shanghai University
Song He: Academy of Military Medical Sciences
Xiaochen Bo: Academy of Military Medical Sciences

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract Drug-target interaction (DTI) prediction is a crucial component of drug discovery. Recent deep learning methods show great potential in this field but also encounter substantial challenges. These include generating reliable confidence estimates for predictions, enhancing robustness when handling novel, unseen DTIs, and mitigating the tendency toward overconfident and incorrect predictions. To solve these problems, we propose EviDTI, a novel approach utilizing evidential deep learning (EDL) for uncertainty quantification in neural network-based DTI prediction. EviDTI integrates multiple data dimensions, including drug 2D topological graphs and 3D spatial structures, and target sequence features. Through EDL, EviDTI provides uncertainty estimates for its predictions. Experimental results on three benchmark datasets demonstrate the competitiveness of EviDTI against 11 baseline models. In addition, our study shows that EviDTI can calibrate prediction errors. More importantly, well-calibrated uncertainty information enhances the efficiency of drug discovery by prioritizing DTIs with higher confident predictions for experimental validation. In a case study focused on tyrosine kinase modulators, uncertainty-guided predictions identify novel potential modulators targeting tyrosine kinase FAK and FLT3. These results underscore the potential of evidential deep learning as a robust tool for uncertainty quantification in DTI prediction and its broader implications for accelerating drug discovery.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-62235-6 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-62235-6

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-62235-6

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().