FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug–target interaction prediction
Bioinformatics · 03.06.2024 · 40 (6)
DOI: 10.1093/bioinformatics/btae347 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 29.05.2024. Verfasst von Qi Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Mathematics and Computer Science, Yan'an University, Yan'an 716000, China. Hauptthemen laut MEDLINE: Proteins. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yan'an City Science and Technology Development Program, National Natural Science Foundation of China.
Abstract (Originalsprache)
Motivation Identifying drug–target interactions (DTI) is crucial in drug discovery. Fragments are less complex and can accurately characterize local features, which is important in DTI prediction. Recently, deep learning (DL)-based methods predict DTI more efficiently. However, two challenges remain in existing DL-based methods: (i) some methods directly encode drugs and proteins into integers, ignoring the substructure representation; (ii) some methods learn the features of the drugs and proteins separately instead of considering their interactions. Results In this article, we propose a fragment-oriented method based on a multihead cross attention mechanism for predicting DTI, named FMCA-DTI. FMCA-DTI obtains multiple types of fragments of drugs and proteins by branch chain mining and category fragment mining. Importantly, FMCA-DTI utilizes the shared-weight-based multihead cross attention mechanism to learn the complex interaction features between different fragments. Experiments on three benchmark datasets show that FMCA-DTI achieves significantly improved performance by comparing it with four state-of-the-art baselines. Availability and implementation The code for this workflow is available at: https://github.com/jacky102022/FMCA-DTI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- College of Mathematics and Computer Science, Yan'an University, Yan'an 716000, China.
- Medical College of Yan'an University, Yan'an University, Yan'an 716000, China.
- Medical Research and Experimental Center, The Second Affiliated Hospital of Xi'an Medical University, Xi'an 710021, China.
ORCID-Profile: Bisheng Xia
Förderung
- Yan'an City Science and Technology Development Program
- National Natural Science Foundation of China
Zitieren
APA
Zhang, Q., Zuo, L., Ren, Y., Wang, S., Wang, W., Ma, L., Zhang, J., & Xia, B. (2024). FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug–target interaction prediction. Bioinformatics, 40(6). https://doi.org/10.1093/bioinformatics/btae347
Vancouver
Zhang Q, Zuo L, Ren Y, Wang S, Wang W, Ma L, et al. FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug–target interaction prediction. Bioinformatics. 2024;40(6). doi:10.1093/bioinformatics/btae347
BibTeX
@article{Zhang2024,
author = {Zhang, Qi and Zuo, Le and Ren, Ying and Wang, Siyuan and Wang, Wenfa and Ma, Lerong and Zhang, Jing and Xia, Bisheng},
title = {FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug–target interaction prediction},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {6},
doi = {10.1093/bioinformatics/btae347}
}
EUVIMED