FMCA-DTI: a fragment-oriented method based on a multihead cross attention mechanism to improve drug–target interaction prediction
Open Access
- 29 May 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 40 (6)
Abstract
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.Keywords
Funding Information
- Yan'an City Science and Technology Development Program (203010096)
- National Natural Science Foundation of China
- National Natural Science Foundation of China (62366053)
This publication has 42 references indexed in Scilit:
- BCM-DTI: A fragment-oriented method for drug–target interaction prediction using deep learningComputational Biology and Chemistry, 2023
- Predicting Drug–Target Interactions with Deep-Embedding Learning of Graphs and SequencesThe Journal of Physical Chemistry A, 2021
- Prediction of drug-target interactions based on multi-layer network representation learningNeurocomputing, 2021
- Predicting Drug–Target Interaction Using a Novel Graph Neural Network with 3D Structure-Embedded Graph RepresentationJournal of Chemical Information and Modeling, 2019
- In silico drug repositioning – what we need to knowDrug Discovery Today, 2013
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010
- Novel opportunities for computational biology and sociology in drug discoveryTrends in Biotechnology, 2010
- Predicting promiscuityNature, 2009
- AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibilityJournal of Computational Chemistry, 2009
- Structure-based maximal affinity model predicts small-molecule druggabilityNature Biotechnology, 2007