MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction

Abstract Background The development of drug–target binding affinity (DTA) prediction tasks significantly drives the drug discovery process forward. Leveraging the rapid advancement of artificial intelligence, DTA prediction tasks have undergone a transformative shift from wet lab experimentation to...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinghong Sun, Han Wang, Jia Mi, Jing Wan, Jingyang Gao
Format: Article
Language:English
Published: BMC 2024-12-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-024-05984-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169205540782080
author Jinghong Sun
Han Wang
Jia Mi
Jing Wan
Jingyang Gao
author_facet Jinghong Sun
Han Wang
Jia Mi
Jing Wan
Jingyang Gao
author_sort Jinghong Sun
collection DOAJ
description Abstract Background The development of drug–target binding affinity (DTA) prediction tasks significantly drives the drug discovery process forward. Leveraging the rapid advancement of artificial intelligence, DTA prediction tasks have undergone a transformative shift from wet lab experimentation to machine learning-based prediction. This transition enables a more expedient exploration of potential interactions between drugs and targets, leading to substantial savings in time and funding resources. However, existing methods still face several challenges, such as drug information loss, lack of calculation of the contribution of each modality, and lack of simulation regarding the drug–target binding mechanisms. Results We propose MTAF–DTA, a method for drug–target binding affinity prediction to solve the above problems. The drug representation module extracts three modalities of features from drugs and uses an attention mechanism to update their respective contribution weights. Additionally, we design a Spiral-Attention Block (SAB) as drug–target feature fusion module based on multi-type attention mechanisms, facilitating a triple fusion process between them. The SAB, to some extent, simulates the interactions between drugs and targets, thereby enabling outstanding performance in the DTA task. Our regression task on the Davis and KIBA datasets demonstrates the predictive capability of MTAF–DTA, with CI and MSE metrics showing respective improvements of 1.1% and 9.2% over the state-of-the-art (SOTA) method in the novel target settings. Furthermore, downstream tasks further validate MTAF–DTA’s superiority in DTA prediction. Conclusions Experimental results and case study demonstrate the superior performance of our approach in DTA prediction tasks, showing its potential in practical applications such as drug discovery and disease treatment.
format Article
id doaj-art-a6082d8aefad4a1c84a09e1709b59d3b
institution OA Journals
issn 1471-2105
language English
publishDate 2024-12-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-a6082d8aefad4a1c84a09e1709b59d3b2025-08-20T02:20:47ZengBMCBMC Bioinformatics1471-21052024-12-0125112110.1186/s12859-024-05984-3MTAF–DTA: multi-type attention fusion network for drug–target affinity predictionJinghong Sun0Han Wang1Jia Mi2Jing Wan3Jingyang Gao4College of Information Science and Technology, Beijing University of Chemical TechnologyCollege of Information Science and Technology, Beijing University of Chemical TechnologyCollege of Information Science and Technology, Beijing University of Chemical TechnologyCollege of Information Science and Technology, Beijing University of Chemical TechnologyCollege of Information Science and Technology, Beijing University of Chemical TechnologyAbstract Background The development of drug–target binding affinity (DTA) prediction tasks significantly drives the drug discovery process forward. Leveraging the rapid advancement of artificial intelligence, DTA prediction tasks have undergone a transformative shift from wet lab experimentation to machine learning-based prediction. This transition enables a more expedient exploration of potential interactions between drugs and targets, leading to substantial savings in time and funding resources. However, existing methods still face several challenges, such as drug information loss, lack of calculation of the contribution of each modality, and lack of simulation regarding the drug–target binding mechanisms. Results We propose MTAF–DTA, a method for drug–target binding affinity prediction to solve the above problems. The drug representation module extracts three modalities of features from drugs and uses an attention mechanism to update their respective contribution weights. Additionally, we design a Spiral-Attention Block (SAB) as drug–target feature fusion module based on multi-type attention mechanisms, facilitating a triple fusion process between them. The SAB, to some extent, simulates the interactions between drugs and targets, thereby enabling outstanding performance in the DTA task. Our regression task on the Davis and KIBA datasets demonstrates the predictive capability of MTAF–DTA, with CI and MSE metrics showing respective improvements of 1.1% and 9.2% over the state-of-the-art (SOTA) method in the novel target settings. Furthermore, downstream tasks further validate MTAF–DTA’s superiority in DTA prediction. Conclusions Experimental results and case study demonstrate the superior performance of our approach in DTA prediction tasks, showing its potential in practical applications such as drug discovery and disease treatment.https://doi.org/10.1186/s12859-024-05984-3Drug–target binding affinityMulti-modal featuresAttention mechanismsNested fusion networks
spellingShingle Jinghong Sun
Han Wang
Jia Mi
Jing Wan
Jingyang Gao
MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
BMC Bioinformatics
Drug–target binding affinity
Multi-modal features
Attention mechanisms
Nested fusion networks
title MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
title_full MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
title_fullStr MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
title_full_unstemmed MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
title_short MTAF–DTA: multi-type attention fusion network for drug–target affinity prediction
title_sort mtaf dta multi type attention fusion network for drug target affinity prediction
topic Drug–target binding affinity
Multi-modal features
Attention mechanisms
Nested fusion networks
url https://doi.org/10.1186/s12859-024-05984-3
work_keys_str_mv AT jinghongsun mtafdtamultitypeattentionfusionnetworkfordrugtargetaffinityprediction
AT hanwang mtafdtamultitypeattentionfusionnetworkfordrugtargetaffinityprediction
AT jiami mtafdtamultitypeattentionfusionnetworkfordrugtargetaffinityprediction
AT jingwan mtafdtamultitypeattentionfusionnetworkfordrugtargetaffinityprediction
AT jingyanggao mtafdtamultitypeattentionfusionnetworkfordrugtargetaffinityprediction