MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (2025)

Table of Contents
Abstract List of references Publications that cite this publication

MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (1) https://doi.org/10.1101/2023.09.19.558555

Journal: 2023

Publisher: Cold Spring Harbor Laboratory

Authors: Liwei Liu, Qi Zhang, Yuxiao Wei, Shengli Zhang, Bo Liao

Abstract

AbstractThe prediction of drug-target affinity (DTA) plays an important role in the development of drugs and the discovery of potential drug targets. In recent years, computer-assisted DTA prediction has become an important method in this field. In this work, we propose a multi-modal deep learning framework for drug-target binding affinity and binding region prediction, namely MMD-DTA. The model can predict DTA while unsupervised learning of drug-target binding regions. The experimental results show that MMD-DTA performs better than the existing models on the main evaluation metrics. In addition, external validation results show that MMD-DTA improves the generalization ability of the model by integrating sequence information and structural information of drugs and targets, and the model trained on the benchmark dataset can be well generalized to independent virtual screening tasks. Visualization of drug-target binding region prediction shows the powerful interpretability of MMD-DTA, which has important implications for exploring the functional regions of drug molecules acting on proteins.

See Also
MMDTA: A Multimodal Deep Model for Drug-Target Affinity with a Hybrid Fusion Strategy | Semantic Scholar

List of references

  1. The current status of drug discovery and development as originated in United States academia: the influence of industrial and academic collaboration on drug discovery and development, Clinical and translational science, № 11, с. 597
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (2) https://doi.org/10.1111/cts.12577
  2. New drugs cost US $2.6 billion to develop, Nature reviews drug discovery, № 13, с. 877
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (3) https://doi.org/10.1038/nrd4507
  3. SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines, Journal of cheminformatics, № 9, с. 1
  4. Zhao, Q. , Xiao, F. , Yang, M. , Li, Y. , & Wang, J . (2019, November). AttentionDTA: prediction of drug–target binding affinity using attention model. In 2019 IEEE international conference on bioinformatics and biomedicine (BIBM) (pp. 64–69). IEEE.
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (4) https://doi.org/10.1109/BIBM47256.2019.8983125
  5. Öztürk, H. , Ozkirimli, E. , & Özgür, A. (2019). WideDTA: prediction of drug-target binding affinity. arXiv preprint arXiv:1902.04166.
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (5) https://doi.org/10.1093/bioinformatics/bty593
  6. Graph convolutional networks for drug response prediction, IEEE/ACM transactions on computational biology and bioinformatics, № 19, с. 146
  7. Drug–target affinity prediction using graph neural network and contact maps, RSC advances, № 10, с. 20701
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (6) https://doi.org/10.1039/D0RA02297G
  8. Convolutional neural network with stacked autoencoders for predicting drug-target interaction and binding affinity. International Journal of Data Mining, Modelling and Management, № 13, с. 81
  9. CPInformer for efficient and robust compound-protein interaction prediction, IEEE/ACM transactions on computational biology and bioinformatics, № 20, с. 285
  10. Perceiver CPI: a nested cross-attention network for compound–protein interaction prediction, Bioinformatics, № 39, с. btac731
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (7) https://doi.org/10.1093/bioinformatics/btac731
  11. SAM-DTA: a sequence-agnostic model for drug–target binding affinity prediction, Briefings in Bioinformatics, № 24, с. bbac533
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (8) https://doi.org/10.1093/bib/bbac533
  12. He, H. , Chen, G. , & Chen, C. Y. C . (2023). NHGNN-DTA: A Node-adaptive Hybrid Graph Neural Network for Interpretable Drug-target Binding Affinity Prediction. Bioinformatics, btad 355.
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (9) https://doi.org/10.1093/bioinformatics/btad355
  13. Compound–protein interaction prediction with end-to-end learning of neural networks for graphs and sequences, Bioinformatics, № 35, с. 309
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (10) https://doi.org/10.1093/bioinformatics/bty535
  14. DeepCDA: deep cross-domain compound–protein affinity prediction through LSTM and convolutional neural networks, Bioinformatics, № 36, с. 4633
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (11) https://doi.org/10.1093/bioinformatics/btaa544
  15. LSTM: A search space odyssey, IEEE transactions on neural networks and learning systems, № 28, с. 2222
  16. Informer: Beyond efficient transformer for long sequence time-series forecasting, In Proceedings of the AAAI conference on artificial intelligence, № 35, с. 11106
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (12) https://doi.org/10.1609/aaai.v35i12.17325
  17. Rectified wing loss for efficient and robust facial landmark localisation with convolutional neural networks, International Journal of Computer Vision, № 128, с. 2126
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (13) https://doi.org/10.1007/s11263-019-01275-0
  18. MFR-DTA: a multi-functional and robust model for predicting drug–target binding affinity and region, Bioinformatics, № 39, с. btad056
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (14) https://doi.org/10.1093/bioinformatics/btad056
  19. PconsC4: fast, accurate and hassle-free contact predictions, Bioinformatics, № 35, с. 2677
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (15) https://doi.org/10.1093/bioinformatics/bty1036
  20. The trRosetta server for fast and accurate protein structure prediction, Nature protocols, № 16, с. 5634
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (16) https://doi.org/10.1038/s41596-021-00628-9
  21. AtomNet: a deep convolutional neural network for bioactivity prediction in structure-based drug discovery, arXiv preprint arXiv, № 1510, с. 02855
  22. Rdkit documentation, Release, № 1, с. 4
  23. Gaber, Y. , Rashad, B. , & Fathy, E . (2019). Biological 3D structural databases. Essentials of Bioinformatics, Volume I: Understanding Bioinformatics: Genes to Proteins, 47-73.
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (17) https://doi.org/10.1007/978-3-030-02634-9_4
  24. Ramsundar, B. , Eastman, P. , Walters, P. , & Pande, V . (2019). Deep learning for the life sciences: applying deep learning to genomics, microscopy, drug discovery, and more. “O’Reilly Media, Inc.”.
  25. Balduzzi, D. , Frean, M. , Leary, L. , Lewis, J. P. , Ma, K. W. D. , & McWilliams, B. (2017, July). The shattered gradients problem: If resnets are the answer, then what is the question?. In International Conference on Machine Learning (pp. 342–350). PMLR.
  26. He, K. , Zhang, X. , Ren, S. , & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770–778).
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (18) https://doi.org/10.1109/CVPR.2016.90
  27. Predicting drug–protein interaction using quasi-visual question answering system, Nature Machine Intelligence, № 2, с. 134
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (19) https://doi.org/10.1038/s42256-020-0152-y
  28. Deep drug-target binding affinity prediction with multiple attention blocks, Briefings in bioinformatics, № 22, с. bbab117
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (20) https://doi.org/10.1093/bib/bbab117
  29. GraphDTA: Predicting drug–target binding affinity with graph neural networks, Bioinformatics, № 37, с. 1140
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (21) https://doi.org/10.1093/bioinformatics/btaa921
  30. Mukherjee, S. , Ghosh, M. , & Basuchowdhuri, P . (2022). DeepGLSTM: deep graph convolutional network and LSTM based approach for predicting drug-target binding affinity. In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM) (pp. 729-737). Society for Industrial and Applied Mathematics.
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (22) https://doi.org/10.1137/1.9781611977172.82
  31. DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences, PLoS computational biology, № 15, с. e1007129
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (23) https://doi.org/10.1371/journal.pcbi.1007129
  32. HyperAttentionDTI: improving drug– protein interaction prediction by sequence-based deep learning with attention mechanism, Bioinformatics, № 38, с. 655
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (24) https://doi.org/10.1093/bioinformatics/btab715
  33. A Biological Feature and Heterogeneous Network Representation Learning-Based Framework for Drug–Target Interaction Prediction, Molecules, № 28, с. 6546
    MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (25) https://doi.org/10.3390/molecules28186546

Publications that cite this publication

BASE: a web service for providing compound-protein binding affinity prediction datasets with reduced similarity bias

Hyojin Son, Sechan Lee, Jaeuk Kim, Haangik Park, Myeong-Ha Hwang, Gwan-Su Yi

MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (26) https://doi.org/10.1186/s12859-024-05968-3 · MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (27)

2024, BMC Bioinformatics, №1

Scopus

WoS

Crossref citations:0

Find all citations of the publication

About this publication

Publication type Оприлюднений вміст
Number of citations 0
Number of works in the list of references 33
Journal indexed in Scopus No
Journal indexed in Web of Science No
MMD-DTA: A multi-modal deep learning framework for drug-target binding affinity and binding region prediction (2025)
Top Articles
Dian Parkinson: Remembering the Legendary Model and Television Personality - Oli And Alex
80 For Brady Showtimes Near Regal Largo Mall
Adventure Time Soap2Day
Latest Posts
Little's Funeral Home Smithfield Virginia
Holly Hallstrom | Biography
Recommended Articles
Article information

Author: Mrs. Angelic Larkin

Last Updated:

Views: 6053

Rating: 4.7 / 5 (47 voted)

Reviews: 94% of readers found this page helpful

Author information

Name: Mrs. Angelic Larkin

Birthday: 1992-06-28

Address: Apt. 413 8275 Mueller Overpass, South Magnolia, IA 99527-6023

Phone: +6824704719725

Job: District Real-Estate Facilitator

Hobby: Letterboxing, Vacation, Poi, Homebrewing, Mountain biking, Slacklining, Cabaret

Introduction: My name is Mrs. Angelic Larkin, I am a cute, charming, funny, determined, inexpensive, joyous, cheerful person who loves writing and wants to share my knowledge and understanding with you.