EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction

Amit Ranjan iD, Adam Bess, Chris Alvin, Supratik Mukhopadhyay

Journal of Chemical Information and Modeling · 08.07.2024 · 64 (13) · 4980-4990

DOI: 10.1021/acs.jcim.4c00310 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 18.06.2024. Verfasst von Amit Ranjan und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Environmental Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States. Hauptthemen laut MEDLINE: Drug Discovery. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Drug-target affinity (DTA) prediction is an important task in the early stages of drug discovery. Traditional biological approaches are time-consuming, effort-consuming, and resource-consuming due to the large size of genomic and chemical spaces. Computational approaches using machine learning have emerged to narrow down the drug candidate search space. However, most of these prediction models focus on single feature encoding of drugs and targets, ignoring the importance of integrating different dimensions of these features. We propose a deep learning-based approach called Multi-Dimensional Fusion for Drug Target Affinity Prediction (MDF-DTA) incorporating different dimensional features. Our model fuses 1D, 2D, and 3D representations obtained from different pretrained models for both drugs and targets. We evaluated MDF-DTA on two standard benchmark data sets: DAVIS and KIBA. Experimental results show that MDF-DTA outperforms many state-of-the-art techniques in the DTA task across both data sets. Through ablation studies and performance evaluation metrics, we evaluate the importance of individual representations and the impact of each representation on MDF-DTA.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Drug DiscoveryDeep LearningPharmaceutical PreparationsProtein BindingMachine LearningProteins

Substanzen

Pharmaceutical PreparationsProteins

Autor:innen und Institutionen

  • Department of Environmental Sciences, Louisiana State University, Baton Rouge, Louisiana 70803, United States.
  • Department of Computer Science, Furman University, Greenville, South Carolina 29613, United States.

ORCID-Profile: Amit Ranjan

Zitieren

APA

Ranjan, A., Bess, A., Alvin, C., & Mukhopadhyay, S. (2024). MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction. Journal of Chemical Information and Modeling, 64(13), 4980-4990. https://doi.org/10.1021/acs.jcim.4c00310

Vancouver

Ranjan A, Bess A, Alvin C, Mukhopadhyay S. MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction. Journal of Chemical Information and Modeling. 2024;64(13):4980-4990. doi:10.1021/acs.jcim.4c00310

BibTeX
@article{Ranjan2024,
  author = {Ranjan, Amit and Bess, Adam and Alvin, Chris and Mukhopadhyay, Supratik},
  title = {MDF-DTA: A Multi-Dimensional Fusion Approach for Drug-Target Binding Affinity Prediction},
  journal = {Journal of Chemical Information and Modeling},
  year = {2024},
  volume = {64},
  number = {13},
  pages = {4980--4990},
  doi = {10.1021/acs.jcim.4c00310}
}
Kostenlos starten →