De novo drug design framework based on mathematical programming method and deep learning model

Small‐molecule drugs are of significant importance to human health. The use of efficient model‐based de novo drug design method is an option worth considering for expediting the discovery of drugs with satisfactory properties. In this article, a deep learning model is first developed for identificat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:AIChE journal Jg. 68; H. 9
Hauptverfasser: Zhao, Yujing, Liu, Qilei, Wu, Xinyuan, Zhang, Lei, Du, Jian, Meng, Qingwei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Hoboken, USA John Wiley & Sons, Inc 01.09.2022
American Institute of Chemical Engineers
Schlagworte:
Artificial neural networks
binding affinity
chemical product design
Deep learning
Design
Design optimization
drug design
Drug development
Drug discovery
Drugs
Mathematical programming
mathematical programming method
Molecular docking
Molecular dynamics
Neural networks
Nonlinear programming
ISSN:0001-1541, 1547-5905
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Small‐molecule drugs are of significant importance to human health. The use of efficient model‐based de novo drug design method is an option worth considering for expediting the discovery of drugs with satisfactory properties. In this article, a deep learning model is first developed for identifications of protein‐ligand complexes with high binding affinity, where the Mol2vec descriptor, the convolutional neural network, and the gate augmentation‐based Attention mechanism are used for the model construction. Then, an optimization‐based de novo drug design framework is established by integrating the deep learning model into a Mixed‐Integer NonLinear Programming (MINLP) model for drug candidate design. The optimal solution of the MINLP model is further verified by the physics‐based methods of molecular docking and molecular dynamics simulation. Finally, two case studies involving the design of anticoagulant and antitumor drug candidates are presented to highlight the wide applicability and effectiveness of the MINLP‐based de novo drug design framework.
Bibliographie:Funding information
National Natural Science Foundation of China, Grant/Award Numbers: 22078041, 21808025, 22178045; the Fundamental Research Funds for the Central Universities, Grant/Award Number: DUT20JC41
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0001-1541
1547-5905
DOI:10.1002/aic.17748