» Articles » PMID: 35216254

A Deep Learning-Based Quantitative Structure-Activity Relationship System Construct Prediction Model of Agonist and Antagonist with High Performance

Overview
Journal Int J Mol Sci
Publisher MDPI
Date 2022 Feb 26
PMID 35216254
Authors
Affiliations
Soon will be listed here.
Abstract

Molecular design and evaluation for drug development and chemical safety assessment have been advanced by quantitative structure-activity relationship (QSAR) using artificial intelligence techniques, such as deep learning (DL). Previously, we have reported the high performance of prediction models molecular initiation events (MIEs) on the adverse toxicological outcome using a DL-based QSAR method, called DeepSnap-DL. This method can extract feature values from images generated on a three-dimensional (3D)-chemical structure as a novel QSAR analytical system. However, there is room for improvement of this system's time-consumption. Therefore, in this study, we constructed an improved DeepSnap-DL system by combining the processes of generating an image from a 3D-chemical structure, DL using the image as input data, and statistical calculation of prediction-performance. Consequently, we obtained that the three prediction models of agonists or antagonists of MIEs achieved high prediction-performance by optimizing the parameters of DeepSnap, such as the angle used in the depiction of the image of a 3D-chemical structure, data-split, and hyperparameters in DL. The improved DeepSnap-DL system will be a powerful tool for computer-aided molecular design as a novel QSAR system.

Citing Articles

AI-Driven Innovation in Skin Kinetics for Transdermal Drug Delivery: Overcoming Barriers and Enhancing Precision.

Albayati N, Talluri S, Dholaria N, Michniak-Kohn B Pharmaceutics. 2025; 17(2).

PMID: 40006555 PMC: 11859831. DOI: 10.3390/pharmaceutics17020188.


Efficiency of pharmaceutical toxicity prediction in computational toxicology.

Uesawa Y Toxicol Res. 2024; 40(1):1-9.

PMID: 38223665 PMC: 10786748. DOI: 10.1007/s43188-023-00215-y.


Ensemble Learning, Deep Learning-Based and Molecular Descriptor-Based Quantitative Structure-Activity Relationships.

Matsuzaka Y, Uesawa Y Molecules. 2023; 28(5).

PMID: 36903654 PMC: 10005768. DOI: 10.3390/molecules28052410.


QSAR, ADMET In Silico Pharmacokinetics, Molecular Docking and Molecular Dynamics Studies of Novel Bicyclo (Aryl Methyl) Benzamides as Potent GlyT1 Inhibitors for the Treatment of Schizophrenia.

El Fadili M, Er-Rajy M, Kara M, Assouguem A, Belhassan A, Alotaibi A Pharmaceuticals (Basel). 2022; 15(6).

PMID: 35745588 PMC: 9228289. DOI: 10.3390/ph15060670.

References
1.
Rosa G, Palmeira A, Resende D, Almeida I, Kane-Pages A, Barreto M . Xanthones for melanogenesis inhibition: Molecular docking and QSAR studies to understand their anti-tyrosinase activity. Bioorg Med Chem. 2020; 29:115873. DOI: 10.1016/j.bmc.2020.115873. View

2.
Tsai K, Chang C, Lo L, Chiang J, Chang C, Huang Y . Automatic segmentation of paravertebral muscles in abdominal CT scan by U-Net: The application of data augmentation technique to increase the Jaccard ratio of deep learning. Medicine (Baltimore). 2021; 100(44):e27649. PMC: 8568419. DOI: 10.1097/MD.0000000000027649. View

3.
Wang X, Duan W, Lin G, Li B, Chen M, Lei F . Synthesis, 3D-QSAR and Molecular Docking Study of Nopol-Based 1,2,4-Triazole-Thioether Compounds as Potential Antifungal Agents. Front Chem. 2021; 9:757584. PMC: 8576812. DOI: 10.3389/fchem.2021.757584. View

4.
Sun C, Feng L, Sun X, Yu R, Kang C . Design and screening of FAK, CDK 4/6 dual inhibitors by pharmacophore model, molecular docking, and molecular dynamics simulation. J Biomol Struct Dyn. 2020; 39(15):5358-5367. DOI: 10.1080/07391102.2020.1786458. View

5.
Elekofehinti O, Iwaloye O, Molehin O, Famusiwa C . Identification of lead compounds from large natural product library targeting 3C-like protease of SARS-CoV-2 using E-pharmacophore modelling, QSAR and molecular dynamics simulation. In Silico Pharmacol. 2021; 9(1):49. PMC: 8349134. DOI: 10.1007/s40203-021-00109-7. View