DeepTransformer: Node Classification Research of a Deep Graph Network on an Osteoporosis Graph based on GraphTransformer

IF 1.5 4区医学 Q4 CHEMISTRY, MEDICINAL

Current computer-aided drug design Pub Date : 2023-12-01 DOI:10.2174/0115734099266731231115065030

Yixin Liu, Guowei Jiang, Miaomiao Sun, Ziyan Zhou, Pengchen Liang, Qing Chang

{"title":"DeepTransformer: Node Classification Research of a Deep Graph Network on an Osteoporosis Graph based on GraphTransformer","authors":"Yixin Liu, Guowei Jiang, Miaomiao Sun, Ziyan Zhou, Pengchen Liang, Qing Chang","doi":"10.2174/0115734099266731231115065030","DOIUrl":null,"url":null,"abstract":"Background:: Osteoporosis (OP) is one of the most common diseases in the elderly population. It is mostly treated with medication, but drug research and development have the disadvantage of taking a long time and having a high cost. Objective:: Therefore, we developed a graph neural network with the help of artificial intelligence to provide new ideas for drug research and development for OP. Methods:: In this study, we built a new osteoporosis graph (called OPGraph) and proposed a deep graph neural network (called DeepTransformer) to predict new drugs for OP. OPGraph is a graph data model established by gathering features and their interrelationships from a vast amount of OP data. DeepTransformer uses GraphTransformer as its foundational network and applies residual connections for deep layering. Results:: The analysis and results showed that DeepTransformer outperformed numerous models on OPGraph, with area under the curve (AUC) and area under the precision-recall curve (AUPR) reaching 0.9916 and 0.9911, respectively. In addition, we conducted an in vitro validation experiment on two of the seven predicted compounds (Puerarin and Aucubin), and the results corroborated the predictions of our model. Conclusion:: The model we developed with the help of artificial intelligence can effectively reduce the time and cost of OP drug development and reduce the heavy economic burden brought to patient's family by complications caused by osteoporosis.","PeriodicalId":10886,"journal":{"name":"Current computer-aided drug design","volume":"32 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current computer-aided drug design","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/0115734099266731231115065030","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CHEMISTRY, MEDICINAL","Score":null,"Total":0}

引用次数: 0

Abstract

Background:: Osteoporosis (OP) is one of the most common diseases in the elderly population. It is mostly treated with medication, but drug research and development have the disadvantage of taking a long time and having a high cost. Objective:: Therefore, we developed a graph neural network with the help of artificial intelligence to provide new ideas for drug research and development for OP. Methods:: In this study, we built a new osteoporosis graph (called OPGraph) and proposed a deep graph neural network (called DeepTransformer) to predict new drugs for OP. OPGraph is a graph data model established by gathering features and their interrelationships from a vast amount of OP data. DeepTransformer uses GraphTransformer as its foundational network and applies residual connections for deep layering. Results:: The analysis and results showed that DeepTransformer outperformed numerous models on OPGraph, with area under the curve (AUC) and area under the precision-recall curve (AUPR) reaching 0.9916 and 0.9911, respectively. In addition, we conducted an in vitro validation experiment on two of the seven predicted compounds (Puerarin and Aucubin), and the results corroborated the predictions of our model. Conclusion:: The model we developed with the help of artificial intelligence can effectively reduce the time and cost of OP drug development and reduce the heavy economic burden brought to patient's family by complications caused by osteoporosis.

查看原文本刊更多论文

DeepTransformer:基于GraphTransformer的骨质疏松图深度图网络节点分类研究

背景:骨质疏松症(Osteoporosis, OP)是老年人最常见的疾病之一。它主要是通过药物治疗，但药物研究和开发的缺点是耗时长，成本高。为此，我们借助人工智能技术开发了一种图神经网络，为OP的药物研发提供新的思路。方法:在本研究中，我们构建了一种新的骨质疏松症图(OPGraph)，并提出了一种深度图神经网络(DeepTransformer)来预测OP的新药。OPGraph是通过收集大量OP数据中的特征及其相互关系而建立的图数据模型。DeepTransformer使用GraphTransformer作为其基础网络，并应用剩余连接进行深层分层。结果:分析和结果表明，DeepTransformer在OPGraph上优于众多模型，曲线下面积(AUC)和精确召回曲线下面积(AUPR)分别达到0.9916和0.9911。此外，我们对预测的7种化合物中的2种(葛根素和Aucubin)进行了体外验证实验，结果证实了我们的模型的预测。结论:我们借助人工智能开发的模型可以有效减少OP药物开发的时间和成本，减轻骨质疏松症并发症给患者家庭带来的沉重经济负担。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Current computer-aided drug design 医学-计算机：跨学科应用

CiteScore

3.70

自引率

5.90%

发文量

审稿时长

>12 weeks

期刊介绍： Aims & Scope Current Computer-Aided Drug Design aims to publish all the latest developments in drug design based on computational techniques. The field of computer-aided drug design has had extensive impact in the area of drug design. Current Computer-Aided Drug Design is an essential journal for all medicinal chemists who wish to be kept informed and up-to-date with all the latest and important developments in computer-aided methodologies and their applications in drug discovery. Each issue contains a series of timely, in-depth reviews, original research articles and letter articles written by leaders in the field, covering a range of computational techniques for drug design, screening, ADME studies, theoretical chemistry; computational chemistry; computer and molecular graphics; molecular modeling; protein engineering; drug design; expert systems; general structure-property relationships; molecular dynamics; chemical database development and usage etc., providing excellent rationales for drug development.