利用深度学习方法预测蛋白质晶体的 X 射线衍射质量

IF 2.4 4区 材料科学 Q2 CRYSTALLOGRAPHY
Crystals Pub Date : 2024-08-29 DOI:10.3390/cryst14090771
Yujian Shen, Zhongjie Zhu, Qingjie Xiao, Kanglei Ye, Qisheng Wang, Yue Wang, Bo Sun
{"title":"利用深度学习方法预测蛋白质晶体的 X 射线衍射质量","authors":"Yujian Shen, Zhongjie Zhu, Qingjie Xiao, Kanglei Ye, Qisheng Wang, Yue Wang, Bo Sun","doi":"10.3390/cryst14090771","DOIUrl":null,"url":null,"abstract":"Over the past few decades, significant advancements in protein crystallography have led to a steady increase in the number of determined protein structures. The X-ray diffraction experiment remains one of the primary methods for investigating protein crystal structures. To obtain information about crystal structures, a sufficient number of high-quality crystals are typically required. At present, X-ray diffraction experiments on protein crystals primarily rely on manual selection by experimenters. However, each experiment is not only costly but also time-consuming. To address the urgent need for automatic selection of the proper protein crystal candidates for X-ray diffraction experiments, a protein-crystal-quality classification network, leveraging the ConvNeXt network architecture, is proposed. Subsequently, a new database is created, which includes protein crystal images and their corresponding X-ray diffraction images. Additionally, a novel method for categorizing protein quality based on the number of diffraction spots and the resolution is introduced. To further enhance the network’s focus on essential features of protein crystal images, a CBAM (Convolutional Block Attention Module) attention mechanism is incorporated between convolution layers. The experimental results demonstrate that the network achieves significant improvement in performing the prediction task, thereby effectively enhancing the probability of high-quality crystals being selected by experimenters.","PeriodicalId":10855,"journal":{"name":"Crystals","volume":"47 1","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting X-ray Diffraction Quality of Protein Crystals Using a Deep-Learning Method\",\"authors\":\"Yujian Shen, Zhongjie Zhu, Qingjie Xiao, Kanglei Ye, Qisheng Wang, Yue Wang, Bo Sun\",\"doi\":\"10.3390/cryst14090771\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Over the past few decades, significant advancements in protein crystallography have led to a steady increase in the number of determined protein structures. The X-ray diffraction experiment remains one of the primary methods for investigating protein crystal structures. To obtain information about crystal structures, a sufficient number of high-quality crystals are typically required. At present, X-ray diffraction experiments on protein crystals primarily rely on manual selection by experimenters. However, each experiment is not only costly but also time-consuming. To address the urgent need for automatic selection of the proper protein crystal candidates for X-ray diffraction experiments, a protein-crystal-quality classification network, leveraging the ConvNeXt network architecture, is proposed. Subsequently, a new database is created, which includes protein crystal images and their corresponding X-ray diffraction images. Additionally, a novel method for categorizing protein quality based on the number of diffraction spots and the resolution is introduced. To further enhance the network’s focus on essential features of protein crystal images, a CBAM (Convolutional Block Attention Module) attention mechanism is incorporated between convolution layers. The experimental results demonstrate that the network achieves significant improvement in performing the prediction task, thereby effectively enhancing the probability of high-quality crystals being selected by experimenters.\",\"PeriodicalId\":10855,\"journal\":{\"name\":\"Crystals\",\"volume\":\"47 1\",\"pages\":\"\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Crystals\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.3390/cryst14090771\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CRYSTALLOGRAPHY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Crystals","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.3390/cryst14090771","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CRYSTALLOGRAPHY","Score":null,"Total":0}
引用次数: 0

摘要

在过去几十年中,蛋白质晶体学取得了重大进展,已确定的蛋白质结构数量稳步增加。X 射线衍射实验仍然是研究蛋白质晶体结构的主要方法之一。要获得晶体结构信息,通常需要足够数量的高质量晶体。目前,蛋白质晶体的 X 射线衍射实验主要依靠实验人员手动选择。然而,每次实验不仅成本高,而且耗时长。为了满足自动选择合适的候选蛋白质晶体进行 X 射线衍射实验的迫切需要,我们提出了一种利用 ConvNeXt 网络结构的蛋白质晶体质量分类网络。随后,创建了一个新的数据库,其中包括蛋白质晶体图像及其相应的 X 射线衍射图像。此外,还引入了一种基于衍射斑点数量和分辨率的蛋白质质量分类新方法。为了进一步提高网络对蛋白质晶体图像基本特征的关注,在卷积层之间加入了 CBAM(卷积块关注模块)关注机制。实验结果表明,该网络在执行预测任务方面取得了显著的改进,从而有效提高了实验人员选择高质量晶体的概率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Predicting X-ray Diffraction Quality of Protein Crystals Using a Deep-Learning Method
Over the past few decades, significant advancements in protein crystallography have led to a steady increase in the number of determined protein structures. The X-ray diffraction experiment remains one of the primary methods for investigating protein crystal structures. To obtain information about crystal structures, a sufficient number of high-quality crystals are typically required. At present, X-ray diffraction experiments on protein crystals primarily rely on manual selection by experimenters. However, each experiment is not only costly but also time-consuming. To address the urgent need for automatic selection of the proper protein crystal candidates for X-ray diffraction experiments, a protein-crystal-quality classification network, leveraging the ConvNeXt network architecture, is proposed. Subsequently, a new database is created, which includes protein crystal images and their corresponding X-ray diffraction images. Additionally, a novel method for categorizing protein quality based on the number of diffraction spots and the resolution is introduced. To further enhance the network’s focus on essential features of protein crystal images, a CBAM (Convolutional Block Attention Module) attention mechanism is incorporated between convolution layers. The experimental results demonstrate that the network achieves significant improvement in performing the prediction task, thereby effectively enhancing the probability of high-quality crystals being selected by experimenters.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Crystals
Crystals CRYSTALLOGRAPHYMATERIALS SCIENCE, MULTIDIS-MATERIALS SCIENCE, MULTIDISCIPLINARY
CiteScore
4.20
自引率
11.10%
发文量
1527
审稿时长
16.12 days
期刊介绍: Crystals (ISSN 2073-4352) is an open access journal that covers all aspects of crystalline material research. Crystals can act as a reference, and as a publication resource, to the community. It publishes reviews, regular research articles, and short communications. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. Therefore, there is no restriction on article length. Full experimental details must be provided to enable the results to be reproduced. Crystals provides a  forum for the advancement of our understanding of the nucleation, growth, processing, and characterization of crystalline materials. Their mechanical, chemical, electronic, magnetic, and optical properties, and their diverse applications, are all considered to be of importance.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信