分子特性预测的多模式表征学习:序列、图形、几何

Zeyu Wang, Tianyi Jiang, Jinhuan Wang, Qi Xuan
{"title":"分子特性预测的多模式表征学习:序列、图形、几何","authors":"Zeyu Wang, Tianyi Jiang, Jinhuan Wang, Qi Xuan","doi":"arxiv-2401.03369","DOIUrl":null,"url":null,"abstract":"Recent years have seen a rapid growth of machine learning in cheminformatics\nproblems. In order to tackle the problem of insufficient training data in\nreality, more and more researchers pay attention to data augmentation\ntechnology. However, few researchers pay attention to the problem of\nconstruction rules and domain information of data, which will directly impact\nthe quality of augmented data and the augmentation performance. While in\ngraph-based molecular research, the molecular connectivity index, as a critical\ntopological index, can directly or indirectly reflect the topology-based\nphysicochemical properties and biological activities. In this paper, we propose\na novel data augmentation technique that modifies the topology of the molecular\ngraph to generate augmented data with the same molecular connectivity index as\nthe original data. The molecular connectivity index combined with data\naugmentation technology helps to retain more topology-based molecular\nproperties information and generate more reliable data. Furthermore, we adopt\nfive benchmark datasets to test our proposed models, and the results indicate\nthat the augmented data generated based on important molecular topology\nfeatures can effectively improve the prediction accuracy of molecular\nproperties, which also provides a new perspective on data augmentation in\ncheminformatics studies.","PeriodicalId":501325,"journal":{"name":"arXiv - QuanBio - Molecular Networks","volume":"16 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometry\",\"authors\":\"Zeyu Wang, Tianyi Jiang, Jinhuan Wang, Qi Xuan\",\"doi\":\"arxiv-2401.03369\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent years have seen a rapid growth of machine learning in cheminformatics\\nproblems. In order to tackle the problem of insufficient training data in\\nreality, more and more researchers pay attention to data augmentation\\ntechnology. However, few researchers pay attention to the problem of\\nconstruction rules and domain information of data, which will directly impact\\nthe quality of augmented data and the augmentation performance. While in\\ngraph-based molecular research, the molecular connectivity index, as a critical\\ntopological index, can directly or indirectly reflect the topology-based\\nphysicochemical properties and biological activities. In this paper, we propose\\na novel data augmentation technique that modifies the topology of the molecular\\ngraph to generate augmented data with the same molecular connectivity index as\\nthe original data. The molecular connectivity index combined with data\\naugmentation technology helps to retain more topology-based molecular\\nproperties information and generate more reliable data. Furthermore, we adopt\\nfive benchmark datasets to test our proposed models, and the results indicate\\nthat the augmented data generated based on important molecular topology\\nfeatures can effectively improve the prediction accuracy of molecular\\nproperties, which also provides a new perspective on data augmentation in\\ncheminformatics studies.\",\"PeriodicalId\":501325,\"journal\":{\"name\":\"arXiv - QuanBio - Molecular Networks\",\"volume\":\"16 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Molecular Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2401.03369\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Molecular Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2401.03369","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

近年来,机器学习在化学信息学问题中得到了快速发展。为了解决现实中训练数据不足的问题,越来越多的研究人员开始关注数据增强技术。然而,很少有研究人员关注数据的构造规则和领域信息问题,这将直接影响增强数据的质量和增强性能。在基于图谱的分子研究中,分子连通性指数作为一个关键的拓扑指标,可以直接或间接地反映基于拓扑的物理化学性质和生物活性。本文提出了一种新颖的数据增强技术,通过修改分子图的拓扑结构,生成与原始数据具有相同分子连通性指数的增强数据。分子连通性指数与数据增强技术相结合,有助于保留更多基于拓扑的分子特性信息,生成更可靠的数据。此外,我们采用了五个基准数据集来测试我们提出的模型,结果表明基于重要分子拓扑特征生成的增强数据能有效提高分子性质预测的准确性,这也为信息学研究中的数据增强提供了一个新的视角。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometry
Recent years have seen a rapid growth of machine learning in cheminformatics problems. In order to tackle the problem of insufficient training data in reality, more and more researchers pay attention to data augmentation technology. However, few researchers pay attention to the problem of construction rules and domain information of data, which will directly impact the quality of augmented data and the augmentation performance. While in graph-based molecular research, the molecular connectivity index, as a critical topological index, can directly or indirectly reflect the topology-based physicochemical properties and biological activities. In this paper, we propose a novel data augmentation technique that modifies the topology of the molecular graph to generate augmented data with the same molecular connectivity index as the original data. The molecular connectivity index combined with data augmentation technology helps to retain more topology-based molecular properties information and generate more reliable data. Furthermore, we adopt five benchmark datasets to test our proposed models, and the results indicate that the augmented data generated based on important molecular topology features can effectively improve the prediction accuracy of molecular properties, which also provides a new perspective on data augmentation in cheminformatics studies.
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
自引率
0.00%
发文量
0
期刊最新文献
Multi-variable control to mitigate loads in CRISPRa networks Some bounds on positive equilibria in mass action networks Non-explosivity of endotactic stochastic reaction systems Limits on the computational expressivity of non-equilibrium biophysical processes When lowering temperature, the in vivo circadian clock in cyanobacteria follows and surpasses the in vitro protein clock trough the Hopf bifurcation
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1