人工智能空间分辨转录组学揭示多种肿瘤的空间组织结构

Tumor discovery Pub Date : 2024-03-06 DOI:10.36922/td.2049
Teng Liu, Jinxin Ye, Chunnan Hu, Zongbo Zhang, Zhuomiao Ye, Jiangnan Liao, Mingzhu Yin
{"title":"人工智能空间分辨转录组学揭示多种肿瘤的空间组织结构","authors":"Teng Liu, Jinxin Ye, Chunnan Hu, Zongbo Zhang, Zhuomiao Ye, Jiangnan Liao, Mingzhu Yin","doi":"10.36922/td.2049","DOIUrl":null,"url":null,"abstract":"Spatially resolved transcriptomics was honored as the Method of the Year 2020 by Nature Methods. This approach allows biologists to precisely discern mRNA expression at the cellular level within structurally preserved tissues. Leveraging artificial intelligence in spatial transcriptomic analysis enhances the understanding of cellular-level biological interactions and offers novel insights into intricate tissues, such as tumor microenvironments. Nevertheless, numerous existing clustering algorithms employing deep learning exhibit the potential for enhancement. In this paper, we focus on graph deep learning-based spatial domain identification for spatial transcriptomics (ST) data from multiple tumors. This identification enables the recognition of cell subpopulations in distinct spatial coordinates, aiding further studies on tumor progression, such as cell-cell communication, pseudo-time trajectory inference, and single-cell deconvolution. Initially, the gene expression profiles and spatial location information were transformed into a gene feature matrix and a cell adjacency matrix. A variational graph autoencoder was then applied to extract features and reduce the dimensions of these two matrices. Following training in the constructed graph neural networks, the latent embeddings of ST data were generated and could be leveraged for spatial domain identification. Through a comparison with established methods, our approach demonstrated superior clustering accuracy. The utilization of accurately segmented spatial regions enables downstream analyses of multiple tumors, encompassing the trajectory of tumor evolution, and facilitating differential gene expression analysis across various cell types.","PeriodicalId":94260,"journal":{"name":"Tumor discovery","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Artificial intelligence enabled spatially resolved transcriptomics reveal spatial tissue organization of multiple tumors\",\"authors\":\"Teng Liu, Jinxin Ye, Chunnan Hu, Zongbo Zhang, Zhuomiao Ye, Jiangnan Liao, Mingzhu Yin\",\"doi\":\"10.36922/td.2049\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spatially resolved transcriptomics was honored as the Method of the Year 2020 by Nature Methods. This approach allows biologists to precisely discern mRNA expression at the cellular level within structurally preserved tissues. Leveraging artificial intelligence in spatial transcriptomic analysis enhances the understanding of cellular-level biological interactions and offers novel insights into intricate tissues, such as tumor microenvironments. Nevertheless, numerous existing clustering algorithms employing deep learning exhibit the potential for enhancement. In this paper, we focus on graph deep learning-based spatial domain identification for spatial transcriptomics (ST) data from multiple tumors. This identification enables the recognition of cell subpopulations in distinct spatial coordinates, aiding further studies on tumor progression, such as cell-cell communication, pseudo-time trajectory inference, and single-cell deconvolution. Initially, the gene expression profiles and spatial location information were transformed into a gene feature matrix and a cell adjacency matrix. A variational graph autoencoder was then applied to extract features and reduce the dimensions of these two matrices. Following training in the constructed graph neural networks, the latent embeddings of ST data were generated and could be leveraged for spatial domain identification. Through a comparison with established methods, our approach demonstrated superior clustering accuracy. The utilization of accurately segmented spatial regions enables downstream analyses of multiple tumors, encompassing the trajectory of tumor evolution, and facilitating differential gene expression analysis across various cell types.\",\"PeriodicalId\":94260,\"journal\":{\"name\":\"Tumor discovery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Tumor discovery\",\"FirstCategoryId\":\"0\",\"ListUrlMain\":\"https://doi.org/10.36922/td.2049\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Tumor discovery","FirstCategoryId":"0","ListUrlMain":"https://doi.org/10.36922/td.2049","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

空间解析转录组学被《自然-方法》杂志评为 "2020 年度方法"。这种方法使生物学家能够在结构保存完好的组织内精确地辨别细胞水平的 mRNA 表达。在空间转录组学分析中利用人工智能,可以增强对细胞水平生物相互作用的理解,并提供对复杂组织(如肿瘤微环境)的新见解。然而,现有的许多采用深度学习的聚类算法都显示出了改进的潜力。在本文中,我们重点研究了基于图深度学习的空间域识别,用于识别来自多个肿瘤的空间转录组学(ST)数据。这种识别可以识别不同空间坐标上的细胞亚群,有助于进一步研究肿瘤进展,如细胞-细胞通讯、伪时间轨迹推断和单细胞解卷积。最初,基因表达谱和空间位置信息被转化为基因特征矩阵和细胞邻接矩阵。然后应用变异图自动编码器提取特征并降低这两个矩阵的维度。在对构建的图神经网络进行训练后,ST 数据的潜在嵌入就生成了,并可用于空间域识别。通过与已有方法的比较,我们的方法显示出更高的聚类精度。利用准确分割的空间区域可以对多个肿瘤进行下游分析,涵盖肿瘤演变的轨迹,并有助于对各种细胞类型进行差异基因表达分析。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Artificial intelligence enabled spatially resolved transcriptomics reveal spatial tissue organization of multiple tumors
Spatially resolved transcriptomics was honored as the Method of the Year 2020 by Nature Methods. This approach allows biologists to precisely discern mRNA expression at the cellular level within structurally preserved tissues. Leveraging artificial intelligence in spatial transcriptomic analysis enhances the understanding of cellular-level biological interactions and offers novel insights into intricate tissues, such as tumor microenvironments. Nevertheless, numerous existing clustering algorithms employing deep learning exhibit the potential for enhancement. In this paper, we focus on graph deep learning-based spatial domain identification for spatial transcriptomics (ST) data from multiple tumors. This identification enables the recognition of cell subpopulations in distinct spatial coordinates, aiding further studies on tumor progression, such as cell-cell communication, pseudo-time trajectory inference, and single-cell deconvolution. Initially, the gene expression profiles and spatial location information were transformed into a gene feature matrix and a cell adjacency matrix. A variational graph autoencoder was then applied to extract features and reduce the dimensions of these two matrices. Following training in the constructed graph neural networks, the latent embeddings of ST data were generated and could be leveraged for spatial domain identification. Through a comparison with established methods, our approach demonstrated superior clustering accuracy. The utilization of accurately segmented spatial regions enables downstream analyses of multiple tumors, encompassing the trajectory of tumor evolution, and facilitating differential gene expression analysis across various cell types.
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
×
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