Sampling and ranking spatial transcriptomics data embeddings to identify tissue architecture.

Sampling and ranking spatial transcriptomics data embeddings to identify tissue architecture.
复制标题

DOI:
10.3389/fgene.2022.912813
复制
发表时间:
2022
影响因子:
3.7
通讯作者:
--
中科院分区:
生物学3区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

空间转录组学是一门新兴的技术,广泛应用于组织结构和生物功能的分析。大量的计算方法已经被开发用于分析空间转录组学数据。这些方法从基因表达和空间位置生成嵌入,用于点聚类或组织结构分割。虽然用于生成嵌入的超参数可以针对给定的训练集进行调整,但由于数据分布的原因,固定嵌入的性能会因情况而异。因此,提前为新数据选择有效的嵌入将是有用的。为此,我们开发了一种嵌入评价方法命名为消息传递-莫兰的我与最大过滤(MP-MIM),它结合了基于消息传递的嵌入变换与空间自相关分析。我们应用图形卷积来聚合空间转录组学数据,并采用全局Moran's I来测量空间自相关并选择最有效的嵌入来推断组织结构。从人脑中产生的16个空间转录组学样本被用来验证我们的方法。结果表明,MP-MIM可以准确地识别出高质量的嵌入,这些嵌入在预测的组织结构和地面实况之间产生高度相关性。总的来说,我们的研究提供了一种新的方法来为新的测试数据选择嵌入,并增强深度学习工具在空间转录组分析中的可用性。
Spatial transcriptomics is an emerging technology widely applied to the analyses of tissue architecture and corresponding biological functions. Substantial computational methods have been developed for analyzing spatial transcriptomics data. These methods generate embeddings from gene expression and spatial locations for spot clustering or tissue architecture segmentation. Although the hyperparameters used to produce an embedding can be tuned for a given training set, a fixed embedding has variable performance from case to case due to data distributions. Therefore, selecting an effective embedding for new data in advance would be useful. For this purpose, we developed an embedding evaluation method named message passing-Moran’s I with maximum filtering (MP-MIM), which combines message passing-based embedding transformation with spatial autocorrelation analysis. We applied a graph convolution to aggregate spatial transcriptomics data and employed global Moran’s I to measure spatial autocorrelation and select the most effective embedding to infer tissue architecture. Sixteen spatial transcriptomics samples generated from the human brain were used to validate our method. The results show that MP-MIM can accurately identify high-quality embeddings that produce a high correlation between the predicted tissue architecture and the ground truth. Overall, our study provides a novel method to select embeddings for new test data and enhance the usability of deep learning tools for spatial transcriptome analyses.
DOI: 10.1038/s41593-020-00787-0
发表时间: 2021-03
影响因子: 25
作者:
Maynard KR;Collado-Torres L;Weber LM;Uytingco C;Barry BK;Williams SR;Catallini JL 2nd;Tran MN;Besich Z;Tippani M;Chew J;Yin Y;Kleinman JE;Hyde TM;Rao N;Hicks SC;Martinowich K;Jaffe AE
通讯作者: Jaffe AE
DOI: 10.1016/j.cell.2019.11.025
发表时间: 2019-12-12
期刊: CELL
影响因子: 64.5
作者:
Asp, Michaela;Giacomello, Stefania;Lundeberg, Joakim
通讯作者: Lundeberg, Joakim
DOI: 10.1080/01431160412331331012
发表时间: 2005-04-01
影响因子: 3.4
作者:
Lee, S
通讯作者: Lee, S
DOI: 10.1126/science.aaf2403
发表时间: 2016-07-01
期刊: SCIENCE
影响因子: 56.9
作者:
Stahl, Patrik L.;Salmen, Fredrik;Frisen, Jonas
通讯作者: Frisen, Jonas
DOI: 10.1038/nmeth.4636
发表时间: 2018-05
期刊: Nature methods
影响因子: 48
作者:
Svensson V;Teichmann SA;Stegle O
通讯作者: Stegle O