Predictive and robust gene selection for spatial transcriptomics.
Predictive and robust gene selection for spatial transcriptomics.
复制标题
用于空间转录组学的预测性和鲁棒性基因选择。
DOI：
10.1038/s41467-023-37392-1
复制
发表时间：
2023-04-12
影响因子：
16.6
通讯作者：
Lee, Su-In
中科院分区：
文献类型：
--
作者：
Covert, Ian;Gala, Rohan;Wang, Tim;Svoboda, Karel;Sumbul, Uygar;Lee, Su-In
单细胞转录组学的一个突出趋势是提供空间背景以及每个细胞的分子状态的表征。这通常需要针对基因的先验选择，通常覆盖不到1%的基因组，一个关键问题是如何最佳地确定小基因面板。我们通过引入灵活的深度学习框架PERSIST来解决这一挑战，通过参考scRNA-seq数据来确定空间转录组学研究的信息性基因靶点。使用跨越不同大脑区域、物种和scRNA-seq技术的数据集，我们发现PERSIST可靠地识别出能够提供更准确的全基因组表达谱预测的面板，从而用更少的基因捕获更多的信息。PERSIST可以适应特定的生物学目标，尽管这些技术之间存在复杂的转换，但我们证明PERSIST的基因表达水平二值化使基于scRNA-seq数据训练的模型能够推广到空间转录组学数据。空间转录组学的基因选择目前还不是最理想的。在这里，作者报告了PERSIST，这是一个灵活的深度学习框架，使用现有的scRNA-seq数据来识别空间转录组学的基因靶标；他们表明，这可以让你用更少的基因获取更多的信息。
A prominent trend in single-cell transcriptomics is providing spatial context alongside a characterization of each cell’s molecular state. This typically requires targeting an a priori selection of genes, often covering less than 1% of the genome, and a key question is how to optimally determine the small gene panel. We address this challenge by introducing a flexible deep learning framework, PERSIST, to identify informative gene targets for spatial transcriptomics studies by leveraging reference scRNA-seq data. Using datasets spanning different brain regions, species, and scRNA-seq technologies, we show that PERSIST reliably identifies panels that provide more accurate prediction of the genome-wide expression profile, thereby capturing more information with fewer genes. PERSIST can be adapted to specific biological goals, and we demonstrate that PERSIST’s binarization of gene expression levels enables models trained on scRNA-seq data to generalize with to spatial transcriptomics data, despite the complex shift between these technologies. Gene selection for spatial transcriptomics is currently not optimal. Here the authors report PERSIST, a flexible deep learning framework that uses existing scRNA-seq data to identify gene targets for spatial transcriptomics; they show this allows you to capture more information with fewer genes.
登录
查看更多内容
影响因子：
9.8
作者：
Harris KD;Hochgerner H;Skene NG;Magno L;Katona L;Bengtsson Gonzales C;Somogyi P;Kessaris N;Linnarsson S;Hjerling-Leffler J
通讯作者：
Hjerling-Leffler J
影响因子：
48
作者：
Amodio, Matthew;van Dijk, David;Srinivasan, Krishnan;Chen, William S.;Mohsen, Hussein;Moon, Kevin R.;Campbell, Allison;Zhao, Yujiao;Wang, Xiaomei;Venkataswamy, Manjunatha;Desai, Anita;Ravi, V.;Kumar, Priti;Montgomery, Ruth;Wolf, Guy;Krishnaswamy, Smita
通讯作者：
Krishnaswamy, Smita
影响因子：
56.9
作者：
Femino, A;Fay, FS;Singer, RH
通讯作者：
Singer, RH
影响因子：
64.5
作者：
Gouwens NW;Sorensen SA;Baftizadeh F;Budzillo A;Lee BR;Jarsky T;Alfiler L;Baker K;Barkan E;Berry K;Bertagnolli D;Bickley K;Bomben J;Braun T;Brouner K;Casper T;Crichton K;Daigle TL;Dalley R;de Frates RA;Dee N;Desta T;Lee SD;Dotson N;Egdorf T;Ellingwood L;Enstrom R;Esposito L;Farrell C;Feng D;Fong O;Gala R;Gamlin C;Gary A;Glandon A;Goldy J;Gorham M;Graybuck L;Gu H;Hadley K;Hawrylycz MJ;Henry AM;Hill D;Hupp M;Kebede S;Kim TK;Kim L;Kroll M;Lee C;Link KE;Mallory M;Mann R;Maxwell M;McGraw M;McMillen D;Mukora A;Ng L;Ng L;Ngo K;Nicovich PR;Oldre A;Park D;Peng H;Penn O;Pham T;Pom A;Popović Z;Potekhina L;Rajanbabu R;Ransford S;Reid D;Rimorin C;Robertson M;Ronellenfitch K;Ruiz A;Sandman D;Smith K;Sulc J;Sunkin SM;Szafer A;Tieu M;Torkelson A;Trinh J;Tung H;Wakeman W;Ward K;Williams G;Zhou Z;Ting JT;Arkhipov A;Sümbül U;Lein ES;Koch C;Yao Z;Tasic B;Berg J;Murphy GJ;Zeng H
通讯作者：
Zeng H
影响因子：
48
作者：
Codeluppi, Simone;Borm, Lars E.;Linnarsson, Sten
通讯作者：
Linnarsson, Sten