Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector.
Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector.
复制标题
DOI：
10.1038/s41467-023-39985-2
复制
发表时间：
2023-07-20
影响因子：
16.6
通讯作者：
McPherson, Andrew
中科院分区：
文献类型：
--
作者：
Ceglia, Nicholas;Sethna, Zachary;Freeman, Samuel S.;Uhlitz, Florian;Bojilova, Viktoria;Rusk, Nicole;Burman, Bharat;Chow, Andrew;Salehi, Sohrab;Kabeer, Farhia;Aparicio, Samuel;Greenbaum, Benjamin D.;Shah, Sohrab P.;McPherson, Andrew
从细胞特有的转录过程中破译单个细胞的表型需要高维的单细胞RNA测序。然而，目前的降维方法跨细胞聚合稀疏的基因信息，没有直接测量基因之间存在的关系。通过对基因共表达进行降维，低维特征可以对这些基因特有的关系进行建模，并利用共享信号来克服稀疏性。我们描述了GeneVector，一个可扩展的降维框架，利用基因表达之间的互信息实现了一个向量空间模型。与包括主成分分析和变分自动编码器在内的其他方法不同，GeneVector在低维基因嵌入中使用潜在空间算法来识别转录程序和分类细胞类型。在这项工作中，我们在四个单细胞RNA-seq数据集中展示了GeneVector能够捕获表型特定的途径，执行批量效应校正，交互地注释细胞类型，并识别随着时间的推移治疗的途径变化。在单细胞RNA序列分析中，测量基因之间的关系将是至关重要的。在这里，作者开发了一个单细胞降维框架，该框架结合了基因特有的关系-基因矢量-，并将其用于诸如注释细胞类型和分析治疗后的路径变化等任务。
Deciphering individual cell phenotypes from cell-specific transcriptional processes requires high dimensional single cell RNA sequencing. However, current dimensionality reduction methods aggregate sparse gene information across cells, without directly measuring the relationships that exist between genes. By performing dimensionality reduction with respect to gene co-expression, low-dimensional features can model these gene-specific relationships and leverage shared signal to overcome sparsity. We describe GeneVector, a scalable framework for dimensionality reduction implemented as a vector space model using mutual information between gene expression. Unlike other methods, including principal component analysis and variational autoencoders, GeneVector uses latent space arithmetic in a lower dimensional gene embedding to identify transcriptional programs and classify cell types. In this work, we show in four single cell RNA-seq datasets that GeneVector was able to capture phenotype-specific pathways, perform batch effect correction, interactively annotate cell types, and identify pathway variation with treatment over time. In single-cell RNA-seq analyses, it would be critical to measure the relationships between genes. Here, the authors develop a framework for single-cell dimensionality reduction that incorporates gene-specific relationships - GeneVector -, and use it for tasks such as annotating cell types and analysing pathway variation after treatment.
登录
查看更多内容
影响因子：
5.8
作者：
Liberzon, Arthur;Subramanian, Aravind;Mesirov, Jill P.
通讯作者：
Mesirov, Jill P.
DOI：
10.1093/bioinformatics/btw216
发表时间：
2016-07-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Lachmann A;Giorgi FM;Lopez G;Califano A
通讯作者：
Califano A
影响因子：
14.9
作者：
Kuleshov MV;Jones MR;Rouillard AD;Fernandez NF;Duan Q;Wang Z;Koplev S;Jenkins SL;Jagodnik KM;Lachmann A;McDermott MG;Monteiro CD;Gundersen GW;Ma'ayan A
通讯作者：
Ma'ayan A
DOI：
10.1126/science.abl5197
发表时间：
2022-05-13
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Domínguez Conde C;Xu C;Jarvis LB;Rainbow DB;Wells SB;Gomes T;Howlett SK;Suchanek O;Polanski K;King HW;Mamanova L;Huang N;Szabo PA;Richardson L;Bolt L;Fasouli ES;Mahbubani KT;Prete M;Tuck L;Richoz N;Tuong ZK;Campos L;Mousa HS;Needham EJ;Pritchard S;Li T;Elmentaite R;Park J;Rahmani E;Chen D;Menon DK;Bayraktar OA;James LK;Meyer KB;Yosef N;Clatworthy MR;Sims PA;Farber DL;Saeb-Parsy K;Jones JL;Teichmann SA
通讯作者：
Teichmann SA
基因表达谱分析识别上皮性卵巢癌细胞中的转移和化疗耐药相关基因
DOI：
10.1007/s12032-014-0426-5
发表时间：
2015-01
期刊：
Medical oncology (Northwood, London, England)
影响因子：
--
作者：
Zhu L;Hu Z;Liu J;Gao J;Lin B
通讯作者：
Lin B