TY - JOUR
T1 - Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector
AU - Ceglia, Nicholas
AU - Sethna, Zachary
AU - Freeman, Samuel S.
AU - Uhlitz, Florian
AU - Bojilova, Viktoria
AU - Rusk, Nicole
AU - Burman, Bharat
AU - Chow, Andrew
AU - Salehi, Sohrab
AU - Kabeer, Farhia
AU - Aparicio, Samuel
AU - Greenbaum, Benjamin D.
AU - Shah, Sohrab P.
AU - McPherson, Andrew
N1 - Publisher Copyright:
© 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85165411286&partnerID=8YFLogxK
U2 - 10.1038/s41467-023-39985-2
DO - 10.1038/s41467-023-39985-2
M3 - Article
C2 - 37474509
AN - SCOPUS:85165411286
SN - 2041-1723
VL - 14
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 4400
ER -