Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector Journal Article


Authors: Ceglia, N.; Sethna, Z.; Freeman, S. S.; Uhlitz, F.; Bojilova, V.; Rusk, N.; Burman, B.; Chow, A.; Salehi, S.; Kabeer, F.; Aparicio, S.; Greenbaum, B. D.; Shah, S. P.; McPherson, A.
Article Title: Identification of transcriptional programs using dense vector representations defined by mutual information with GeneVector
Abstract: 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. © 2023, The Author(s).
Keywords: phenotype; gene expression; genetic transcription; rna; vector; signal; principal component analysis; dimensionality reduction; embedding; article; arithmetic; single cell rna seq; autoencoder; aggregate
Journal Title: Nature Communications
Volume: 14
ISSN: 2041-1723
Publisher: Nature Publishing Group  
Date Published: 2023-07-20
Start Page: 4400
Language: English
DOI: 10.1038/s41467-023-39985-2
PUBMED: 37474509
PROVIDER: scopus
PMCID: PMC10359421
DOI/URL:
Notes: Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Nicholas Ceglia -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Sohrab Prakash Shah
    88 Shah
  2. Andrew Chow
    45 Chow
  3. Nicholas Ceglia
    23 Ceglia
  4. Zachary Michael Sethna
    15 Sethna
  5. Bharat Burman
    13 Burman
  6. Nicole Rusk
    11 Rusk
  7. Florian Soeren Uhlitz
    6 Uhlitz
  8. Sohrab Salehi
    9 Salehi