N-of-one differential gene expression without control samples using a deep generative model
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
N-of-one differential gene expression without control samples using a deep generative model. / Prada-Luengo, Iñigo; Schuster, Viktoria; Liang, Yuhu; Terkelsen, Thilde; Sora, Valentina; Krogh, Anders.
In: Genome Biology, Vol. 24, No. 1, 263, 2023.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - N-of-one differential gene expression without control samples using a deep generative model
AU - Prada-Luengo, Iñigo
AU - Schuster, Viktoria
AU - Liang, Yuhu
AU - Terkelsen, Thilde
AU - Sora, Valentina
AU - Krogh, Anders
N1 - Publisher Copyright: © 2023, The Author(s).
PY - 2023
Y1 - 2023
N2 - Differential analysis of bulk RNA-seq data often suffers from lack of good controls. Here, we present a generative model that replaces controls, trained solely on healthy tissues. The unsupervised model learns a low-dimensional representation and can identify the closest normal representation for a given disease sample. This enables control-free, single-sample differential expression analysis. In breast cancer, we demonstrate how our approach selects marker genes and outperforms a state-of-the-art method. Furthermore, significant genes identified by the model are enriched in driver genes across cancers. Our results show that the in silico closest normal provides a more favorable comparison than control samples.
AB - Differential analysis of bulk RNA-seq data often suffers from lack of good controls. Here, we present a generative model that replaces controls, trained solely on healthy tissues. The unsupervised model learns a low-dimensional representation and can identify the closest normal representation for a given disease sample. This enables control-free, single-sample differential expression analysis. In breast cancer, we demonstrate how our approach selects marker genes and outperforms a state-of-the-art method. Furthermore, significant genes identified by the model are enriched in driver genes across cancers. Our results show that the in silico closest normal provides a more favorable comparison than control samples.
KW - Deep generative models
KW - Deep learning
KW - DEG
KW - DEseq2
KW - Differential expression analysis
KW - Transcriptomics
UR - http://www.scopus.com/inward/record.url?scp=85177077909&partnerID=8YFLogxK
U2 - 10.1186/s13059-023-03104-7
DO - 10.1186/s13059-023-03104-7
M3 - Journal article
C2 - 37974217
AN - SCOPUS:85177077909
VL - 24
JO - Genome Biology (Online Edition)
JF - Genome Biology (Online Edition)
SN - 1474-7596
IS - 1
M1 - 263
ER -
ID: 374645010