FAVA: High-quality functional association networks inferred from scRNA-seq and proteomics data
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
FAVA : High-quality functional association networks inferred from scRNA-seq and proteomics data. / Koutrouli, Mikaela; Nastou, Katerina; Piera Líndez, Pau; Bouwmeester, Robbin; Rasmussen, Simon; Martens, Lennart; Jensen, Lars Juhl.
In: Bioinformatics, Vol. 40, No. 2, btae010, 2024.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - FAVA
T2 - High-quality functional association networks inferred from scRNA-seq and proteomics data
AU - Koutrouli, Mikaela
AU - Nastou, Katerina
AU - Piera Líndez, Pau
AU - Bouwmeester, Robbin
AU - Rasmussen, Simon
AU - Martens, Lennart
AU - Jensen, Lars Juhl
N1 - Publisher Copyright: © 2024 The Author(s). Published by Oxford University Press.
PY - 2024
Y1 - 2024
N2 - Motivation: Protein networks are commonly used for understanding how proteins interact. However, they are typically biased by data availability, favoring well-studied proteins with more interactions. To uncover functions of understudied proteins, we must use data that are not affected by this literature bias, such as single-cell RNA-seq and proteomics. Due to data sparseness and redundancy, functional association analysis becomes complex. Results: To address this, we have developed FAVA (Functional Associations using Variational Autoencoders), which compresses high-dimensional data into a low-dimensional space. FAVA infers networks from high-dimensional omics data with much higher accuracy than existing methods, across a diverse collection of real as well as simulated datasets. FAVA can process large datasets with over 0.5 million conditions and has predicted 4210 interactions between 1039 understudied proteins. Our findings showcase FAVA's capability to offer novel perspectives on protein interactions. FAVA functions within the scverse ecosystem, employing AnnData as its input source.
AB - Motivation: Protein networks are commonly used for understanding how proteins interact. However, they are typically biased by data availability, favoring well-studied proteins with more interactions. To uncover functions of understudied proteins, we must use data that are not affected by this literature bias, such as single-cell RNA-seq and proteomics. Due to data sparseness and redundancy, functional association analysis becomes complex. Results: To address this, we have developed FAVA (Functional Associations using Variational Autoencoders), which compresses high-dimensional data into a low-dimensional space. FAVA infers networks from high-dimensional omics data with much higher accuracy than existing methods, across a diverse collection of real as well as simulated datasets. FAVA can process large datasets with over 0.5 million conditions and has predicted 4210 interactions between 1039 understudied proteins. Our findings showcase FAVA's capability to offer novel perspectives on protein interactions. FAVA functions within the scverse ecosystem, employing AnnData as its input source.
U2 - 10.1093/bioinformatics/btae010
DO - 10.1093/bioinformatics/btae010
M3 - Journal article
C2 - 38192003
AN - SCOPUS:85184480522
VL - 40
JO - Bioinformatics (Online)
JF - Bioinformatics (Online)
SN - 1367-4811
IS - 2
M1 - btae010
ER -
ID: 383092029