Deep learning-based cell composition analysis from tissue expression profiles
Standard
Deep learning-based cell composition analysis from tissue expression profiles. / Menden, Kevin; Marouf, Mohamed; Oller, Sergio; Dalmia, Anupriya; Magruder, Daniel Sumner; Kloiber, Karin; Heutink, Peter; Bonn, Stefan.
In: SCI ADV, Vol. 6, No. 30, 22.07.2020, p. eaba2619.Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Deep learning-based cell composition analysis from tissue expression profiles
AU - Menden, Kevin
AU - Marouf, Mohamed
AU - Oller, Sergio
AU - Dalmia, Anupriya
AU - Magruder, Daniel Sumner
AU - Kloiber, Karin
AU - Heutink, Peter
AU - Bonn, Stefan
N1 - Copyright © 2020 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution NonCommercial License 4.0 (CC BY-NC).
PY - 2020/7/22
Y1 - 2020/7/22
N2 - We present Scaden, a deep neural network for cell deconvolution that uses gene expression information to infer the cellular composition of tissues. Scaden is trained on single-cell RNA sequencing (RNA-seq) data to engineer discriminative features that confer robustness to bias and noise, making complex data preprocessing and feature selection unnecessary. We demonstrate that Scaden outperforms existing deconvolution algorithms in both precision and robustness. A single trained network reliably deconvolves bulk RNA-seq and microarray, human and mouse tissue expression data and leverages the combined information of multiple datasets. Because of this stability and flexibility, we surmise that deep learning will become an algorithmic mainstay for cell deconvolution of various data types. Scaden's software package and web application are easy to use on new as well as diverse existing expression datasets available in public resources, deepening the molecular and cellular understanding of developmental and disease processes.
AB - We present Scaden, a deep neural network for cell deconvolution that uses gene expression information to infer the cellular composition of tissues. Scaden is trained on single-cell RNA sequencing (RNA-seq) data to engineer discriminative features that confer robustness to bias and noise, making complex data preprocessing and feature selection unnecessary. We demonstrate that Scaden outperforms existing deconvolution algorithms in both precision and robustness. A single trained network reliably deconvolves bulk RNA-seq and microarray, human and mouse tissue expression data and leverages the combined information of multiple datasets. Because of this stability and flexibility, we surmise that deep learning will become an algorithmic mainstay for cell deconvolution of various data types. Scaden's software package and web application are easy to use on new as well as diverse existing expression datasets available in public resources, deepening the molecular and cellular understanding of developmental and disease processes.
U2 - 10.1126/sciadv.aba2619
DO - 10.1126/sciadv.aba2619
M3 - SCORING: Journal article
C2 - 32832661
VL - 6
SP - eaba2619
JO - SCI ADV
JF - SCI ADV
SN - 2375-2548
IS - 30
ER -