RT Journal Article SR Electronic T1 Deep-learning-based cell composition analysis from tissue expression profiles JF bioRxiv FD Cold Spring Harbor Laboratory SP 659227 DO 10.1101/659227 A1 Kevin Menden A1 Mohamed Marouf A1 Anupriya Dalmia A1 Peter Heutink A1 Stefan Bonn YR 2019 UL http://biorxiv.org/content/early/2019/07/16/659227.abstract 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-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, across tissues and species. A single trained network reliably deconvolves bulk RNA-seq and microarray, human and mouse tissue expression data. Due to this stability and flexibility, we surmise that deep learning-based cell deconvolution will become a mainstay across data types and algorithmic approaches. Scaden’s comprehensive software package is easy to use on novel as well as diverse existing expression datasets available in public resources, deepening the molecular and cellular understanding of developmental and disease processes.RNA-seqNext Generation RNA SequencingGEPgene expression profile matrixSVRSupport Vector RegressionDNNDeep Neural NetworkscRNA-seqsingle cell RNA-seqsimulated tissuetraining data generated by mixing proportions of scRNA-seq dataPBMCperipheral blood mononuclear cellsCCCconcordance correlation coefficientrPearson’s correlation coefficientCSCIBERSORTCSxCIBERSORTxCPMCell Population Mapping