Cargando…
Deep learning–based cell composition analysis from tissue expression profiles
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 comp...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Association for the Advancement of Science
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7439569/ https://www.ncbi.nlm.nih.gov/pubmed/32832661 http://dx.doi.org/10.1126/sciadv.aba2619 |
_version_ | 1783573008787439616 |
---|---|
author | Menden, Kevin Marouf, Mohamed Oller, Sergio Dalmia, Anupriya Magruder, Daniel Sumner Kloiber, Karin Heutink, Peter Bonn, Stefan |
author_facet | Menden, Kevin Marouf, Mohamed Oller, Sergio Dalmia, Anupriya Magruder, Daniel Sumner Kloiber, Karin Heutink, Peter Bonn, Stefan |
author_sort | Menden, Kevin |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-7439569 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | American Association for the Advancement of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-74395692020-08-20 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 Sci Adv Research Articles 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. American Association for the Advancement of Science 2020-07-22 /pmc/articles/PMC7439569/ /pubmed/32832661 http://dx.doi.org/10.1126/sciadv.aba2619 Text en 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). https://creativecommons.org/licenses/by-nc/4.0/ https://creativecommons.org/licenses/by-nc/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution-NonCommercial license (https://creativecommons.org/licenses/by-nc/4.0/) , which permits use, distribution, and reproduction in any medium, so long as the resultant use is not for commercial advantage and provided the original work is properly cited. |
spellingShingle | Research Articles Menden, Kevin Marouf, Mohamed Oller, Sergio Dalmia, Anupriya Magruder, Daniel Sumner Kloiber, Karin Heutink, Peter Bonn, Stefan Deep learning–based cell composition analysis from tissue expression profiles |
title | Deep learning–based cell composition analysis from tissue expression profiles |
title_full | Deep learning–based cell composition analysis from tissue expression profiles |
title_fullStr | Deep learning–based cell composition analysis from tissue expression profiles |
title_full_unstemmed | Deep learning–based cell composition analysis from tissue expression profiles |
title_short | Deep learning–based cell composition analysis from tissue expression profiles |
title_sort | deep learning–based cell composition analysis from tissue expression profiles |
topic | Research Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7439569/ https://www.ncbi.nlm.nih.gov/pubmed/32832661 http://dx.doi.org/10.1126/sciadv.aba2619 |
work_keys_str_mv | AT mendenkevin deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT maroufmohamed deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT ollersergio deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT dalmiaanupriya deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT magruderdanielsumner deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT kloiberkarin deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT heutinkpeter deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles AT bonnstefan deeplearningbasedcellcompositionanalysisfromtissueexpressionprofiles |