Cargando…

DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment

Drug treatment induces cell type specific transcriptional programs, and as the number of combinations of drugs and cell types grows, the cost for exhaustive screens measuring the transcriptional drug response becomes intractable. We developed DeepCellState, a deep learning autoencoder-based framewor...

Descripción completa

Detalles Bibliográficos
Autores principales: Umarov, Ramzan, Li, Yu, Arner, Erik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8519465/
https://www.ncbi.nlm.nih.gov/pubmed/34610009
http://dx.doi.org/10.1371/journal.pcbi.1009465
_version_ 1784584455889879040
author Umarov, Ramzan
Li, Yu
Arner, Erik
author_facet Umarov, Ramzan
Li, Yu
Arner, Erik
author_sort Umarov, Ramzan
collection PubMed
description Drug treatment induces cell type specific transcriptional programs, and as the number of combinations of drugs and cell types grows, the cost for exhaustive screens measuring the transcriptional drug response becomes intractable. We developed DeepCellState, a deep learning autoencoder-based framework, for predicting the induced transcriptional state in a cell type after drug treatment, based on the drug response in another cell type. Training the method on a large collection of transcriptional drug perturbation profiles, prediction accuracy improves significantly over baseline and alternative deep learning approaches when applying the method to two cell types, with improved accuracy when generalizing the framework to additional cell types. Treatments with drugs or whole drug families not seen during training are predicted with similar accuracy, and the same framework can be used for predicting the results from other interventions, such as gene knock-downs. Finally, analysis of the trained model shows that the internal representation is able to learn regulatory relationships between genes in a fully data-driven manner.
format Online
Article
Text
id pubmed-8519465
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-85194652021-10-16 DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment Umarov, Ramzan Li, Yu Arner, Erik PLoS Comput Biol Research Article Drug treatment induces cell type specific transcriptional programs, and as the number of combinations of drugs and cell types grows, the cost for exhaustive screens measuring the transcriptional drug response becomes intractable. We developed DeepCellState, a deep learning autoencoder-based framework, for predicting the induced transcriptional state in a cell type after drug treatment, based on the drug response in another cell type. Training the method on a large collection of transcriptional drug perturbation profiles, prediction accuracy improves significantly over baseline and alternative deep learning approaches when applying the method to two cell types, with improved accuracy when generalizing the framework to additional cell types. Treatments with drugs or whole drug families not seen during training are predicted with similar accuracy, and the same framework can be used for predicting the results from other interventions, such as gene knock-downs. Finally, analysis of the trained model shows that the internal representation is able to learn regulatory relationships between genes in a fully data-driven manner. Public Library of Science 2021-10-05 /pmc/articles/PMC8519465/ /pubmed/34610009 http://dx.doi.org/10.1371/journal.pcbi.1009465 Text en © 2021 Umarov et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Umarov, Ramzan
Li, Yu
Arner, Erik
DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title_full DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title_fullStr DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title_full_unstemmed DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title_short DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
title_sort deepcellstate: an autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8519465/
https://www.ncbi.nlm.nih.gov/pubmed/34610009
http://dx.doi.org/10.1371/journal.pcbi.1009465
work_keys_str_mv AT umarovramzan deepcellstateanautoencoderbasedframeworkforpredictingcelltypespecifictranscriptionalstatesinducedbydrugtreatment
AT liyu deepcellstateanautoencoderbasedframeworkforpredictingcelltypespecifictranscriptionalstatesinducedbydrugtreatment
AT arnererik deepcellstateanautoencoderbasedframeworkforpredictingcelltypespecifictranscriptionalstatesinducedbydrugtreatment