Cargando…

Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations

BACKGROUND: Unsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice, most re...

Descripción completa

Detalles Bibliográficos
Autores principales: Way, Gregory P., Zietz, Michael, Rubinetti, Vincent, Himmelstein, Daniel S., Greene, Casey S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7212571/
https://www.ncbi.nlm.nih.gov/pubmed/32393369
http://dx.doi.org/10.1186/s13059-020-02021-3
_version_ 1783531643750842368
author Way, Gregory P.
Zietz, Michael
Rubinetti, Vincent
Himmelstein, Daniel S.
Greene, Casey S.
author_facet Way, Gregory P.
Zietz, Michael
Rubinetti, Vincent
Himmelstein, Daniel S.
Greene, Casey S.
author_sort Way, Gregory P.
collection PubMed
description BACKGROUND: Unsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice, most researchers fit a single algorithm and latent dimensionality. We sought to determine the extent by which selecting only one fit limits the biological features captured in the latent representations and, consequently, limits what can be discovered with subsequent analyses. RESULTS: We compress gene expression data from three large datasets consisting of adult normal tissue, adult cancer tissue, and pediatric cancer tissue. We train many different models across a large range of latent space dimensionalities and observe various performance differences. We identify more curated pathway gene sets significantly associated with individual dimensions in denoising autoencoder and variational autoencoder models trained using an intermediate number of latent dimensionalities. Combining compressed features across algorithms and dimensionalities captures the most pathway-associated representations. When trained with different latent dimensionalities, models learn strongly associated and generalizable biological representations including sex, neuroblastoma MYCN amplification, and cell types. Stronger signals, such as tumor type, are best captured in models trained at lower dimensionalities, while more subtle signals such as pathway activity are best identified in models trained with more latent dimensionalities. CONCLUSIONS: There is no single best latent dimensionality or compression algorithm for analyzing gene expression data. Instead, using features derived from different compression models across multiple latent space dimensionalities enhances biological representations.
format Online
Article
Text
id pubmed-7212571
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-72125712020-05-18 Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations Way, Gregory P. Zietz, Michael Rubinetti, Vincent Himmelstein, Daniel S. Greene, Casey S. Genome Biol Research BACKGROUND: Unsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice, most researchers fit a single algorithm and latent dimensionality. We sought to determine the extent by which selecting only one fit limits the biological features captured in the latent representations and, consequently, limits what can be discovered with subsequent analyses. RESULTS: We compress gene expression data from three large datasets consisting of adult normal tissue, adult cancer tissue, and pediatric cancer tissue. We train many different models across a large range of latent space dimensionalities and observe various performance differences. We identify more curated pathway gene sets significantly associated with individual dimensions in denoising autoencoder and variational autoencoder models trained using an intermediate number of latent dimensionalities. Combining compressed features across algorithms and dimensionalities captures the most pathway-associated representations. When trained with different latent dimensionalities, models learn strongly associated and generalizable biological representations including sex, neuroblastoma MYCN amplification, and cell types. Stronger signals, such as tumor type, are best captured in models trained at lower dimensionalities, while more subtle signals such as pathway activity are best identified in models trained with more latent dimensionalities. CONCLUSIONS: There is no single best latent dimensionality or compression algorithm for analyzing gene expression data. Instead, using features derived from different compression models across multiple latent space dimensionalities enhances biological representations. BioMed Central 2020-05-11 /pmc/articles/PMC7212571/ /pubmed/32393369 http://dx.doi.org/10.1186/s13059-020-02021-3 Text en © The Author(s) 2020 Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
spellingShingle Research
Way, Gregory P.
Zietz, Michael
Rubinetti, Vincent
Himmelstein, Daniel S.
Greene, Casey S.
Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title_full Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title_fullStr Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title_full_unstemmed Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title_short Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
title_sort compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7212571/
https://www.ncbi.nlm.nih.gov/pubmed/32393369
http://dx.doi.org/10.1186/s13059-020-02021-3
work_keys_str_mv AT waygregoryp compressinggeneexpressiondatausingmultiplelatentspacedimensionalitieslearnscomplementarybiologicalrepresentations
AT zietzmichael compressinggeneexpressiondatausingmultiplelatentspacedimensionalitieslearnscomplementarybiologicalrepresentations
AT rubinettivincent compressinggeneexpressiondatausingmultiplelatentspacedimensionalitieslearnscomplementarybiologicalrepresentations
AT himmelsteindaniels compressinggeneexpressiondatausingmultiplelatentspacedimensionalitieslearnscomplementarybiologicalrepresentations
AT greenecaseys compressinggeneexpressiondatausingmultiplelatentspacedimensionalitieslearnscomplementarybiologicalrepresentations