Cargando…
Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects
Many biological data acquisition platforms suffer from inadvertent inclusion of biologically irrelevant variance in analyzed data, collectively termed batch effects. Batch effects can lead to difficulties in downstream analysis by lowering the power to detect biologically interesting differences and...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6386283/ https://www.ncbi.nlm.nih.gov/pubmed/30794641 http://dx.doi.org/10.1371/journal.pone.0212669 |
_version_ | 1783397353055584256 |
---|---|
author | Gradin, Robin Lindstedt, Malin Johansson, Henrik |
author_facet | Gradin, Robin Lindstedt, Malin Johansson, Henrik |
author_sort | Gradin, Robin |
collection | PubMed |
description | Many biological data acquisition platforms suffer from inadvertent inclusion of biologically irrelevant variance in analyzed data, collectively termed batch effects. Batch effects can lead to difficulties in downstream analysis by lowering the power to detect biologically interesting differences and can in certain instances lead to false discoveries. They are especially troublesome in predictive modelling where samples in training sets and test sets are often completely correlated with batches. In this article, we present BARA, a normalization method for adjusting batch effects in predictive modelling. BARA utilizes a few reference samples to adjust for batch effects in a compressed data space spanned by the training set. We evaluate BARA using a collection of publicly available datasets and three different prediction models, and compare its performance to already existing methods developed for similar purposes. The results show that data normalized with BARA generates high and consistent prediction performances. Further, they suggest that BARA produces reliable performances independent of the examined classifiers. We therefore conclude that BARA has great potential to facilitate the development of predictive assays where test sets and training sets are correlated with batch. |
format | Online Article Text |
id | pubmed-6386283 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-63862832019-03-09 Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects Gradin, Robin Lindstedt, Malin Johansson, Henrik PLoS One Research Article Many biological data acquisition platforms suffer from inadvertent inclusion of biologically irrelevant variance in analyzed data, collectively termed batch effects. Batch effects can lead to difficulties in downstream analysis by lowering the power to detect biologically interesting differences and can in certain instances lead to false discoveries. They are especially troublesome in predictive modelling where samples in training sets and test sets are often completely correlated with batches. In this article, we present BARA, a normalization method for adjusting batch effects in predictive modelling. BARA utilizes a few reference samples to adjust for batch effects in a compressed data space spanned by the training set. We evaluate BARA using a collection of publicly available datasets and three different prediction models, and compare its performance to already existing methods developed for similar purposes. The results show that data normalized with BARA generates high and consistent prediction performances. Further, they suggest that BARA produces reliable performances independent of the examined classifiers. We therefore conclude that BARA has great potential to facilitate the development of predictive assays where test sets and training sets are correlated with batch. Public Library of Science 2019-02-22 /pmc/articles/PMC6386283/ /pubmed/30794641 http://dx.doi.org/10.1371/journal.pone.0212669 Text en © 2019 Gradin et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://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 Gradin, Robin Lindstedt, Malin Johansson, Henrik Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title | Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title_full | Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title_fullStr | Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title_full_unstemmed | Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title_short | Batch adjustment by reference alignment (BARA): Improved prediction performance in biological test sets with batch effects |
title_sort | batch adjustment by reference alignment (bara): improved prediction performance in biological test sets with batch effects |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6386283/ https://www.ncbi.nlm.nih.gov/pubmed/30794641 http://dx.doi.org/10.1371/journal.pone.0212669 |
work_keys_str_mv | AT gradinrobin batchadjustmentbyreferencealignmentbaraimprovedpredictionperformanceinbiologicaltestsetswithbatcheffects AT lindstedtmalin batchadjustmentbyreferencealignmentbaraimprovedpredictionperformanceinbiologicaltestsetswithbatcheffects AT johanssonhenrik batchadjustmentbyreferencealignmentbaraimprovedpredictionperformanceinbiologicaltestsetswithbatcheffects |