Cargando…

Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer

Established prognostic tests based on limited numbers of transcripts can identify high-risk breast cancer patients, yet are approved only for individuals presenting with specific clinical features or disease characteristics. Deep learning algorithms could hold potential for stratifying patient cohor...

Descripción completa

Detalles Bibliográficos
Autores principales: Guttà, Cristiano, Morhard, Christoph, Rehm, Markus
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10101642/
https://www.ncbi.nlm.nih.gov/pubmed/37011102
http://dx.doi.org/10.1371/journal.pcbi.1011035
_version_ 1785025552572219392
author Guttà, Cristiano
Morhard, Christoph
Rehm, Markus
author_facet Guttà, Cristiano
Morhard, Christoph
Rehm, Markus
author_sort Guttà, Cristiano
collection PubMed
description Established prognostic tests based on limited numbers of transcripts can identify high-risk breast cancer patients, yet are approved only for individuals presenting with specific clinical features or disease characteristics. Deep learning algorithms could hold potential for stratifying patient cohorts based on full transcriptome data, yet the development of robust classifiers is hampered by the number of variables in omics datasets typically far exceeding the number of patients. To overcome this hurdle, we propose a classifier based on a data augmentation pipeline consisting of a Wasserstein generative adversarial network (GAN) with gradient penalty and an embedded auxiliary classifier to obtain a trained GAN discriminator (T-GAN-D). Applied to 1244 patients of the METABRIC breast cancer cohort, this classifier outperformed established breast cancer biomarkers in separating low- from high-risk patients (disease specific death, progression or relapse within 10 years from initial diagnosis). Importantly, the T-GAN-D also performed across independent, merged transcriptome datasets (METABRIC and TCGA-BRCA cohorts), and merging data improved overall patient stratification. In conclusion, the reiterative GAN-based training process allowed generating a robust classifier capable of stratifying low- vs high-risk patients based on full transcriptome data and across independent and heterogeneous breast cancer cohorts.
format Online
Article
Text
id pubmed-10101642
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-101016422023-04-14 Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer Guttà, Cristiano Morhard, Christoph Rehm, Markus PLoS Comput Biol Research Article Established prognostic tests based on limited numbers of transcripts can identify high-risk breast cancer patients, yet are approved only for individuals presenting with specific clinical features or disease characteristics. Deep learning algorithms could hold potential for stratifying patient cohorts based on full transcriptome data, yet the development of robust classifiers is hampered by the number of variables in omics datasets typically far exceeding the number of patients. To overcome this hurdle, we propose a classifier based on a data augmentation pipeline consisting of a Wasserstein generative adversarial network (GAN) with gradient penalty and an embedded auxiliary classifier to obtain a trained GAN discriminator (T-GAN-D). Applied to 1244 patients of the METABRIC breast cancer cohort, this classifier outperformed established breast cancer biomarkers in separating low- from high-risk patients (disease specific death, progression or relapse within 10 years from initial diagnosis). Importantly, the T-GAN-D also performed across independent, merged transcriptome datasets (METABRIC and TCGA-BRCA cohorts), and merging data improved overall patient stratification. In conclusion, the reiterative GAN-based training process allowed generating a robust classifier capable of stratifying low- vs high-risk patients based on full transcriptome data and across independent and heterogeneous breast cancer cohorts. Public Library of Science 2023-04-03 /pmc/articles/PMC10101642/ /pubmed/37011102 http://dx.doi.org/10.1371/journal.pcbi.1011035 Text en © 2023 Guttà 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
Guttà, Cristiano
Morhard, Christoph
Rehm, Markus
Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title_full Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title_fullStr Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title_full_unstemmed Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title_short Applying a GAN-based classifier to improve transcriptome-based prognostication in breast cancer
title_sort applying a gan-based classifier to improve transcriptome-based prognostication in breast cancer
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10101642/
https://www.ncbi.nlm.nih.gov/pubmed/37011102
http://dx.doi.org/10.1371/journal.pcbi.1011035
work_keys_str_mv AT guttacristiano applyingaganbasedclassifiertoimprovetranscriptomebasedprognosticationinbreastcancer
AT morhardchristoph applyingaganbasedclassifiertoimprovetranscriptomebasedprognosticationinbreastcancer
AT rehmmarkus applyingaganbasedclassifiertoimprovetranscriptomebasedprognosticationinbreastcancer