Verifying explainability of a deep learning tissue classifier trained on RNA-seq data

Abstract For complex machine learning (ML) algorithms to gain widespread acceptance in decision making, we must be able to identify the features driving the predictions. Explainability models allow transparency of ML algorithms, however their reliability within high-dimensional data is unclear. To t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Melvyn Yap, Rebecca L. Johnston, Helena Foley, Samual MacDonald, Olga Kondrashova, Khoa A. Tran, Katia Nones, Lambros T. Koufariotis, Cameron Bean, John V. Pearson, Maciej Trzaskowski, Nicola Waddell
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1e3b3aca06414847b486a6e05de1d438
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1e3b3aca06414847b486a6e05de1d438
record_format	dspace
spelling	oai:doaj.org-article:1e3b3aca06414847b486a6e05de1d4382021-12-02T14:16:57ZVerifying explainability of a deep learning tissue classifier trained on RNA-seq data10.1038/s41598-021-81773-92045-2322https://doaj.org/article/1e3b3aca06414847b486a6e05de1d4382021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81773-9https://doaj.org/toc/2045-2322Abstract For complex machine learning (ML) algorithms to gain widespread acceptance in decision making, we must be able to identify the features driving the predictions. Explainability models allow transparency of ML algorithms, however their reliability within high-dimensional data is unclear. To test the reliability of the explainability model SHapley Additive exPlanations (SHAP), we developed a convolutional neural network to predict tissue classification from Genotype-Tissue Expression (GTEx) RNA-seq data representing 16,651 samples from 47 tissues. Our classifier achieved an average F1 score of 96.1% on held-out GTEx samples. Using SHAP values, we identified the 2423 most discriminatory genes, of which 98.6% were also identified by differential expression analysis across all tissues. The SHAP genes reflected expected biological processes involved in tissue differentiation and function. Moreover, SHAP genes clustered tissue types with superior performance when compared to all genes, genes detected by differential expression analysis, or random genes. We demonstrate the utility and reliability of SHAP to explain a deep learning model and highlight the strengths of applying ML to transcriptome data.Melvyn YapRebecca L. JohnstonHelena FoleySamual MacDonaldOlga KondrashovaKhoa A. TranKatia NonesLambros T. KoufariotisCameron BeanJohn V. PearsonMaciej TrzaskowskiNicola WaddellNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Melvyn Yap Rebecca L. Johnston Helena Foley Samual MacDonald Olga Kondrashova Khoa A. Tran Katia Nones Lambros T. Koufariotis Cameron Bean John V. Pearson Maciej Trzaskowski Nicola Waddell Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
description	Abstract For complex machine learning (ML) algorithms to gain widespread acceptance in decision making, we must be able to identify the features driving the predictions. Explainability models allow transparency of ML algorithms, however their reliability within high-dimensional data is unclear. To test the reliability of the explainability model SHapley Additive exPlanations (SHAP), we developed a convolutional neural network to predict tissue classification from Genotype-Tissue Expression (GTEx) RNA-seq data representing 16,651 samples from 47 tissues. Our classifier achieved an average F1 score of 96.1% on held-out GTEx samples. Using SHAP values, we identified the 2423 most discriminatory genes, of which 98.6% were also identified by differential expression analysis across all tissues. The SHAP genes reflected expected biological processes involved in tissue differentiation and function. Moreover, SHAP genes clustered tissue types with superior performance when compared to all genes, genes detected by differential expression analysis, or random genes. We demonstrate the utility and reliability of SHAP to explain a deep learning model and highlight the strengths of applying ML to transcriptome data.
format	article
author	Melvyn Yap Rebecca L. Johnston Helena Foley Samual MacDonald Olga Kondrashova Khoa A. Tran Katia Nones Lambros T. Koufariotis Cameron Bean John V. Pearson Maciej Trzaskowski Nicola Waddell
author_facet	Melvyn Yap Rebecca L. Johnston Helena Foley Samual MacDonald Olga Kondrashova Khoa A. Tran Katia Nones Lambros T. Koufariotis Cameron Bean John V. Pearson Maciej Trzaskowski Nicola Waddell
author_sort	Melvyn Yap
title	Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
title_short	Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
title_full	Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
title_fullStr	Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
title_full_unstemmed	Verifying explainability of a deep learning tissue classifier trained on RNA-seq data
title_sort	verifying explainability of a deep learning tissue classifier trained on rna-seq data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1e3b3aca06414847b486a6e05de1d438
work_keys_str_mv	AT melvynyap verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT rebeccaljohnston verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT helenafoley verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT samualmacdonald verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT olgakondrashova verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT khoaatran verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT katianones verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT lambrostkoufariotis verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT cameronbean verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT johnvpearson verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT maciejtrzaskowski verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata AT nicolawaddell verifyingexplainabilityofadeeplearningtissueclassifiertrainedonrnaseqdata
_version_	1718391653318787072

Verifying explainability of a deep learning tissue classifier trained on RNA-seq data

Ejemplares similares