Cargando…

Genomic pan-cancer classification using image-based deep learning

Accurate cancer type classification based on genetic mutation can significantly facilitate cancer-related diagnosis. However, existing methods usually use feature selection combined with simple classifiers to quantify key mutated genes, resulting in poor classification performance. To circumvent thi...

Descripción completa

Detalles Bibliográficos
Autores principales: Ye, Taoyu, Li, Sen, Zhang, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Research Network of Computational and Structural Biotechnology 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7848437/
https://www.ncbi.nlm.nih.gov/pubmed/33598099
http://dx.doi.org/10.1016/j.csbj.2021.01.010
_version_ 1783645136610131968
author Ye, Taoyu
Li, Sen
Zhang, Yang
author_facet Ye, Taoyu
Li, Sen
Zhang, Yang
author_sort Ye, Taoyu
collection PubMed
description Accurate cancer type classification based on genetic mutation can significantly facilitate cancer-related diagnosis. However, existing methods usually use feature selection combined with simple classifiers to quantify key mutated genes, resulting in poor classification performance. To circumvent this problem, a novel image-based deep learning strategy is employed to distinguish different types of cancer. Unlike conventional methods, we first convert gene mutation data containing single nucleotide polymorphisms, insertions and deletions into a genetic mutation map, and then apply the deep learning networks to classify different cancer types based on the mutation map. We outline these methods and present results obtained in training VGG-16, Inception-v3, ResNet-50 and Inception-ResNet-v2 neural networks to classify 36 types of cancer from 9047 patient samples. Our approach achieves overall higher accuracy (over 95%) compared with other widely adopted classification methods. Furthermore, we demonstrate the application of a Guided Grad-CAM visualization to generate heatmaps and identify the top-ranked tumor-type-specific genes and pathways. Experimental results on prostate and breast cancer demonstrate our method can be applied to various types of cancer. Powered by the deep learning, this approach can potentially provide a new solution for pan-cancer classification and cancer driver gene discovery. The source code and datasets supporting the study is available at https://github.com/yetaoyu/Genomic-pan-cancer-classification.
format Online
Article
Text
id pubmed-7848437
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Research Network of Computational and Structural Biotechnology
record_format MEDLINE/PubMed
spelling pubmed-78484372021-02-16 Genomic pan-cancer classification using image-based deep learning Ye, Taoyu Li, Sen Zhang, Yang Comput Struct Biotechnol J Research Article Accurate cancer type classification based on genetic mutation can significantly facilitate cancer-related diagnosis. However, existing methods usually use feature selection combined with simple classifiers to quantify key mutated genes, resulting in poor classification performance. To circumvent this problem, a novel image-based deep learning strategy is employed to distinguish different types of cancer. Unlike conventional methods, we first convert gene mutation data containing single nucleotide polymorphisms, insertions and deletions into a genetic mutation map, and then apply the deep learning networks to classify different cancer types based on the mutation map. We outline these methods and present results obtained in training VGG-16, Inception-v3, ResNet-50 and Inception-ResNet-v2 neural networks to classify 36 types of cancer from 9047 patient samples. Our approach achieves overall higher accuracy (over 95%) compared with other widely adopted classification methods. Furthermore, we demonstrate the application of a Guided Grad-CAM visualization to generate heatmaps and identify the top-ranked tumor-type-specific genes and pathways. Experimental results on prostate and breast cancer demonstrate our method can be applied to various types of cancer. Powered by the deep learning, this approach can potentially provide a new solution for pan-cancer classification and cancer driver gene discovery. The source code and datasets supporting the study is available at https://github.com/yetaoyu/Genomic-pan-cancer-classification. Research Network of Computational and Structural Biotechnology 2021-01-15 /pmc/articles/PMC7848437/ /pubmed/33598099 http://dx.doi.org/10.1016/j.csbj.2021.01.010 Text en © 2021 The Author(s) http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Research Article
Ye, Taoyu
Li, Sen
Zhang, Yang
Genomic pan-cancer classification using image-based deep learning
title Genomic pan-cancer classification using image-based deep learning
title_full Genomic pan-cancer classification using image-based deep learning
title_fullStr Genomic pan-cancer classification using image-based deep learning
title_full_unstemmed Genomic pan-cancer classification using image-based deep learning
title_short Genomic pan-cancer classification using image-based deep learning
title_sort genomic pan-cancer classification using image-based deep learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7848437/
https://www.ncbi.nlm.nih.gov/pubmed/33598099
http://dx.doi.org/10.1016/j.csbj.2021.01.010
work_keys_str_mv AT yetaoyu genomicpancancerclassificationusingimagebaseddeeplearning
AT lisen genomicpancancerclassificationusingimagebaseddeeplearning
AT zhangyang genomicpancancerclassificationusingimagebaseddeeplearning