Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data

IntroductionThe combination of next-generation sequencing technology and Cancer Genome Atlas (TCGA) data provides unprecedented opportunities for the discovery of cancer subtypes. Through comprehensive analysis and in-depth analysis of the genomic data of a large number of cancer patients, researche...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Liu, Xinzheng Xue, Pengbo Wen, Qian Song, Jun Yao, Shuguang Ge
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-11-01
Series:Frontiers in Genetics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fgene.2024.1466825/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846168208537550848
author Jian Liu
Xinzheng Xue
Pengbo Wen
Qian Song
Jun Yao
Shuguang Ge
author_facet Jian Liu
Xinzheng Xue
Pengbo Wen
Qian Song
Jun Yao
Shuguang Ge
author_sort Jian Liu
collection DOAJ
description IntroductionThe combination of next-generation sequencing technology and Cancer Genome Atlas (TCGA) data provides unprecedented opportunities for the discovery of cancer subtypes. Through comprehensive analysis and in-depth analysis of the genomic data of a large number of cancer patients, researchers can more accurately identify different cancer subtypes and reveal their molecular heterogeneity.MethodsIn this paper, we propose the SMMSN (Self-supervised Multi-fusion Strategy Network) model for the discovery of cancer subtypes. SMMSN can not only fuse multi-level data representations of single omics data by Graph Convolutional Network (GCN) and Stacked Autoencoder Network (SAE), but also achieve the organic fusion of multi- -omics data through multiple fusion strategies. In response to the problem of lack label information in multi-omics data, SMMSN propose to use dual self-supervise method to cluster cancer subtypes from the integrated data.ResultsWe conducted experiments on three labeled and five unlabeled multi-omics datasets to distinguish potential cancer subtypes. Kaplan Meier survival curves and other results showed that SMMSN can obtain cancer subtypes with significant differences.DiscussionIn the case analysis of Glioblastoma Multiforme (GBM) and Breast Invasive Carcinoma (BIC), we conducted survival time and age distribution analysis, drug response analysis, differential expression analysis, functional enrichment analysis on the predicted cancer subtypes. The research results showed that SMMSN can discover clinically meaningful cancer subtypes.
format Article
id doaj-art-c838892bda594476aada3c9a637d5c05
institution Kabale University
issn 1664-8021
language English
publishDate 2024-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Genetics
spelling doaj-art-c838892bda594476aada3c9a637d5c052024-11-14T06:21:08ZengFrontiers Media S.A.Frontiers in Genetics1664-80212024-11-011510.3389/fgene.2024.14668251466825Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics dataJian Liu0Xinzheng Xue1Pengbo Wen2Qian Song3Jun Yao4Shuguang Ge5School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Information and Control Engineering, China University of Mining and Technology, Xuzhou, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, ChinaDepartment of Gynecology and Obstetrics, Taizhou Cancer Hospital, Wenling, ChinaDepartment of Colorectal Surgery, Taizhou Cancer Hospital, Wenling, ChinaSchool of Medical Information and Engineering, Xuzhou Medical University, Xuzhou, ChinaIntroductionThe combination of next-generation sequencing technology and Cancer Genome Atlas (TCGA) data provides unprecedented opportunities for the discovery of cancer subtypes. Through comprehensive analysis and in-depth analysis of the genomic data of a large number of cancer patients, researchers can more accurately identify different cancer subtypes and reveal their molecular heterogeneity.MethodsIn this paper, we propose the SMMSN (Self-supervised Multi-fusion Strategy Network) model for the discovery of cancer subtypes. SMMSN can not only fuse multi-level data representations of single omics data by Graph Convolutional Network (GCN) and Stacked Autoencoder Network (SAE), but also achieve the organic fusion of multi- -omics data through multiple fusion strategies. In response to the problem of lack label information in multi-omics data, SMMSN propose to use dual self-supervise method to cluster cancer subtypes from the integrated data.ResultsWe conducted experiments on three labeled and five unlabeled multi-omics datasets to distinguish potential cancer subtypes. Kaplan Meier survival curves and other results showed that SMMSN can obtain cancer subtypes with significant differences.DiscussionIn the case analysis of Glioblastoma Multiforme (GBM) and Breast Invasive Carcinoma (BIC), we conducted survival time and age distribution analysis, drug response analysis, differential expression analysis, functional enrichment analysis on the predicted cancer subtypes. The research results showed that SMMSN can discover clinically meaningful cancer subtypes.https://www.frontiersin.org/articles/10.3389/fgene.2024.1466825/fullcancer subtypes discoveringmulti-omics dataclusteringdeep learningfusion strategy
spellingShingle Jian Liu
Xinzheng Xue
Pengbo Wen
Qian Song
Jun Yao
Shuguang Ge
Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
Frontiers in Genetics
cancer subtypes discovering
multi-omics data
clustering
deep learning
fusion strategy
title Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
title_full Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
title_fullStr Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
title_full_unstemmed Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
title_short Multi-fusion strategy network-guided cancer subtypes discovering based on multi-omics data
title_sort multi fusion strategy network guided cancer subtypes discovering based on multi omics data
topic cancer subtypes discovering
multi-omics data
clustering
deep learning
fusion strategy
url https://www.frontiersin.org/articles/10.3389/fgene.2024.1466825/full
work_keys_str_mv AT jianliu multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata
AT xinzhengxue multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata
AT pengbowen multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata
AT qiansong multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata
AT junyao multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata
AT shuguangge multifusionstrategynetworkguidedcancersubtypesdiscoveringbasedonmultiomicsdata