Survival prediction in patients with colon adenocarcinoma via multi-omics data integration using a deep learning algorithm

This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Bioscience reports
Hlavní autoři: Lv, Jiudi, Wang, Junjie, Shang, Xiujuan, Liu, Fangfang, Guo, Shixun
Médium: Journal Article
Jazyk:angličtina
Vydáno: England 01.12.2020
Témata:
ISSN:1573-4935, 1573-4935
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with COAD. The autoencoder framework was compared to PCA, NMF, t-SNE, and univariable Cox-PH model for identifying survival-related features. The prognostic robustness of the inferred survival risk groups was validated using three independent confirmation cohorts. Differential expression analysis, Pearson's correlation analysis, construction of miRNA-target gene network, and function enrichment analysis were performed. Two risk groups with significant survival differences were identified in TCGA set using the autoencoder-based model (log-rank p-value = 5.51e-07). The autoencoder framework showed superior performance compared to PCA, NMF, t-SNE, and the univariable Cox-PH model based on the C-index, log-rank p-value, and Brier score. The robustness of the classification model was successfully verified in three independent validation sets. There were 1271 differentially expressed genes, 10 differentially expressed miRNAs, and 12 hypermethylated genes between the survival risk groups. Among these, miR-133b and its target genes (GNB4, PTPRZ1, RUNX1T1, EPHA7, GPM6A, BICC1, and ADAMTS5) were used to construct a network. These genes were significantly enriched in ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, and glucose metabolism-related pathways. The risk subgroups obtained through a multi-omics data integration pipeline using the DL algorithm had good robustness. miR-133b and its target genes could be potential diagnostic markers. The results would assist in elucidating the possible pathogenesis of COAD.
AbstractList This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with COAD. The autoencoder framework was compared to PCA, NMF, t-SNE, and univariable Cox-PH model for identifying survival-related features. The prognostic robustness of the inferred survival risk groups was validated using three independent confirmation cohorts. Differential expression analysis, Pearson's correlation analysis, construction of miRNA-target gene network, and function enrichment analysis were performed. Two risk groups with significant survival differences were identified in TCGA set using the autoencoder-based model (log-rank p-value = 5.51e-07). The autoencoder framework showed superior performance compared to PCA, NMF, t-SNE, and the univariable Cox-PH model based on the C-index, log-rank p-value, and Brier score. The robustness of the classification model was successfully verified in three independent validation sets. There were 1271 differentially expressed genes, 10 differentially expressed miRNAs, and 12 hypermethylated genes between the survival risk groups. Among these, miR-133b and its target genes (GNB4, PTPRZ1, RUNX1T1, EPHA7, GPM6A, BICC1, and ADAMTS5) were used to construct a network. These genes were significantly enriched in ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, and glucose metabolism-related pathways. The risk subgroups obtained through a multi-omics data integration pipeline using the DL algorithm had good robustness. miR-133b and its target genes could be potential diagnostic markers. The results would assist in elucidating the possible pathogenesis of COAD.
This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with COAD. The autoencoder framework was compared to PCA, NMF, t-SNE, and univariable Cox-PH model for identifying survival-related features. The prognostic robustness of the inferred survival risk groups was validated using three independent confirmation cohorts. Differential expression analysis, Pearson's correlation analysis, construction of miRNA-target gene network, and function enrichment analysis were performed. Two risk groups with significant survival differences were identified in TCGA set using the autoencoder-based model (log-rank p-value = 5.51e-07). The autoencoder framework showed superior performance compared to PCA, NMF, t-SNE, and the univariable Cox-PH model based on the C-index, log-rank p-value, and Brier score. The robustness of the classification model was successfully verified in three independent validation sets. There were 1271 differentially expressed genes, 10 differentially expressed miRNAs, and 12 hypermethylated genes between the survival risk groups. Among these, miR-133b and its target genes (GNB4, PTPRZ1, RUNX1T1, EPHA7, GPM6A, BICC1, and ADAMTS5) were used to construct a network. These genes were significantly enriched in ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, and glucose metabolism-related pathways. The risk subgroups obtained through a multi-omics data integration pipeline using the DL algorithm had good robustness. miR-133b and its target genes could be potential diagnostic markers. The results would assist in elucidating the possible pathogenesis of COAD.This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The survival-sensitive model was constructed using an autoencoder for DL implementation based on The Cancer Genome Atlas (TCGA) data of patients with COAD. The autoencoder framework was compared to PCA, NMF, t-SNE, and univariable Cox-PH model for identifying survival-related features. The prognostic robustness of the inferred survival risk groups was validated using three independent confirmation cohorts. Differential expression analysis, Pearson's correlation analysis, construction of miRNA-target gene network, and function enrichment analysis were performed. Two risk groups with significant survival differences were identified in TCGA set using the autoencoder-based model (log-rank p-value = 5.51e-07). The autoencoder framework showed superior performance compared to PCA, NMF, t-SNE, and the univariable Cox-PH model based on the C-index, log-rank p-value, and Brier score. The robustness of the classification model was successfully verified in three independent validation sets. There were 1271 differentially expressed genes, 10 differentially expressed miRNAs, and 12 hypermethylated genes between the survival risk groups. Among these, miR-133b and its target genes (GNB4, PTPRZ1, RUNX1T1, EPHA7, GPM6A, BICC1, and ADAMTS5) were used to construct a network. These genes were significantly enriched in ECM-receptor interaction, focal adhesion, PI3K-Akt signaling pathway, and glucose metabolism-related pathways. The risk subgroups obtained through a multi-omics data integration pipeline using the DL algorithm had good robustness. miR-133b and its target genes could be potential diagnostic markers. The results would assist in elucidating the possible pathogenesis of COAD.
Author Lv, Jiudi
Liu, Fangfang
Guo, Shixun
Shang, Xiujuan
Wang, Junjie
Author_xml – sequence: 1
  givenname: Jiudi
  surname: Lv
  fullname: Lv, Jiudi
  organization: Xinxiang Central Hospital, Xinxiang, China
– sequence: 2
  givenname: Junjie
  surname: Wang
  fullname: Wang, Junjie
  organization: Xinxiang Central Hospital, Xinxiang, China
– sequence: 3
  givenname: Xiujuan
  surname: Shang
  fullname: Shang, Xiujuan
  organization: Xinxiang Central Hospital, Xinxiang, China
– sequence: 4
  givenname: Fangfang
  surname: Liu
  fullname: Liu, Fangfang
  organization: Xinxiang Central Hospital, Xinxiang, China
– sequence: 5
  givenname: Shixun
  surname: Guo
  fullname: Guo, Shixun
  organization: Xinxiang Central Hospital, Xinxiang, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33258470$$D View this record in MEDLINE/PubMed
BookMark eNpNkEtPwzAQhC1URB9w4o585BJw_EiTI1S8pEpItPdo42yLUWIH2ymCX08oReK0M6OZ77BTMrLOIiHnKbtKmeTXt6sXzjhLZc6PyCRVc5HIQqjRPz0m0xDeGGODkSdkLARXuZyzCfla9X5ndtDQzmNtdDTOUmNpB9GgjYF-mPhKtWuGGGq0ToPXxroW6M4AbfsmmsS1RgdaQ4RhGnHrYY_pg7FbCrRG7GiD4O3eN1vnB2h7So430AQ8O9wZWd_frRePyfL54Wlxs0w6lbFEg8qZqFhW55UslC5SVfFMzXXOK6mFyAWi3swBCkzrFAsGqGUOkKWbLM-04DNy-YvtvHvvMcSyNUFj04BF14eSyyxjQgn5U704VPuqxbrsvGnBf5Z_7-LfSr9wFw
ContentType Journal Article
Copyright Copyright 2020 The Author(s).
Copyright_xml – notice: Copyright 2020 The Author(s).
DBID NPM
7X8
DOI 10.1042/BSR20201482
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Chemistry
Biology
EISSN 1573-4935
ExternalDocumentID 33258470
Genre Journal Article
GroupedDBID ---
.86
0R~
23N
4.4
5GY
5RE
5VS
6J9
78A
7X7
AAHRG
ABJNI
ABUWG
ACGFS
ACIWK
ACPRK
ADBBV
ADIMF
AEGXH
AENEX
AFBBN
AFRAH
AGIHE
AHBYD
ALMA_UNASSIGNED_HOLDINGS
AOIJS
ATCPS
BAWUL
BCNDV
BENPR
BGNMA
CS3
DIK
DL5
DU5
E3Z
EBD
EBS
EMOBN
EPAXT
F5P
FRP
GX1
H13
HCIFZ
HYE
HZ~
I09
IZQ
KDC
KQ8
LAK
M2O
M2P
M48
M4Y
MV1
NPM
NU0
O9-
OK1
OVD
QOK
QOS
R4E
RHI
RNS
RPM
RPO
RPX
RRX
SBL
SDH
SDM
SOJ
SV3
TR2
TSK
U2A
VC2
~EX
7X8
PYCSY
ID FETCH-LOGICAL-p560-ca5803b06d8b495c915b2657c82b4c3383eecf7aa9e1d1e90aec48aa61f686c32
IEDL.DBID 7X8
ISSN 1573-4935
IngestDate Thu Jul 10 23:42:13 EDT 2025
Sun Nov 09 08:39:27 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords deep learning
multi-omics data
miRNA
methylation
Language English
License Copyright 2020 The Author(s).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-p560-ca5803b06d8b495c915b2657c82b4c3383eecf7aa9e1d1e90aec48aa61f686c32
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 33258470
PQID 2466035343
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2466035343
pubmed_primary_33258470
PublicationCentury 2000
PublicationDate 2020-Dec-01
20201201
PublicationDateYYYYMMDD 2020-12-01
PublicationDate_xml – month: 12
  year: 2020
  text: 2020-Dec-01
  day: 01
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Bioscience reports
PublicationTitleAlternate Biosci Rep
PublicationYear 2020
SSID ssj0004934
Score 2.2597075
Snippet This study proposed a deep learning (DL) algorithm to predict survival in patients with colon adenocarcinoma (COAD) based on multi-omics integration. The...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
Title Survival prediction in patients with colon adenocarcinoma via multi-omics data integration using a deep learning algorithm
URI https://www.ncbi.nlm.nih.gov/pubmed/33258470
https://www.proquest.com/docview/2466035343
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF7UKnrxUV_1xQpel6bZzeskWiwetBTbQ29lsrutAZvGpi3or3emSdGLIHgJySHLsjM7882bsZvYBa0iCARC0VAoVCkCpGfEUMcACDc8VRQKPwXtdtjvR53S4ZaXaZUrmbgU1GaiyUded5XvO9KTSt5m74KmRlF0tRyhsc4qEqEMXcyg_6NbeFRElb1ACnz3yvo85NP6ffcFzX5yp7m_Y8uljmnt_Xd3-2y3RJf8rmCHA7Zm0yrbKuZNflTZdnM13u2QfXbnKCWQz3g2pWANEYgnKS8breacPLScelqnHFA4oc6b6iSdjIEvEuDLRERBJc05pyxTvuo7QctQMv2IAzfWZrycS4HfbyPc8ux1fMR6rYde81GUgxhEhoBIaPBCR8aOb8IY7SkdNbzY9b1Ah26sNNm41uphABDZhmnYyAGrVQjgN4Z-6GvpHrONdJLaU8aNBkcGOvbBARVoA5bsHVzQGCXR1Kyx69X5DvA8KHgBqZ3M88H3CdfYSUGkQVY05BhI6VK01zn7w9_nbIcIX2SkXLDKEG-5vWSbejFL8unVkoHw2e48fwFNVtLA
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Survival+prediction+in+patients+with+colon+adenocarcinoma+via+multi-omics+data+integration+using+a+deep+learning+algorithm&rft.jtitle=Bioscience+reports&rft.au=Lv%2C+Jiudi&rft.au=Wang%2C+Junjie&rft.au=Shang%2C+Xiujuan&rft.au=Liu%2C+Fangfang&rft.date=2020-12-01&rft.issn=1573-4935&rft.eissn=1573-4935&rft_id=info:doi/10.1042%2FBSR20201482&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1573-4935&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1573-4935&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1573-4935&client=summon