Aligned deep neural network for integrative analysis with high-dimensional input

Deep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis has been conducted on data with high-dimensional input such as omics measurements. In such analysis, regularization, in particular penalizati...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of biomedical informatics Ročník 144; s. 104434
Hlavní autoři: Zhang, Shunqin, Zhang, Sanguo, Yi, Huangdi, Ma, Shuangge
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 01.08.2023
Témata:
ISSN:1532-0480, 1532-0480
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Deep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis has been conducted on data with high-dimensional input such as omics measurements. In such analysis, regularization, in particular penalization, has been applied to regularize estimation and distinguish relevant input variables from irrelevant ones. A unique challenge arises from the "lack of information" attributable to high dimensionality of input and limited size of training data. For many data/studies, there exist other data/studies that may be relevant and can potentially provide additional information to boost performance. In this study, we conduct integrative analysis of multiple independent datasets/studies, with the goal of borrowing information across each other and improving overall performance. Significantly different from regression-based integrative analysis (where alignment can be easily achieved based on covariates), alignment across multiple DNNs can be nontrivial. We develop ANNI, an Aligned DNN technique for Integrative analysis with high-dimensional input. Penalization is applied for regularized estimation, selection of important input variables, and, equally importantly, information borrowing across multiple DNNs. An effective computational algorithm is developed. Extensive simulations demonstrate competitive performance of the proposed technique. The analysis of cancer omics data further establishes its practical utility.
AbstractList Deep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis has been conducted on data with high-dimensional input such as omics measurements. In such analysis, regularization, in particular penalization, has been applied to regularize estimation and distinguish relevant input variables from irrelevant ones. A unique challenge arises from the "lack of information" attributable to high dimensionality of input and limited size of training data. For many data/studies, there exist other data/studies that may be relevant and can potentially provide additional information to boost performance. In this study, we conduct integrative analysis of multiple independent datasets/studies, with the goal of borrowing information across each other and improving overall performance. Significantly different from regression-based integrative analysis (where alignment can be easily achieved based on covariates), alignment across multiple DNNs can be nontrivial. We develop ANNI, an Aligned DNN technique for Integrative analysis with high-dimensional input. Penalization is applied for regularized estimation, selection of important input variables, and, equally importantly, information borrowing across multiple DNNs. An effective computational algorithm is developed. Extensive simulations demonstrate competitive performance of the proposed technique. The analysis of cancer omics data further establishes its practical utility.
Deep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis has been conducted on data with high-dimensional input such as omics measurements. In such analysis, regularization, in particular penalization, has been applied to regularize estimation and distinguish relevant input variables from irrelevant ones. A unique challenge arises from the "lack of information" attributable to high dimensionality of input and limited size of training data. For many data/studies, there exist other data/studies that may be relevant and can potentially provide additional information to boost performance.OBJECTIVEDeep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis has been conducted on data with high-dimensional input such as omics measurements. In such analysis, regularization, in particular penalization, has been applied to regularize estimation and distinguish relevant input variables from irrelevant ones. A unique challenge arises from the "lack of information" attributable to high dimensionality of input and limited size of training data. For many data/studies, there exist other data/studies that may be relevant and can potentially provide additional information to boost performance.In this study, we conduct integrative analysis of multiple independent datasets/studies, with the goal of borrowing information across each other and improving overall performance. Significantly different from regression-based integrative analysis (where alignment can be easily achieved based on covariates), alignment across multiple DNNs can be nontrivial. We develop ANNI, an Aligned DNN technique for Integrative analysis with high-dimensional input. Penalization is applied for regularized estimation, selection of important input variables, and, equally importantly, information borrowing across multiple DNNs. An effective computational algorithm is developed.METHODSIn this study, we conduct integrative analysis of multiple independent datasets/studies, with the goal of borrowing information across each other and improving overall performance. Significantly different from regression-based integrative analysis (where alignment can be easily achieved based on covariates), alignment across multiple DNNs can be nontrivial. We develop ANNI, an Aligned DNN technique for Integrative analysis with high-dimensional input. Penalization is applied for regularized estimation, selection of important input variables, and, equally importantly, information borrowing across multiple DNNs. An effective computational algorithm is developed.Extensive simulations demonstrate competitive performance of the proposed technique. The analysis of cancer omics data further establishes its practical utility.RESULTSExtensive simulations demonstrate competitive performance of the proposed technique. The analysis of cancer omics data further establishes its practical utility.
Author Yi, Huangdi
Zhang, Sanguo
Zhang, Shunqin
Ma, Shuangge
Author_xml – sequence: 1
  givenname: Shunqin
  surname: Zhang
  fullname: Zhang, Shunqin
  organization: School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China; Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China; Department of Biostatistics, Yale University, New Haven, CT, USA
– sequence: 2
  givenname: Sanguo
  surname: Zhang
  fullname: Zhang, Sanguo
  organization: School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China; Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China
– sequence: 3
  givenname: Huangdi
  surname: Yi
  fullname: Yi, Huangdi
  organization: Department of Biostatistics, Yale University, New Haven, CT, USA
– sequence: 4
  givenname: Shuangge
  surname: Ma
  fullname: Ma, Shuangge
  email: shuangge.ma@yale.edu
  organization: Department of Biostatistics, Yale University, New Haven, CT, USA. Electronic address: shuangge.ma@yale.edu
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37391115$$D View this record in MEDLINE/PubMed
BookMark eNpNkD1PwzAYhC1URD_gB7Agjywp_qyTsaooIFWCAebIjd-0LokTbIeq_x5LFInp7nSPbrgpGrnOAUK3lMwpoYuHw_ywtXNGGE9ZCC4u0IRKzjIicjL658doGsKBEEqlXFyhMVe8oClM0NuysTsHBhuAHjsYvG6SxGPnP3HdeWxdhJ3X0X4D1k43p2ADPtq4x3u722fGtuCC7VKT0H6I1-iy1k2Am7PO0Mf68X31nG1en15Wy01WCcliVuVMky2ta6ULKgUxsjILDUoUTGlRJ880lywnSuWpoloqZSSvwTAhjAY2Q_e_u73vvgYIsWxtqKBptINuCCXLOZMq50WR0LszOmxbMGXvbav9qfx7gf0A1qZiJw
CitedBy_id crossref_primary_10_1007_s40846_024_00859_7
crossref_primary_10_1002_sim_70226
ContentType Journal Article
Copyright Copyright © 2023 Elsevier Inc. All rights reserved.
Copyright_xml – notice: Copyright © 2023 Elsevier Inc. All rights reserved.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1016/j.jbi.2023.104434
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
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 Medicine
Engineering
Public Health
EISSN 1532-0480
ExternalDocumentID 37391115
Genre Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NCI NIH HHS
  grantid: R01 CA204120
– fundername: NHLBI NIH HHS
  grantid: R21 HL161691
– fundername: NCATS NIH HHS
  grantid: UL1 TR001863
GroupedDBID ---
--K
--M
-~X
.DC
.GJ
.~1
0R~
1B1
1RT
1~.
1~5
29J
4.4
457
4G.
53G
5GY
5VS
7-5
71M
8P~
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAWTL
AAXKI
AAXUO
AAYFN
AAYWO
ABBOA
ABBQC
ABDPE
ABFRF
ABJNI
ABMAC
ABMZM
ABWVN
ABXDB
ACDAQ
ACGFO
ACGFS
ACIEU
ACNNM
ACRLP
ACRPL
ACVFH
ACZNC
ADBBV
ADCNI
ADEZE
ADFGL
ADMUD
ADNMO
ADVLN
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AEXQZ
AFJKZ
AFPUW
AFTJW
AFXIZ
AGCQF
AGHFR
AGQPQ
AGRNS
AGUBO
AGYEJ
AHZHX
AIALX
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
AOUOD
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BAWUL
BKOJK
BLXMC
BNPGV
CAG
CGR
COF
CS3
CUY
CVF
DIK
DM4
DU5
EBS
ECM
EFBJH
EFKBS
EIF
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HVGLF
HZ~
IHE
IXB
J1W
KOM
LG5
M41
MO0
N9A
NPM
O-L
O9-
OAUVE
OK1
OZT
P-8
P-9
PC.
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSH
SSV
SSZ
T5K
UAP
UHS
UNMZH
XPP
ZGI
ZMT
ZU3
~G-
7X8
ACLOT
EFLBG
~HD
ID FETCH-LOGICAL-c452t-c82a0b1ff7a91540d5cd6ae74927a4fd6a2a352807785cd1a577d53fed244dae2
IEDL.DBID 7X8
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001085208000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1532-0480
IngestDate Sun Sep 28 05:48:13 EDT 2025
Mon Jul 21 06:04:15 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Integrative analysis
Alignment
Penalization
DNN
High-dimensional
Language English
License Copyright © 2023 Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c452t-c82a0b1ff7a91540d5cd6ae74927a4fd6a2a352807785cd1a577d53fed244dae2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://dx.doi.org/10.1016/j.jbi.2023.104434
PMID 37391115
PQID 2832578399
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2832578399
pubmed_primary_37391115
PublicationCentury 2000
PublicationDate 2023-08-01
PublicationDateYYYYMMDD 2023-08-01
PublicationDate_xml – month: 08
  year: 2023
  text: 2023-08-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of biomedical informatics
PublicationTitleAlternate J Biomed Inform
PublicationYear 2023
SSID ssj0011556
Score 2.3765576
Snippet Deep neural network (DNN) techniques have demonstrated significant advantages over regression and some other techniques. In recent studies, DNN-based analysis...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 104434
SubjectTerms Algorithms
Humans
Neoplasms
Neural Networks, Computer
Title Aligned deep neural network for integrative analysis with high-dimensional input
URI https://www.ncbi.nlm.nih.gov/pubmed/37391115
https://www.proquest.com/docview/2832578399
Volume 144
WOSCitedRecordID wos001085208000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB7Uiijio75frOB1Nd1ks8lJili8tPSg0FvZ7G6kImm0rb_fmWxCvQiClxDyIuxOZr6dmXwfwE2MYdxhKOLCOMkjowXXzhmeqTDJU5fF1iaV2IQaDJLRKB3WCbdZ3VbZ-MTKUdupoRz5HUnqoHVhPL0vPzipRlF1tZbQWIVWiFCGWrrUaFlFwFgZe75Uwenf6aaqWfV3vWWTW9IOpypnRLrJvyHMKtL0dv_7jnuwU2NM1vVGsQ8rrmjD1g_mwTZs9Ouaehu2feaO-R-SDmDYfZ-8ovNl1rmSEd8lPqvw3eIMIS5rGCbQTzJdc5owyucy4j7mlvQCPNcHXlou5ofw0nt8fnjite4CN5EUc24SoYOsk-dKp4iwAiuNjbVTUSqUjnLcF5pIYQKlEjzV0VIpK8PcWcQKVjtxBGvFtHAnwIzNpU3SwGYOgZfNU4kr-Sx2GS68NR49hetmJMdo11Ss0IWbLmbj5ViewrGfjnHpCTjGoQrJR8uzP9x9Dps0y75n7wJaOX7V7hLWzdd8Mvu8qgwGt4Nh_xsuvMyO
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=Aligned+deep+neural+network+for+integrative+analysis+with+high-dimensional+input&rft.jtitle=Journal+of+biomedical+informatics&rft.au=Zhang%2C+Shunqin&rft.au=Zhang%2C+Sanguo&rft.au=Yi%2C+Huangdi&rft.au=Ma%2C+Shuangge&rft.date=2023-08-01&rft.eissn=1532-0480&rft.volume=144&rft.spage=104434&rft_id=info:doi/10.1016%2Fj.jbi.2023.104434&rft_id=info%3Apmid%2F37391115&rft_id=info%3Apmid%2F37391115&rft.externalDocID=37391115
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1532-0480&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1532-0480&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1532-0480&client=summon