Loading…
Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data
Accurate prognostic prediction using molecular information is a challenging area of research, which is essential to develop precision medicine. In this paper, we develop translational models to identify major actionable proteins that are associated with clinical outcomes, like the survival time of p...
Saved in:
Published in: | Biometrics 2020-03, Vol.76 (1), p.316-325 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623 |
---|---|
cites | cdi_FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623 |
container_end_page | 325 |
container_issue | 1 |
container_start_page | 316 |
container_title | Biometrics |
container_volume | 76 |
creator | Maity, Arnab Kumar Bhattacharya, Anirban Mallick, Bani K. Baladandayuthapani, Veerabhadran |
description | Accurate prognostic prediction using molecular information is a challenging area of research, which is essential to develop precision medicine. In this paper, we develop translational models to identify major actionable proteins that are associated with clinical outcomes, like the survival time of patients. There are considerable statistical and computational challenges due to the large dimension of the problems. Furthermore, data are available for different tumor types; hence data integration for various tumors is desirable. Having censored survival outcomes escalates one more level of complexity in the inferential procedure. We develop Bayesian hierarchical survival models, which accommodate all the challenges mentioned here. We use the hierarchical Bayesian accelerated failure time model for survival regression. Furthermore, we assume sparse horseshoe prior distribution for the regression coefficients to identify the major proteomic drivers. We borrow strength across tumor groups by introducing a correlation structure among the prior distributions. The proposed methods have been used to analyze data from the recently curated “The Cancer Proteome Atlas” (TCPA), which contains reverse‐phase protein arrays–based high‐quality protein expression data as well as detailed clinical annotation, including survival times. Our simulation and the TCPA data analysis illustrate the efficacy of the proposed integrative model, which links different tumors with the correlated prior structures. |
doi_str_mv | 10.1111/biom.13132 |
format | article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7007312</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2375889737</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623</originalsourceid><addsrcrecordid>eNp9kc1u1DAUhS0EokNhwwMgS2wQUlr_JHayQaIVtJVadQMSO-vGuRlcZezBTgZmxyPwjDwJTlMqYIE3ls_5dO61DiHPOTvi-Ry3LmyOuORSPCArXpW8YKVgD8mKMaYKWfJPB-RJSjf52VRMPCYHmW0kY3JF0gnsMTnwtIMRqPMjriOMLngKvqM7iA7aAWnCAe2t3IdIt-B_fv9hwVuMNE1x53Yw0G3Ezi3QlJxfZyGM6DzFb9lKaTbmKU_Jox6GhM_u7kPy8f27D6fnxeX12cXp28vClmUtCq4tg75telWVDe-UUIpDxbmQsrZdpxvVdxYb1dQAjPWsqludFWC2FqiUkIfkzZK7ndoNZtaPEQazjW4DcW8COPO3491nsw47oxnTks8Br-4CYvgyYRrNxiWLwwAew5SMEJnkXIsmoy__QW_CFH3-nhFSV3XdaKkz9XqhbAwpRezvl-HMzF2auUtz22WGX_y5_j36u7wM8AX46gbc_yfKnFxcXy2hvwBRD61E</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2375889737</pqid></control><display><type>article</type><title>Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data</title><source>Oxford Journals Online</source><source>SPORTDiscus with Full Text</source><creator>Maity, Arnab Kumar ; Bhattacharya, Anirban ; Mallick, Bani K. ; Baladandayuthapani, Veerabhadran</creator><creatorcontrib>Maity, Arnab Kumar ; Bhattacharya, Anirban ; Mallick, Bani K. ; Baladandayuthapani, Veerabhadran</creatorcontrib><description>Accurate prognostic prediction using molecular information is a challenging area of research, which is essential to develop precision medicine. In this paper, we develop translational models to identify major actionable proteins that are associated with clinical outcomes, like the survival time of patients. There are considerable statistical and computational challenges due to the large dimension of the problems. Furthermore, data are available for different tumor types; hence data integration for various tumors is desirable. Having censored survival outcomes escalates one more level of complexity in the inferential procedure. We develop Bayesian hierarchical survival models, which accommodate all the challenges mentioned here. We use the hierarchical Bayesian accelerated failure time model for survival regression. Furthermore, we assume sparse horseshoe prior distribution for the regression coefficients to identify the major proteomic drivers. We borrow strength across tumor groups by introducing a correlation structure among the prior distributions. The proposed methods have been used to analyze data from the recently curated “The Cancer Proteome Atlas” (TCPA), which contains reverse‐phase protein arrays–based high‐quality protein expression data as well as detailed clinical annotation, including survival times. Our simulation and the TCPA data analysis illustrate the efficacy of the proposed integrative model, which links different tumors with the correlated prior structures.</description><identifier>ISSN: 0006-341X</identifier><identifier>EISSN: 1541-0420</identifier><identifier>DOI: 10.1111/biom.13132</identifier><identifier>PMID: 31393003</identifier><language>eng</language><publisher>United States: Blackwell Publishing Ltd</publisher><subject>AFT regression ; Annotations ; Bayesian analysis ; borrowing strength ; Cancer ; Computer applications ; Computer simulation ; Data analysis ; Data integration ; Failure times ; horseshoe ; Integration ; Mathematical models ; pan‐cancer model ; Precision medicine ; Protein arrays ; Protein expression ; Proteins ; Proteomes ; Regression analysis ; Regression coefficients ; Regression models ; Statistical analysis ; Survival ; TCPA ; Tumors</subject><ispartof>Biometrics, 2020-03, Vol.76 (1), p.316-325</ispartof><rights>2019 The International Biometric Society</rights><rights>2019 The International Biometric Society.</rights><rights>2020 The International Biometric Society</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623</citedby><cites>FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623</cites><orcidid>0000-0002-6692-0155</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/31393003$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Maity, Arnab Kumar</creatorcontrib><creatorcontrib>Bhattacharya, Anirban</creatorcontrib><creatorcontrib>Mallick, Bani K.</creatorcontrib><creatorcontrib>Baladandayuthapani, Veerabhadran</creatorcontrib><title>Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data</title><title>Biometrics</title><addtitle>Biometrics</addtitle><description>Accurate prognostic prediction using molecular information is a challenging area of research, which is essential to develop precision medicine. In this paper, we develop translational models to identify major actionable proteins that are associated with clinical outcomes, like the survival time of patients. There are considerable statistical and computational challenges due to the large dimension of the problems. Furthermore, data are available for different tumor types; hence data integration for various tumors is desirable. Having censored survival outcomes escalates one more level of complexity in the inferential procedure. We develop Bayesian hierarchical survival models, which accommodate all the challenges mentioned here. We use the hierarchical Bayesian accelerated failure time model for survival regression. Furthermore, we assume sparse horseshoe prior distribution for the regression coefficients to identify the major proteomic drivers. We borrow strength across tumor groups by introducing a correlation structure among the prior distributions. The proposed methods have been used to analyze data from the recently curated “The Cancer Proteome Atlas” (TCPA), which contains reverse‐phase protein arrays–based high‐quality protein expression data as well as detailed clinical annotation, including survival times. Our simulation and the TCPA data analysis illustrate the efficacy of the proposed integrative model, which links different tumors with the correlated prior structures.</description><subject>AFT regression</subject><subject>Annotations</subject><subject>Bayesian analysis</subject><subject>borrowing strength</subject><subject>Cancer</subject><subject>Computer applications</subject><subject>Computer simulation</subject><subject>Data analysis</subject><subject>Data integration</subject><subject>Failure times</subject><subject>horseshoe</subject><subject>Integration</subject><subject>Mathematical models</subject><subject>pan‐cancer model</subject><subject>Precision medicine</subject><subject>Protein arrays</subject><subject>Protein expression</subject><subject>Proteins</subject><subject>Proteomes</subject><subject>Regression analysis</subject><subject>Regression coefficients</subject><subject>Regression models</subject><subject>Statistical analysis</subject><subject>Survival</subject><subject>TCPA</subject><subject>Tumors</subject><issn>0006-341X</issn><issn>1541-0420</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kc1u1DAUhS0EokNhwwMgS2wQUlr_JHayQaIVtJVadQMSO-vGuRlcZezBTgZmxyPwjDwJTlMqYIE3ls_5dO61DiHPOTvi-Ry3LmyOuORSPCArXpW8YKVgD8mKMaYKWfJPB-RJSjf52VRMPCYHmW0kY3JF0gnsMTnwtIMRqPMjriOMLngKvqM7iA7aAWnCAe2t3IdIt-B_fv9hwVuMNE1x53Yw0G3Ezi3QlJxfZyGM6DzFb9lKaTbmKU_Jox6GhM_u7kPy8f27D6fnxeX12cXp28vClmUtCq4tg75telWVDe-UUIpDxbmQsrZdpxvVdxYb1dQAjPWsqludFWC2FqiUkIfkzZK7ndoNZtaPEQazjW4DcW8COPO3491nsw47oxnTks8Br-4CYvgyYRrNxiWLwwAew5SMEJnkXIsmoy__QW_CFH3-nhFSV3XdaKkz9XqhbAwpRezvl-HMzF2auUtz22WGX_y5_j36u7wM8AX46gbc_yfKnFxcXy2hvwBRD61E</recordid><startdate>202003</startdate><enddate>202003</enddate><creator>Maity, Arnab Kumar</creator><creator>Bhattacharya, Anirban</creator><creator>Mallick, Bani K.</creator><creator>Baladandayuthapani, Veerabhadran</creator><general>Blackwell Publishing Ltd</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-6692-0155</orcidid></search><sort><creationdate>202003</creationdate><title>Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data</title><author>Maity, Arnab Kumar ; Bhattacharya, Anirban ; Mallick, Bani K. ; Baladandayuthapani, Veerabhadran</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>AFT regression</topic><topic>Annotations</topic><topic>Bayesian analysis</topic><topic>borrowing strength</topic><topic>Cancer</topic><topic>Computer applications</topic><topic>Computer simulation</topic><topic>Data analysis</topic><topic>Data integration</topic><topic>Failure times</topic><topic>horseshoe</topic><topic>Integration</topic><topic>Mathematical models</topic><topic>pan‐cancer model</topic><topic>Precision medicine</topic><topic>Protein arrays</topic><topic>Protein expression</topic><topic>Proteins</topic><topic>Proteomes</topic><topic>Regression analysis</topic><topic>Regression coefficients</topic><topic>Regression models</topic><topic>Statistical analysis</topic><topic>Survival</topic><topic>TCPA</topic><topic>Tumors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Maity, Arnab Kumar</creatorcontrib><creatorcontrib>Bhattacharya, Anirban</creatorcontrib><creatorcontrib>Mallick, Bani K.</creatorcontrib><creatorcontrib>Baladandayuthapani, Veerabhadran</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Biometrics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Maity, Arnab Kumar</au><au>Bhattacharya, Anirban</au><au>Mallick, Bani K.</au><au>Baladandayuthapani, Veerabhadran</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data</atitle><jtitle>Biometrics</jtitle><addtitle>Biometrics</addtitle><date>2020-03</date><risdate>2020</risdate><volume>76</volume><issue>1</issue><spage>316</spage><epage>325</epage><pages>316-325</pages><issn>0006-341X</issn><eissn>1541-0420</eissn><abstract>Accurate prognostic prediction using molecular information is a challenging area of research, which is essential to develop precision medicine. In this paper, we develop translational models to identify major actionable proteins that are associated with clinical outcomes, like the survival time of patients. There are considerable statistical and computational challenges due to the large dimension of the problems. Furthermore, data are available for different tumor types; hence data integration for various tumors is desirable. Having censored survival outcomes escalates one more level of complexity in the inferential procedure. We develop Bayesian hierarchical survival models, which accommodate all the challenges mentioned here. We use the hierarchical Bayesian accelerated failure time model for survival regression. Furthermore, we assume sparse horseshoe prior distribution for the regression coefficients to identify the major proteomic drivers. We borrow strength across tumor groups by introducing a correlation structure among the prior distributions. The proposed methods have been used to analyze data from the recently curated “The Cancer Proteome Atlas” (TCPA), which contains reverse‐phase protein arrays–based high‐quality protein expression data as well as detailed clinical annotation, including survival times. Our simulation and the TCPA data analysis illustrate the efficacy of the proposed integrative model, which links different tumors with the correlated prior structures.</abstract><cop>United States</cop><pub>Blackwell Publishing Ltd</pub><pmid>31393003</pmid><doi>10.1111/biom.13132</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-6692-0155</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0006-341X |
ispartof | Biometrics, 2020-03, Vol.76 (1), p.316-325 |
issn | 0006-341X 1541-0420 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7007312 |
source | Oxford Journals Online; SPORTDiscus with Full Text |
subjects | AFT regression Annotations Bayesian analysis borrowing strength Cancer Computer applications Computer simulation Data analysis Data integration Failure times horseshoe Integration Mathematical models pan‐cancer model Precision medicine Protein arrays Protein expression Proteins Proteomes Regression analysis Regression coefficients Regression models Statistical analysis Survival TCPA Tumors |
title | Bayesian data integration and variable selection for pan‐cancer survival prediction using protein expression data |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-03T23%3A24%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Bayesian%20data%20integration%20and%20variable%20selection%20for%20pan%E2%80%90cancer%20survival%20prediction%20using%20protein%20expression%20data&rft.jtitle=Biometrics&rft.au=Maity,%20Arnab%20Kumar&rft.date=2020-03&rft.volume=76&rft.issue=1&rft.spage=316&rft.epage=325&rft.pages=316-325&rft.issn=0006-341X&rft.eissn=1541-0420&rft_id=info:doi/10.1111/biom.13132&rft_dat=%3Cproquest_pubme%3E2375889737%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c4482-17c0afb9f65491d62661a5112338cdd796fdce9698aa00f058b7fdca0c82e6623%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2375889737&rft_id=info:pmid/31393003&rfr_iscdi=true |