Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks

VA Million Veteran Program

doi:10.1186/s12920-022-01298-6

Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks

VA Million Veteran Program

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Background: Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. Results: This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration’s Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. Conclusions: To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.

Original language	English
Article number	151
Journal	BMC Medical Genomics
Volume	15
Issue number	1
DOIs	https://doi.org/10.1186/s12920-022-01298-6
State	Published - Dec 2022

Funding

This research is based on data from the Million Veteran Program, Office of Research and Development, Veterans Health Administration, and was supported by award MVP017. This publication does not represent the views of the Department of Veteran Affairs or the United States Government. This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. This research used resources of the Knowledge Discovery Infrastructure at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725 and the Department of Veterans Affairs Office of Information Technology Inter-Agency Agreement with the Department of Energy under IAA No. VA118-16-M-1062. The authors also wish to acknowledge the support of the larger partnership. Most importantly, the authors would like to thank and acknowledge the veterans who chose to get their care at the Veterans Affairs. This project is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725 and the Department of Veterans Affairs Office of Information Technology Inter-Agency Agreement with the Department of Energy under IAA No. VA118-16-M-1062.

Keywords

Genome-wide Association Study
Machine Learning
Network Representation Learning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1186/s12920-022-01298-6

Cite this

@article{0ccd83ad04d04f5dbe9ce97a6fde1100,

title = "Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks",

abstract = "Background: Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. Results: This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration{\textquoteright}s Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. Conclusions: To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.",

keywords = "Genome-wide Association Study, Machine Learning, Network Representation Learning",

author = "{VA Million Veteran Program} and Minsu Kim and Huffman, {Jennifer E.} and Amy Justice and Ian Goethert and Greeshma Agasthya and Yan Sun and Rachel McArdle and Louis Dellitalia and Brady Stephens and Kelly Cho and Saiju Pyarajan and Kristin Mattocks and John Harley and Jeffrey Whittle and Roy Mathew and Jean Beckham and River Smith and John Wells and Salvador Gutierrez and Kimberly Hammer and Pran Iruvanti and Zuhair Ballas and Stephen Mastorides and Jonathan Moorman and Saib Gappy and Jon Klein and Nora Ratcliffe and Ana Palacio and Olaoluwa Okusaga and Maureen Murdoch and Peruvemba Sriram and Argyres, {Dean P.} and Todd Connor and Gerardo Villareal and Scott Kinlay and Yeh, {Shing Shing} and Darshana Jhala and Neeraj Tandon and Chang, {Kyong Mi} and Samuel Aguayo and David Cohen and Satish Sharma and Mark Hamner and Suthat Liangpunsakul and Michael Godschalk and Oursler, {Kris Ann} and Mary Whooley and Jennifer Greco and Sunil Ahuja and Joseph Constans",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1186/s12920-022-01298-6",

language = "English",

volume = "15",

journal = "BMC Medical Genomics",

issn = "1755-8794",

publisher = "BioMed Central",

number = "1",

}

TY - JOUR

T1 - Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks

AU - VA Million Veteran Program

AU - Kim, Minsu

AU - Huffman, Jennifer E.

AU - Justice, Amy

AU - Goethert, Ian

AU - Agasthya, Greeshma

AU - Sun, Yan

AU - McArdle, Rachel

AU - Dellitalia, Louis

AU - Stephens, Brady

AU - Cho, Kelly

AU - Pyarajan, Saiju

AU - Mattocks, Kristin

AU - Harley, John

AU - Whittle, Jeffrey

AU - Mathew, Roy

AU - Beckham, Jean

AU - Smith, River

AU - Wells, John

AU - Gutierrez, Salvador

AU - Hammer, Kimberly

AU - Iruvanti, Pran

AU - Ballas, Zuhair

AU - Mastorides, Stephen

AU - Moorman, Jonathan

AU - Gappy, Saib

AU - Klein, Jon

AU - Ratcliffe, Nora

AU - Palacio, Ana

AU - Okusaga, Olaoluwa

AU - Murdoch, Maureen

AU - Sriram, Peruvemba

AU - Argyres, Dean P.

AU - Connor, Todd

AU - Villareal, Gerardo

AU - Kinlay, Scott

AU - Yeh, Shing Shing

AU - Jhala, Darshana

AU - Tandon, Neeraj

AU - Chang, Kyong Mi

AU - Aguayo, Samuel

AU - Cohen, David

AU - Sharma, Satish

AU - Hamner, Mark

AU - Liangpunsakul, Suthat

AU - Godschalk, Michael

AU - Oursler, Kris Ann

AU - Whooley, Mary

AU - Greco, Jennifer

AU - Ahuja, Sunil

AU - Constans, Joseph

PY - 2022/12

Y1 - 2022/12

N2 - Background: Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. Results: This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration’s Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. Conclusions: To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.

AB - Background: Genome-wide Association Studies (GWAS) aims to uncover the link between genomic variation and phenotype. They have been actively applied in cancer biology to investigate associations between variations and cancer phenotypes, such as susceptibility to certain types of cancer and predisposed responsiveness to specific treatments. Since GWAS primarily focuses on finding associations between individual genomic variations and cancer phenotypes, there are limitations in understanding the mechanisms by which cancer phenotypes are cooperatively affected by more than one genomic variation. Results: This paper proposes a network representation learning approach to learn associations among genomic variations using a prostate cancer cohort. The learned associations are encoded into representations that can be used to identify functional modules of genomic variations within genes associated with early- and late-onset prostate cancer. The proposed method was applied to a prostate cancer cohort provided by the Veterans Administration’s Million Veteran Program to identify candidates for functional modules associated with early-onset prostate cancer. The cohort included 33,159 prostate cancer patients, 3181 early-onset patients, and 29,978 late-onset patients. The reproducibility of the proposed approach clearly showed that the proposed approach can improve the model performance in terms of robustness. Conclusions: To our knowledge, this is the first attempt to use a network representation learning approach to learn associations among genomic variations within genes. Associations learned in this way can lead to an understanding of the underlying mechanisms of how genomic variations cooperatively affect each cancer phenotype. This method can reveal unknown knowledge in the field of cancer biology and can be utilized to design more advanced cancer-targeted therapies.

KW - Genome-wide Association Study

KW - Machine Learning

KW - Network Representation Learning

UR - http://www.scopus.com/inward/record.url?scp=85133605498&partnerID=8YFLogxK

U2 - 10.1186/s12920-022-01298-6

DO - 10.1186/s12920-022-01298-6

M3 - Article

C2 - 35794577

AN - SCOPUS:85133605498

SN - 1755-8794

VL - 15

JO - BMC Medical Genomics

JF - BMC Medical Genomics

IS - 1

M1 - 151

ER -

Identifying intragenic functional modules of genomic variations associated with cancer phenotypes by learning representation of association networks

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this