Prediction of inherited genomic susceptibility to 20 common cancer types by a supervised machine-learning method

Kim, Byung-Ju; Kim, Sung-Hou

doi:10.1073/pnas.1717960115

Prediction of inherited genomic susceptibility to 20 common cancer types by a supervised machine-learning method

Journal Article · Thu Dec 21 00:00:00 EST 2017 · Proceedings of the National Academy of Sciences of the United States of America

DOI:https://doi.org/10.1073/pnas.1717960115· OSTI ID:1625007

Kim, Byung-Ju ^[1]; ^[2]

Univ. of California, Berkeley, CA (United States). Dept. of Chemistry; Yonsei Univ., Seoul (Korea). Dept. of Integrative Omics for Biomedical Sciences; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Molecular Biophysics and Integrated Bioimaging Division; DOE/OSTI
Univ. of California, Berkeley, CA (United States). Dept. of Chemistry and Center for Computational Biology; Yonsei Univ., Seoul (Korea). Dept. of Integrative Omics for Biomedical Sciences; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Molecular Biophysics and Integrated Bioimaging Division

Prevention and early intervention are the most effective ways of avoiding or minimizing psychological, physical, and financial suffering from cancer. However, such proactive action requires the ability to predict the individual’s susceptibility to cancer with a measure of probability. Of the triad of cancer-causing factors (inherited genomic susceptibility, environmental factors, and lifestyle factors), the inherited genomic component may be derivable from the recent public availability of a large body of whole-genome variation data. However, genome-wide association studies have so far showed limited success in predicting the inherited susceptibility to common cancers. We present here a multiple classification approach for predicting individuals’ inherited genomic susceptibility to acquire the most likely phenotype among a panel of 20 major common cancer types plus 1 “healthy” type by application of a supervised machine-learning method under competing conditions among the cohorts of the 21 types. This approach suggests that, depending on the phenotypes of 5,919 individuals of “white” ethnic population in this study, (i) the portion of the cohort of a cancer type who acquired the observed type due to mostly inherited genomic susceptibility factors ranges from about 33 to 88% (or its corollary: the portion due to mostly environmental and lifestyle factors ranges from 12 to 67%), and (ii) on an individual level, the method also predicts individuals’ inherited genomic susceptibility to acquire the other types ranked with associated probabilities. These probabilities may provide practical information for individuals, heath professionals, and health policymakers related to prevention and/or early intervention of cancer.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)

Sponsoring Organization:: Ministry of Education, Science and Technology; USDOE Office of Science (SC)

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 1625007

Journal Information:: Proceedings of the National Academy of Sciences of the United States of America, Journal Name: Proceedings of the National Academy of Sciences of the United States of America Journal Issue: 6 Vol. 115; ISSN 0027-8424

Publisher:: National Academy of SciencesCopyright Statement

Country of Publication:: United States

Language:: English

References (24)

Diagnosis and Management of Hereditary Phaeochromocytoma and Paraganglioma Lalloo, Fiona Recent Results in Cancer Research https://doi.org/10.1007/978-3-319-29998-3_7	book	January 2016
Multiobjective evolutionary algorithms to identify highly autocorrelated areas: the case of spatial distribution in financially compromised farms García-Alonso, Carlos R.; Pérez-Naranjo, Leonor M.; Fernández-Caballero, Juan C. Annals of Operations Research, Vol. 219, Issue 1 https://doi.org/10.1007/s10479-011-0841-3	journal	January 2011
Hallmarks of Cancer: The Next Generation Hanahan, Douglas; Weinberg, Robert A. Cell, Vol. 144, Issue 5 https://doi.org/10.1016/j.cell.2011.02.013	journal	March 2011
Genes mirror geography within Europe Novembre, John; Johnson, Toby; Bryc, Katarzyna Nature, Vol. 456, Issue 7218 https://doi.org/10.1038/nature07331	journal	August 2008
Genes mirror geography within Europe Novembre, John; Johnson, Toby; Bryc, Katarzyna Nature, Vol. 456, Issue 7219 https://doi.org/10.1038/nature07566	journal	November 2008
A global reference for human genetic variation Consortium, The 1000 Genomes Project; Auton, Adam; Abecasis, Gonçalo R. Nature, Vol. 526, Issue 7571, p. 68-74 https://doi.org/10.1038/nature15393	journal	January 2015
The Cancer Genome Atlas Pan-Cancer analysis project Weinstein, John N.; Collisson, Eric A.; Mills, Gordon B. Nature Genetics, Vol. 45, Issue 10 https://doi.org/10.1038/ng.2764	journal	September 2013
Common variation and heritability estimates for breast, ovarian and prostate cancers Bahcall, Orli Nature Genetics https://doi.org/10.1038/ngicogs.1	journal	March 2013
Data quality control in genetic case-control association studies Anderson, Carl A.; Pettersson, Fredrik H.; Clarke, Geraldine M. Nature Protocols, Vol. 5, Issue 9 https://doi.org/10.1038/nprot.2010.116	journal	August 2010
Linkage disequilibrium — understanding the evolutionary past and mapping the medical future Slatkin, Montgomery Nature Reviews Genetics, Vol. 9, Issue 6 https://doi.org/10.1038/nrg2361	journal	June 2008
A synthetic energy dataset for non-intrusive load monitoring in households Klemenjak, Christoph; Kovatsch, Christoph; Herold, Manuel Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-0434-6	journal	April 2020
Genomewide Association Studies and Assessment of the Risk of Disease Manolio, Teri A. New England Journal of Medicine, Vol. 363, Issue 2 https://doi.org/10.1056/NEJMra0905980	journal	July 2010
Empirical prediction of genomic susceptibilities for multiple cancer classes Kim, Minseung; Kim, Sung-Hou Proceedings of the National Academy of Sciences, Vol. 111, Issue 5 https://doi.org/10.1073/pnas.1318383110	journal	January 2014
Polygenic Modeling of Genome-Wide Association Studies: An Application to Prostate and Breast Cancer Witte, John S.; Hoffmann, Thomas J. OMICS: A Journal of Integrative Biology, Vol. 15, Issue 6 https://doi.org/10.1089/omi.2010.0090	journal	June 2011
Robust relationship inference in genome-wide association studies Manichaikul, Ani; Mychaleckyj, Josyf C.; Rich, Stephen S. Bioinformatics, Vol. 26, Issue 22 https://doi.org/10.1093/bioinformatics/btq559	journal	October 2010
Divergence measures based on the Shannon entropy Lin, J. IEEE Transactions on Information Theory, Vol. 37, Issue 1 https://doi.org/10.1109/18.61115	journal	January 1991
Second-generation PLINK: rising to the challenge of larger and richer datasets Chang, Christopher C.; Chow, Carson C.; Tellier, Laurent CAM GigaScience, Vol. 4, Issue 1 https://doi.org/10.1186/s13742-015-0047-8	journal	February 2015
Staging the Tumor and Staging the Host: Pretreatment Combined Neutrophil Lymphocyte Ratio and Modified Glasgow Prognostic Score Is Associated with Overall Survival in Patients with Esophagogastric Cancers Undergoing Treatment with Curative Intent McSorley, Stephen T.; Lau, Hiu Y. N.; McIntosh, David Annals of Surgical Oncology, Vol. 28, Issue 2 https://doi.org/10.1245/s10434-020-09074-5	journal	September 2020
A global reference for human genetic variation Xiaosen, Guo,; Meifang, Tang,; Tianming, Lan, The University of North Carolina at Chapel Hill University Libraries https://doi.org/10.17615/0ez3-8z76	text	January 2015
The cancer genome atlas pan-cancer analysis project B., Mills, Gordon; R., Mills Shaw, Kenna; Ilya, Shmulevich, The University of North Carolina at Chapel Hill University Libraries https://doi.org/10.17615/670y-yr53	text	January 2013
A global reference for human genetic variation Yun, Li, The University of North Carolina at Chapel Hill University Libraries https://doi.org/10.17615/p70n-j697	text	January 2015
ROC analysis of classifiers in machine learning: A survey Majnik, Matjaž; Bosnić, Zoran Intelligent Data Analysis, Vol. 17, Issue 3 https://doi.org/10.3233/IDA-130592	journal	May 2013
Cancer Statistics, 2008 Jemal, A.; Siegel, R.; Ward, E. CA: A Cancer Journal for Clinicians, Vol. 58, Issue 2 https://doi.org/10.3322/CA.2007.0010	journal	January 2008
Second-generation PLINK: rising to the challenge of larger and richer datasets Chang, Christopher C.; Chow, Carson C.; Tellier, Laurent C. A. M. arXiv https://doi.org/10.48550/arxiv.1410.4803	text	January 2014

Cited By (5)

Collective behavior of artificial intelligence population: transition from optimization to game Zhang, Si-Ping; Zhang, Ji-Qiang; Huang, Zi-Gang Nonlinear Dynamics, Vol. 95, Issue 2 https://doi.org/10.1007/s11071-018-4649-4	journal	January 2019
The impact of artificial intelligence on the current and future practice of clinical cancer genomics Greatbatch, Olivia; Garrett, Alice; Snape, Katie Genetics Research, Vol. 101 https://doi.org/10.1017/s0016672319000089	journal	January 2019
Cancer classification of single-cell gene expression data by neural network Kim, Bong-Hyun; Yu, Kijin; Lee, Peter C. W. Bioinformatics https://doi.org/10.1093/bioinformatics/btz772	journal	October 2019
Identifying genetic determinants of complex phenotypes from whole genome sequence data Long, George S.; Hussen, Mohammed; Dench, Jonathan BMC Genomics, Vol. 20, Issue 1 https://doi.org/10.1186/s12864-019-5820-0	journal	June 2019
Classification of Kidney Cancer Data Using Cost-Sensitive Hybrid Deep Learning Approach Shon, Ho Sun; Batbaatar, Erdenebileg; Kim, Kyoung Ok Symmetry, Vol. 12, Issue 1 https://doi.org/10.3390/sym12010154	journal	January 2020

Similar Records

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

Journal Article · Tue Jul 05 20:00:00 EDT 2022 · BMC Medical Genomics · OSTI ID:1876318

On whole-genome demography of world’s ethnic groups and individual genomic identity

Journal Article · Mon Apr 17 20:00:00 EDT 2023 · Scientific Reports · OSTI ID:2470994

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
SNP syntax
cancer risk
genomic/environmental factors
k nearest neighbor method
multiple assortment model
science & technology - other topics

Prediction of inherited genomic susceptibility to 20 common cancer types by a supervised machine-learning method

Citation Formats

References (24)

Cited By (5)

Similar Records

Related Subjects