A Prostate Cancer Model Build by a Novel SVM-ID3 Hybrid Feature Selection Method Using Both Genotyping and Phenotype Data from DbGaP

Overview

Journal PLoS One

Specialties General Medicine
Science

Date 2014 Mar 22

PMID 24651484

Citations 5

Authors

Sait Can Yucebas

Yesim Aydin Son

Affiliations

Soon will be listed here.

Abstract

Through Genome Wide Association Studies (GWAS) many Single Nucleotide Polymorphism (SNP)-complex disease relations can be investigated. The output of GWAS can be high in amount and high dimensional, also relations between SNPs, phenotypes and diseases are most likely to be nonlinear. In order to handle high volume-high dimensional data and to be able to find the nonlinear relations we have utilized data mining approaches and a hybrid feature selection model of support vector machine and decision tree has been designed. The designed model is tested on prostate cancer data and for the first time combined genotype and phenotype information is used to increase the diagnostic performance. We were able to select phenotypic features such as ethnicity and body mass index, and SNPs those map to specific genes such as CRR9, TERT. The performance results of the proposed hybrid model, on prostate cancer dataset, with 90.92% of sensitivity and 0.91 of area under ROC curve, shows the potential of the approach for prediction and early detection of the prostate cancer.

Citing Articles

Identifying Critical States of Complex Diseases by Single-Sample Jensen-Shannon Divergence.

Yan J, Li P, Gao R, Li Y, Chen L Front Oncol. 2021; 11:684781.

PMID: 34150649 PMC: 8212786. DOI: 10.3389/fonc.2021.684781.

Precise diagnosis of three top cancers using dbGaP data.

Liu X, Liu X, Rong J, Gao F, Wu Y, Deng C Sci Rep. 2021; 11(1):823.

PMID: 33436913 PMC: 7804208. DOI: 10.1038/s41598-020-80832-x.

Building a genetic risk model for bipolar disorder from genome-wide association data with random forest algorithm.

Chuang L, Kuo P Sci Rep. 2017; 7:39943.

PMID: 28045094 PMC: 5206749. DOI: 10.1038/srep39943.

FHSA-SED: Two-Locus Model Detection for Genome-Wide Association Study with Harmony Search Algorithm.

Tuo S, Zhang J, Yuan X, Zhang Y, Liu Z PLoS One. 2016; 11(3):e0150669.

PMID: 27014873 PMC: 4807955. DOI: 10.1371/journal.pone.0150669.

Incorporation of personal single nucleotide polymorphism (SNP) data into a national level electronic health record for disease risk assessment, part 3: an evaluation of SNP incorporated national health information system of Turkey for prostate cancer.

Beyan T, Aydin Son Y JMIR Med Inform. 2015; 2(2):e21.

PMID: 25600087 PMC: 4288064. DOI: 10.2196/medinform.3560.

References

Aksoy Y, Oral A, Aksoy H, Demirel A, Akcay F . PSA density and PSA transition zone density in the diagnosis of prostate cancer in PSA gray zone cases. Ann Clin Lab Sci. 2003; 33(3):320-3. View

Kleinmann N, Zaorsky N, Showalter T, Gomella L, Lallas C, Trabulsi E . The effect of ethnicity and sexual preference on prostate-cancer-related quality of life. Nat Rev Urol. 2012; 9(5):258-65. DOI: 10.1038/nrurol.2012.56. View

Musani S, Shriner D, Liu N, Feng R, Coffey C, Yi N . Detection of gene x gene interactions in genome-wide association studies of human population data. Hum Hered. 2007; 63(2):67-84. DOI: 10.1159/000099179. View

Giovannucci E, Rimm E, Liu Y, Leitzmann M, Wu K, Stampfer M . Body mass index and risk of prostate cancer in U.S. health professionals. J Natl Cancer Inst. 2003; 95(16):1240-4. DOI: 10.1093/jnci/djg009. View

Huang L, Hsu S, Lin E . A comparison of classification methods for predicting Chronic Fatigue Syndrome based on genetic data. J Transl Med. 2009; 7:81. PMC: 2765429. DOI: 10.1186/1479-5876-7-81. View

Hoffman R, Gilliland F, Adams-Cameron M, Hunt W, Key C . Prostate-specific antigen testing accuracy in community practice. BMC Fam Pract. 2002; 3:19. PMC: 137591. DOI: 10.1186/1471-2296-3-19. View

Hoffman R, Gilliland F, Eley J, Harlan L, Stephenson R, Stanford J . Racial and ethnic differences in advanced-stage prostate cancer: the Prostate Cancer Outcomes Study. J Natl Cancer Inst. 2001; 93(5):388-95. DOI: 10.1093/jnci/93.5.388. View

Ritchie M, Motsinger A, Bush W, Coffey C, Moore J . Genetic Programming Neural Networks: A Powerful Bioinformatics Tool for Human Genetics. Appl Soft Comput. 2011; 7(1):471-479. PMC: 2952963. DOI: 10.1016/j.asoc.2006.01.013. View

He J, Hu H, Harrison R, Tai P, Pan Y . Rule generation for protein secondary structure prediction with support vector machines and decision tree. IEEE Trans Nanobioscience. 2006; 5(1):46-53. DOI: 10.1109/tnb.2005.864021. View

10.

Lee J, Parkes M . Genome-wide association studies and Crohn's disease. Brief Funct Genomics. 2011; 10(2):71-6. DOI: 10.1093/bfgp/elr009. View

11.

Reddy M, Wang H, Liu S, Bode B, Reed J, Steed R . Association between type 1 diabetes and GWAS SNPs in the southeast US Caucasian population. Genes Immun. 2011; 12(3):208-12. PMC: 3952552. DOI: 10.1038/gene.2010.70. View

12.

Stahl E, Raychaudhuri S, Remmers E, Xie G, Eyre S, Thomson B . Genome-wide association study meta-analysis identifies seven new rheumatoid arthritis risk loci. Nat Genet. 2010; 42(6):508-14. PMC: 4243840. DOI: 10.1038/ng.582. View

13.

Listgarten J, Damaraju S, Poulin B, Cook L, Dufour J, Driga A . Predictive models for breast cancer susceptibility from multiple single nucleotide polymorphisms. Clin Cancer Res. 2004; 10(8):2725-37. DOI: 10.1158/1078-0432.ccr-1115-03. View

14.

Klein R, Zeiss C, Chew E, Tsai J, Sackler R, Haynes C . Complement factor H polymorphism in age-related macular degeneration. Science. 2005; 308(5720):385-9. PMC: 1512523. DOI: 10.1126/science.1109557. View

15.

Chow W, Blot W, Vaughan T, Risch H, Gammon M, Stanford J . Body mass index and risk of adenocarcinomas of the esophagus and gastric cardia. J Natl Cancer Inst. 1998; 90(2):150-5. DOI: 10.1093/jnci/90.2.150. View

16.

Gerstenblith M, Shi J, Landi M . Genome-wide association studies of pigmentation and skin cancer: a review and meta-analysis. Pigment Cell Melanoma Res. 2010; 23(5):587-606. PMC: 3179913. DOI: 10.1111/j.1755-148X.2010.00730.x. View

17.

Mourad R, Sinoquet C, Leray P . A hierarchical Bayesian network approach for linkage disequilibrium modeling and data-dimensionality reduction prior to genome-wide association studies. BMC Bioinformatics. 2011; 12:16. PMC: 3033325. DOI: 10.1186/1471-2105-12-16. View

18.

Mooney M, Wilmot B, Bipolar Genome Study T, McWeeney S . The GA and the GWAS: using genetic algorithms to search for multilocus associations. IEEE/ACM Trans Comput Biol Bioinform. 2011; 9(3):899-910. PMC: 3748153. DOI: 10.1109/TCBB.2011.145. View

19.

Yeager M, Orr N, Hayes R, Jacobs K, Kraft P, Wacholder S . Genome-wide association study of prostate cancer identifies a second risk locus at 8q24. Nat Genet. 2007; 39(5):645-9. DOI: 10.1038/ng2022. View

20.

Appleby P, Reeves G, Roddam A, Dorgan J, Stanczyk F, STEPHENSON Jr H . Body mass index, serum sex hormones, and breast cancer risk in postmenopausal women. J Natl Cancer Inst. 2003; 95(16):1218-26. DOI: 10.1093/jnci/djg022. View