DocumentCode :
3528457
Title :
Detection of complex interactions of multi-locus SNPS
Author :
Yu, Guoqiang ; Herrington, David ; Langefeld, Carl ; Wang, Yue
Author_Institution :
Dept. of Electr. & Comput. Eng., Virginia Polytech. Inst. & State Univ., Arlington, VA
fYear :
2008
fDate :
16-19 Oct. 2008
Firstpage :
85
Lastpage :
90
Abstract :
Detection of interacting SNPs predictive of complex disease will help identify individuals at high risk, make personalized treatment possible, and provide novel insights into the pathophysiology of the conditions in question. Although the interaction effect of multi-locus SNPs is widely expected, the existing strategies have limited power in detecting SNPs with interaction effects. This paper presents a new method (SCA-HCIG) to detect complex interaction effects. The method is tested on a realistic simulated data with 17 embedded ground-truth SNPs under 5 interaction models. Compared to six existing methods, SCA-HCIG achieves the best result in terms of both high sensitivity and specificity.
Keywords :
DNA; bioinformatics; combinatorial mathematics; genomics; learning (artificial intelligence); molecular biophysics; SCA-HCIG method; SNP interaction effects; complex disease; interaction models; multilocus SNP interaction detection; pathophysiology; single nucleotide polymorphisms; Bioinformatics; Cancer; DNA; Diseases; Genetics; Genomics; Humans; Medical diagnostic imaging; Sequences; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning for Signal Processing, 2008. MLSP 2008. IEEE Workshop on
Conference_Location :
Cancun
ISSN :
1551-2541
Print_ISBN :
978-1-4244-2375-0
Electronic_ISBN :
1551-2541
Type :
conf
DOI :
10.1109/MLSP.2008.4685460
Filename :
4685460
Link To Document :
بازگشت