PBMDR: A particle swarm optimization-based multifactor dimensionality reduction for the detection of multilocus interactions.


Department of Electronic Engineering, National Kaohsiung University of Science and Technology, No.415, Jiangong Rd., Sanmin Dist., Kaohsiung City 80778, Taiwan.; Graduate Institute of Clinical Medicine, Kaohsiung Medical University, Kaohsiung City 80708, Taiwan.. Electronic address: [Email]


Studies on multilocus interactions have mainly investigated the associations between genetic variations from the related genes and histopathological tumor characteristics in patients. However, currently, the identification and characterization of susceptibility genes for complex diseases remain a great challenge for geneticists. In this study, a particle swarm optimization (PSO)-based multifactor dimensionality reduction (MDR) approach was proposed, denoted by PBMDR. MDR was used to detect multilocus interactions based on the PSO algorithm. A test data set was simulated from the genotype frequencies of 26 SNPs from eight breast-cancer-related gene. In simulated disease models, we demonstrated that PBMDR outperforms existing global optimization algorithms in terms of its ability to explore and power to detect specific SNP-genotype combinations. In addition, the PBMDR algorithm was compared with other algorithms, including PSO and chaotic PSOs, and the results revealed that the PBMDR algorithm yielded higher accuracy and chi-square values than other algorithms did.


Multifactor dimensionality reduction,Particle swarm optimization,Single nucleotide polymorphism,