TY - JOUR ID - 119745 TI - Study of Genes Associated With Parkinson Disease Using Feature Selection JO - Journal of Bioengineering Research JA - JBR LA - en SN - 2645-5633 AU - Rafieipour, Hoda AU - Abdollah Zadeh, Azadeh AU - Moradan, Atefeh AU - Salekshahrezaee, Zahra AD - Department of Computer Science, Memorial University of Newfoundland, NF, Canada AD - Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA AD - Department of Computer Science, Aarhus University, Aarhus, Denmark AD - Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, FL, USA Y1 - 2020 PY - 2020 VL - 2 IS - 4 SP - 1 EP - 11 KW - Genome-wide association (GWAS) KW - Single Nucleotide Polymorphisms KW - Perturbation- based feature selection KW - Support vector machine (SVM) KW - Adaboost DO - 10.22034/jbr.2020.251812.1035 N2 - The second most prevalent age-related neurodegenerative disease is Parkinson's (PD) and Genes associated with human diseases like Parkinson are descriptive. Genome-wide association study (GWAS) is used to classify the genes associated with Parkinson’s and other diseases. The information of identified genes empowers scientists to early diagnose, treat, and sop diseases. Due to the complexities of the illness, identifying such genes is a challenging task. In this article, we apply two methods of feature selection to choose a subset of genes that are used to predict PD with high precision in classification. The chromosome corresponding to selected features is analyzed by Perturbation-based Feature Selection (PFS) and Hilbert-Schmidt independence criterion (HSIC)-Lasso. These algorithms are used to identify how chromosomes play an important role with respect to PD. We used a dataset consist of 50 predominantly patients gene expression profiles with early-stage Parkinson's disease (PD) and 55 normal GEO samples. These methods provide a series of features involved in disease-specific processes that are applied to prioritize candidate genes in GWAS loci. UR - https://www.journalbe.com/article_119745.html L1 - https://www.journalbe.com/article_119745_70020972d36e404d1cf7b917f4b871a0.pdf ER -