• Journal of Digital Contents Society
• /
• v.17 no.6
• /
• pp.509-521
• /
• 2016

A novel Samples Balanced Genetic Algorithm combined with Extreme Learning Machine (SBGA-ELM) for Parkinson's Disease diagnosis and detecting bio-markers is presented in this paper. Proposed approach uses genes' expression data of 22,283 genes from open source ParkDB data base for accurate PD diagnosis and detecting bio-markers. Proposed SBGA-ELM includes two major steps: feature (genes) selection and classification. Feature selection procedure is based on proposed Samples Balanced Genetic Algorithm designed specifically for genes expression data from ParkDB. Proposed SBGA searches a robust subset of genes among 22,283 genes available in ParkDB for further analysis. In the "classification" step chosen set of genes is used to train an Extreme Learning Machine (ELM) classifier for an accurate PD diagnosis. Discovered robust subset of genes creates ELM classifier with stable generalization performance for PD diagnosis. In this research the robust subset of genes is also used to discover 24 bio-markers probably responsible for Parkinson's Disease. Discovered robust subset of genes was verified by using existing PD diagnosis approaches such as SVM and PBL-McRBFN. Both tested methods caused maximum generalization performance.

• Analytical Science and Technology
• /
• v.23 no.6
• /
• pp.537-543
• /
• 2010

Dopamine (DA) is an important neurotransmitter molecule of catecholamines. Its deficiency could lead to brain disorder such as Parkinson's disease and schizophrenia. Therefore, it is necessary to establish a suitable analytical technique with sensitivity and simplicity. A competitive enzyme-linked immunosorbent assay for DA has been optimized and characterized. Assay sensitivity is controlled by two factors in competitive immunoassay. One is a nature and concentration of competitor, and the other is those of binder, antibody. Thus, optimization was performed: BSA-DA conjugate and antibody-avidin conjugate were prepared by dual heterobifunctional coupling method using SATA and SMCC. Assay condition was optimized with $6.66\;{\mu}gmL^{-1}$ of BSA-DA and $4.17{\times}10^{-10}\;M$ of antibody-avidin conjugate. A dose-response curve was constructed, and a limit of detection and a dynamic range for DA were accomplished to $2.3{\times}10^{-2}\;{\mu}g\;mL^{-1}$ and four orders of magnitude ($1.0{\times}10^{-7}\;M$ to $1.0{\times}10^{-3}\;M$), respectively. Calibration curve was constructed on dynamic range and least-squares regression of this data gave the following relationship: absorbance = -0.1098 log[DA]+0.0353 ($R^2$ = 0.9956).