Effect of Feature Selection on Gene Expression Datasets Classification Accurac

<span>Feature selection attracts researchers who deal with machine learning and data mining. It consists of selecting the variables that have the greatest impact on the dataset classification, and discarding the rest. This dimentionality reduction allows classifiers to be fast and more accurate. This paper traits the effect of feature selection on the accuracy of widely used classifiers in literature. These classifiers are compared with three real datasets which are pre-processed with feature selection methods. More than 9% amelioration in classification accuracy is observed, and k-means appears to be the most sensitive classifier to feature selection.</span>

USE OF MOLECULAR GENETIC METHODS IN THE STUDY OF HEREDITARY PREDISPOSITION TO ATOPIC DISEASES INCHILDREN

Background. Study of the аssociations of susceptibility genes to the development of atopic diseases in children. Materials and methods. All 325 examined children reside on the territory of the European part of Russia who by according to surveys, Russian by nationality. Analysis of polymorphism in genes of receptors ADRB2, GRL, ALOX5, genes of biotransformation - CYP1A1, CYP2C9, CYP2C19, GSTT1, GSTM1, NAT2 as well as the variants of the genes MTHFR and TNFA was performed in patients suffering from atopic disease and in healthy individuals. Using Multifactor Dimentionality Reduction method (MDR) it was defined the most significant model of genegene interaction for the development of atopic disease Results. Association of the development of atopic diseases with polymorphic variants of the genes: ALOX5 (VNTR) GRL (1220A > G) TNFA (-308G > A) CYP1A1 (6235T > C) and GSTM1 was identified in surveyed children. The highrisk alleles and genotypes of developing atopic diseases in pediatric patients were determined. Using Multifactor Dimentionality Reduction method (MDR) it was defined the most significant model of gene-gene interaction for the development of atopic disease, including ADRB2 (79 C >G), (46A > G), CYP2C19 (G681A) was defined. Conclusion. There were identified polymorphic variants of genes and important gene-gene interactions associated with development of atopic diseases in children.