Fine Tuning Data Mining Algorithm for an Efficient Classification of E-Coli

Abstract

E. coli is the first organisms to be sequenced as genome and the classification within the DEC pathotypes has epidemiologic and clinical implications for managing diarrheal diseases. In many developing countries E.coli leads to cause of diarrhea in children. where the mode of transmissions takes place via food and water. based on their pathogenic phenotype and diseases they cause it can be classified into 6 groups. consequently, our awareness of the spectrum of diseases and syndromes that they cause is quite limited. Also, because we cannot readily identify infected patients, there are many complexities in defining the modes of attainment, prevention and treatment strategies, and estimating the burden of infectious squealed. These infections create many challenges, and no progress will take place until the diagnostic potential for these agents got improved. Identifying E. coli isolate co-express LA reiterates the difficulty of assigning bacteria to groups on the basis of their adherence phenotype or genotype. Therefore the analysis of E -coli with molecular methods demonstrates that strains carry will represent more characteristics of typical EPEC and also the lack of AggR regulon, we propose a novel classification approach for classifying E-coli therefore to recognize pathogens. In addition, the ability to simultaneously induce attaching effacing lesions and biofilm production may enhance the potential of the strains to cause diarrhea and prolong bacterial residence in the intestines, thus worsening malnutrition in the patients.