アメリカのコンピューター科学工学ジャーナル の調査 オープンアクセス

抽象的な

Usage of Machine Learning Algorithms to Detect Intrusion

N. Raghavendra Sai, M.Jogendra Kumar

A simple computational protocol to estimate the secondary structure of a protein is developed, using the amino acid propensities and the graphic programming language LabVIEW. The protocol estimates the number of residues of the structures α-helix, β-sheet and turns; their validation can be checked by the method of leastsquares in the different established relationships. 31 proteins were analyzed using the NADH dehydrogenase as a standard to evaluate the performance of protocol, the results obtained when comparing the values of the programmed structures with those calculated, showed that the Pearson’s correlation coefficients (r) obtained were statistically significant (P<0.001). This result shows that the number of α-helix, β-sheet and turns are a linear function of the number of amino acid residues in the proteins. It can be concluded that this procedure can be useful for novice researchers with limited technological resources and poor laboratory infrastructure, to estimate the secondary structure of a variety of proteins, suggesting some consequences in protein folding.