In silico studies of ns5 methyltransferase protein of dengue virus using hidden markov model

Abstract

newline Dengue fever is a pandemic disease caused by the Dengue virus (DENV), a flavivirus spread by mosquitos. Dengue fever has become a leading cause of severe sickness and mortality in underdeveloped countries. Dengue fever affects over 400 million people worldwide each year. Dengue infections usually cause only minor symptoms, but they can occasionally progress to severe dengue, which is fatal and for no specific treatment. In recent years, biological data has risen exponentially, resulting in two concerns. The first concern is efficient data storage, while the second is how helpful knowledge can be extracted from the data. Machine learning can generate knowledge from heterogeneous data and solve the second problem. In bioinformatics, the machine learning approach is essential. Artificial Neural Network (ANN), Hidden Markov Model (HMM), Support Vector Machine (SVM), and Genetic Algorithm (GA) are some of the techniques used. The GA is a randomized search method that uses natural selection to solve a problem. Many machine learning approaches based on HMM have been positively employed for biological sequence interpretation. The machine-learning approach to genomics, which takes the form of a probabilistic graphical model, finds its primary application in the modeling of DNA sequences. Models are used to discover genes using the Hidden Markov Model. These models determine the probability of observing sequences and detecting alternative splicing. newlineThe NS5 protein has been shown to play an essential part in the dengue virus replication. At the beginning of this study, the HMM was used to analyze the NS5 Methyltransferase protein of DENV. Determine the HMM parameters with the help of forward algorithm. After that, find the highest possible value of the probability that P(O|and#120582;) represents for the observation sequence in an order that is not descending. Take the gene sequence from 1-20 for the x-axis, the maximum value of P(O|and#120582;), and the number of iterations of the probability of observation sequence for the y