Long Short-Term Memory Neural Networks for RNA Viruses Mutations Prediction

Abstract

Viral progress remains a major deterrent in the viability of antiviral drugs. The ability to anticipate this development will provide assistance in the early detection of drug-resistant strains and may encourage antiviral drugs to be the most effective plan. In recent years, a deep learning model called the seq2seq neural network has emerged and has been widely used in natural language processing. In this research, we borrow this approach for predicting next generation sequences using the seq2seq LSTM neural network while considering these sequences as text data. We used hot single vectors to represent the sequences as input to the model; subsequently, it maintains the basic information position of each nucleotide in the sequences. Two RNA viruses sequence datasets are used to evaluate the proposed model which achieved encouraging results. The achieved results illustrate the potential for utilizing the LSTM neural network for DNA and RNA sequences in solving other sequencing issues in bioinformatics.

Quantifying Mutational Response to Track the Evolution of SARS-CoV-2 Spike Variants: Introducing a Statistical-Mechanics-Guided Machine Learning Method

“…How accurately can we predict these mutations? Predicting the mutational pattern of a species may provide insights into the mutation process and future activity of the species and may help design potential drugs targeting the viral species. , Machine Learning techniques offer assistance for analyzing the available mutational data with several models utilizing different methods to predict the mutations in different scenarios, such as Long–Short-Term Memory (LSTM) models and Neural Networks and Rough Set theory to predict mutations in viral species, Statistical Relational Learning for generating resistant mutations in HIV reverse transcriptase inhibitors, Deep Convolutional Neural Network to classify and predict mutation from histopathology images of lung cancer, Variational Autoencoders (VAE) to examine the heterogeneity and fluctuation of chromatin structure, Interactive Interface to analyze biomedical and clinical data sets, Supervised Machine Learning Model of coarse-grained molecular dynamic force fields, and Multilayer Perceptron classifier to predict mutations in the influenza virus. As a new approach, information entropy can be utilized for data compression and transmission and to calculate the target-class imbalances in binary classification models of machine learning.…”

A Multiple Model Approach for Flood Forecasting, Simulation, and Evaluation Coupling in Zhouqu County

“…Figure 4 presents the measured daily flow data of the Zhouqu hydrological station, while Figure 5 showcases the corresponding rainfall data from both the Zhouqu and Sanyanyu stations. For comparison purposes, this study utilizes the LSTM model [33,34] and the XAJ model to predict the flow of hydrological stations in Zhouqu using the same historical…”

“…Figure 4 presents the measured daily flow data of the Zhouqu hydrological station, while Figure 5 showcases the corresponding rainfall data from both the Zhouqu and Sanyanyu stations. For comparison purposes, this study utilizes the LSTM model [33,34] and the XAJ model to predict the flow of hydrological stations in Zhouqu using the same historical For comparison purposes, this study utilizes the LSTM model [33,34] and the XAJ model to predict the flow of hydrological stations in Zhouqu using the same historical flow data. The LSTM model is a commonly employed data-driven model known for its high computational accuracy and stability.…”

Design of Accounting Earnings Forecasting Model Based on Artificial Intelligence

“…With the improvement of seq2seq [25,26], we can incorporate many factors related to earnings value into the earnings forecast model. However, many parameters still need to be manually adjusted in the entire forecast model.…”