Research On SiRNA Design And Its Silencing Efficiency Prediction Methods

First discovered in Wuhan of China,SARS-Co V-2 is a highly pathogenic novel coronavirus,which rapidly spreads globally and becomes a pandemic with no vaccine and limited distinctive clinical drugs available till March 13 th,2020.Ribonucleic Acid interference(RNAi)technology,a gene-silencing technology that targets m RNA,can cause damage to RNA viruses effectively.Here,we report a new efficient small interfering RNA(siRNA)design method named Simple Multiple Rules Intelligent method(MRI method)to propose a new solution of the treatment of COVID-19.To be specific,this study proposes a new model named Base Preference and Thermodynamic Characteristic model(BPTC model)indicating the siRNA silencing efficiency and a new index named siRNA Extended Rules index(SER index)based on BPTC model to screen high-efficiency siRNAs and filter out the siRNAs that are difficult to take effect or synthesize as a part of the MRI method,which is more robust and efficient than the traditional statistical indicators under the same circumstances.Besides,to silence the spike protein of SARS-Co V-2 to invade cells,this study further puts forward the MRI method to search candidate high-efficiency siRNAs on SARS-Co V-2's S gene.In addition,in order to predict the silencing efficiency of siRNA more accurately,we propose a robust deep convolutional neural network model,Deep_siRNA.In this paper,the research status of COVID-19,the mechanism of RNAi,the mainstream design methods of siRNA and other fields are reviewed,and the related theories and methods are introduced.Inspired by the idea of integrated learning in machine learning,combined with the current research status and existing theoretical methods,this paper proposes a design method MRI for Covid-19.In addition,for the first time,we innovatively propose to use deep convolution neural network to learn the influence of the interaction between m RNA and siRNA on RNAi,and to predict the silencing efficiency of siRNA.The results of this study are as follows:(1)According to the analysis results,the average value of predicted interference efficiency of the candidate siRNAs designed by the MRI method is comparable to that of the mainstream siRNA design algorithms.(2)Moreover,the MRI method ensures that the designed siRNAs has more than three base mismatches with human genes,thus avoiding silencing normal human genes.This is not considered by other mainstream methods.(3)The five candidate high-efficiency siRNAs which are easy to take effect or synthesize and more safer for human body are obtained by our MRI method,which provide a new safer,small dosage and long efficacy solution for the treatment of COVID-19.(4)The fusion of mRNA information and siRNA information improves the performance of deep convolutional neural network model by 5.75%,which shows that our idea has brought significant improvement.(5)At the same time,by comparison,our model is superior to the current mainstream siRNA interference efficiency prediction algorithms on several independent siRNA data sets,showing strong robustness.The conclusions of this study are as follows:(1)Compared with the existing research,this study proposed a new mathematical model named BPTC model regarding the siRNA silencing efficiency,a new index SER to extract the rules in methods summarizing the characteristic properties of high-efficiency siRNAs and to efficiently screen high-efficiency siRNAs based on BPTC model and a new,efficient method named MRI method to efficiently design siRNAs which using SER index to effectively filter out the candidate siRNAs that are difficult to take effect or synthesize.That is the SER index is part of the MRI method Moreover,this study successfully designed five potentially efficient siRNAs using the MRI method.Findings in this study provide an effective support for the subsequent research and development of RNAi for the treatment of COVID-19.(2)In addition,we innovatively propose a robust deep convolution neural network model,Deep_siRNA,for predicting the silencing efficiency of siRNA.