Data Analysis On The Mechanism Of Soybean Resistance To Phytophthora Sojae Based On Machine Learning

Soybean is an important protein-rich food crop widely cultivated worldwide.Increasing soybean production is a major issue that affects people’s livelihood.Soybean root rot caused by Phytophthora sojae infection causes more than one billion US dollars of economic losses worldwide every year,and no method to completely prevent the disease has been found so far.The main control measures are: Focus on the study of resistant varieties,combined with comprehensive control measures of chemical agents.However,resistant varieties are usually no longer resistant after being promoted for several years,and with the increase of resistant varieties,the breeding work becomes more complicated.In recent years,more and more studies have shown that there is a small RNA(sRNA)level cross-border interaction mechanism between plants and pathogenic bacteria,which provides new research ideas for the control of soybean root rot.sRNA is a type of small molecule that binds to target mRNA using complementary base pairing and plays a regulatory role.Play an important role in the process of life.At present,the mechanism of action of soybean and Phytophthora sojae on sRNA level is not clear.Therefore,analyzing the resistance of soybeans after infection by Phytophthora sojae from the sRNA level,and then carrying out control work at the sRNA level are of great significance for the prevention and control of soybean root rot and the increase of soybean yield and income.Based on the high-throughput data of differentially expressed sRNA in soybean infected by Phytophthora sojae,a variety of machine learning models are used to mine and analyze the characteristics of key sRNAs that are resistant to soybean disease.And platform;the identified key sRNA sequences were targeted to soybean and Phytophthora sojae respectively,and the PageRank algorithm was used to mine core regulatory modules and analyze the function of regulatory pathways to verify the role of selected key soybean resistance sRNA sequences against Phytophthora infestans.This article first details the research background,significance,progress at home and abroad,and related statistical methods and machine learning algorithms.Secondly,the differentially expressed soybean sRNA sequences after infection by Phytophthora sojae were counted according to the abundance and growth rate.Then,based on machine learning methods,the sequence and structure characteristics of key sRNAs were analyzed and excavated,and a machine learning model for predicting the degree of correlation between unknown sRNAs and the disease resistance of soybean against Phytophthora was constructed.86.98%.Finally,the function of key sRNA sequences was verified by functional enrichment analysis,and it was found that it can not only promote soybean resistance to infection by regulating soybean enzyme activity,membrane permeability,and chromosomal cohesion,but also reversely inhibit and degrade Phytophthora sojae mRNA and other processes to inhibit its toxicity.sRNA data usually has the characteristics of a large amount of data and high dimensions.Traditional data analysis methods have been difficult to mine effective biological information.This paper analyzes the high-throughput biological data based on machine learning methods,and analyzes the dynamic biological characteristics of soybean’s key sRNA resistant to Phytophthora infestans infection.The research results in this paper provide a data basis for soybean reverse regulation of Phytophthora sojae,and provide a new perspective and approach for new prevention and control of soybean root rot.Besides,this paper also provides a general data analysis scheme for the study of antifungal pathogenicity of other plants.