A Research on Prediction of Polyadenylation Sites Based on Neural Network
With the extensive application of machine learning algorithms in bioinformatics,more and more computer researchers are beginning to focus on this field.Polyadenylation of messenger RNA(mRNA)is one of the key steps of gene expression in eukaryotes,polyadenylation site marks the end of transcription,it is of great significance to explore prediction of the site of gene sequences encoding gene.In this study,Arabidopsis gene sequences,that is representative in plants,were used as the object of study.First,we used the k-mer scheme and position probability matrix(PPM)to extract useful feature information in the sequences.Then,the principal component analysis(PCA)was used to remove the redundant features.Finally,we used the neural network method for the prediction of polyadenylation sites.The results show that the accuracy,sensitivity and specificity of the experiment are 0.9608,0.9521 and 0.9695,respectively.Comparison of previous studies,the experimental results have been greatly improved.
Polyadenylation Poly(A) sites Machine learning Neural network Neuralnet
Li Ma Ming Yang Kang Sun Tian Li Fang Wang Yue Li
College of Computer and Information Science,Southwest University of China,Chongqing 400715,China State Key Laboratory of Silkworm Genome Biology,Southwest University,Chongqing 400715,China College of life Sciences,Southwest University of China,Chongqing 400715,China
国际会议
重庆
英文
799-803
2017-10-03（万方平台首次上网日期，不代表论文的发表时间）