The recognition of splicing sites is a very important step in the eukaryotic DNA sequence\nanalysis. Many scholars are working hard to improve the accuracy of identification.\nOur team carried out research on this issue based on support vector machine,\nwhich is one famous algorithm in data mining. The training and testing data is\nfrom the HS3D dataset, and excellent accuracy rate is achieved by nucleic acid sequence\northogonal coding and RBF core function, and the cross validation experiment\nhints that base pattern information is mainly located within 20 nucleotides upstream\nand downstream splice sites.
Loading....