PolyApred

PolyApred is a support vector machine (SVM) based method for the prediction of polyadenylation signal (PAS) in human coding DNA. In this method we developed mixed pattern as an input feature by using different nucleotides composition around Polyadenylation signal (PAS) and combined them with the binary pattern of PASes. The mono-nucleotide, di-nucleotide, tri-nucleotide and tetra-nucleotide composition of mixed pattern achieved accuracy of 0.56, 0.69 and 0.76 respectively. Finally we combined all of the 4 different mixed pattern to form a hybrid. These new hybrid were used as the input features to generate a model and implement to SVM and achieved the overall accuracy of 0.78.
The main aim of this server is to help users to identify the real polyadenylation signal (A[A/T]TAAA) from pseudo-PAS one.The input sequence should not be shorter than 206 nucleotide sequence and must be in fasta format.