A Novel Method for Splice Sites Recognition Using Comprehensive Information

To identify splice sites more accurately and efficiently, a method for the recognition of splice sites based on comprehensive information is proposed. By analyzing the splicing signals, splicing sequences, secondary structures of flank sequence, different splicing factor mechanism of action and other characteristics of donor sites and acceptor sites, donor sites identification signal model, acceptor sites identification signal model, donor sites identification sequence model, acceptor sites identification sequence model were built respectively. Then the Mfold package in Vienna soft was used to predict the most stable secondary structure of flank sequences. The traditional four-letter alphabet was converted into eight-letter alphabet sequence. The sequence-structure combination strings were used for training signal models, sequence models, then recognized splice sites by the well trained models. Our results show that the accuracy of splice site recognition is greater than 95%, suggesting that the method has great potential to achieve a good performance for splice sites identification.