@article{Sinha:Nikolajewa:Szafranski:Accur_predi_NAGNA:NAR2009,
author = {Sinha, Rileen and Nikolajewa, Swetlana and Szafranski, 
          Karol and Hiller, Michael and Jahn, Niels and Huse, Klaus 
          and Platzer, Matthias and Backofen, Rolf},
title = {Accurate prediction of {NAGNAG} alternative splicing},
journal = {NAR},
year = {2009},
doi = {10.1093/nar/gkp220},
volume = {37},
user = {backofen},
pmid = {19359358},
pages = {3569-79},
number = {11},
issn = {1362-4962},
abstract = {Alternative splicing (AS) involving NAGNAG tandem acceptors 
            is an evolutionarily widespread class of AS. Recent 
            predictions of alternative acceptor usage reported better 
            results for acceptors separated by larger distances, than 
            for NAGNAGs. To improve the latter, we aimed at the use of 
            Bayesian networks (BN), and extensive experimental 
            validation of the predictions. Using carefully constructed 
            training and test datasets, a balanced sensitivity and 
            specificity of >or=92% was achieved. A BN trained on the 
            combined dataset was then used to make predictions, and 81% 
            (38/47) of the experimentally tested predictions were 
            verified. Using a BN learned on human data on six other 
            genomes, we show that while the performance for the 
            vertebrate genomes matches that achieved on human data, 
            there is a slight drop for Drosophila and worm. Lastly, 
            using the prediction accuracy according to experimental 
            validation, we estimate the number of yet undiscovered 
            alternative NAGNAGs. State of the art classifiers can 
            produce highly accurate prediction of AS at NAGNAGs, 
            indicating that we have identified the major features of the 
            'NAGNAG-splicing code' within the splice site and its 
            immediate neighborhood. Our results suggest that the 
            mechanism behind NAGNAG AS is simple, stochastic, and 
            conserved among vertebrates and beyond.}
}