Bayesian network prediction of splicing outcome at NAGNAG tandem acceptors

explanation of E/I
Nomenclature of NAGNAG alternative splicing: NAGNAG splicing results in two possible splice variants - splicing after the first AG results in the E (exonic, also known as proximal) isoform, whereas splicing after the second AG results in the I (intronic, also known as distal) isoform - accordingly, we refer to constitutively spliced NAGNAG acceptors as the E- or I-class, and to usage of both acceptors, or AS, as the EI-class.

upstream sequence
(at least 20 bases)
select your
downstream sequence
(at least 3 bases)

intron length
U3 (last base of upstream exon)

Features used for prediction of NAGNAG splicing

Two predictions are provided :


Accurate prediction of NAGNAG alternative splicing
Sinha R, Nikolajewa S, Szafranski K, Hiller M, Jahn N, Huse K, Platzer M,Backofen R: Accurate prediction of NAGNAG alternative splicing. Nucl Acids Res 2009, 37(11):3569-3579.
Maximum entropy modeling of short sequence motifs with applications to RNA splicing signals.
Yeo G, Burge CB.
J Comput Biol. 2004;11(2-3):377-94
Ian H. Witten and Eibe Frank (2005) 'Data Mining: Practical machine learning tools and techniques', 2nd Edition, Morgan Kaufmann, San Francisco, 2005

Training and test data for WEKA/BioBayesNet used in this work