@Article{Sinha:Hiller:Pudimat:Impro_ident_conse:2008,
  author =	 {R. Sinha and M. Hiller and R. Pudimat and U. Gausmann and 
                  M. Platzer and R. Backofen},
  title =	 {Improved identification of conserved cassette exons using 
                  {Bayesian} networks},
  journal =	 {BMC Bioinformatics},
  year =	 {2008},
  issn  =        {1471-2105},
  volume =	 {9},
  number =	 {1},
  pages =	 {477},
  user =	 {backofen},
  pmid =	 {19014490},
  doi = 	 {10.1186/1471-2105-9-477},
  abstract =	 {ABSTRACT: BACKGROUND: Alternative splicing is a major 
                  contributor to the diversity of eukaryotic transcriptomes 
                  and proteomes. Currently, large scale detection of 
                  alternative splicing using expressed sequence tags (ESTs) or 
                  microarrays does not capture all alternative splicing 
                  events. Moreover, for many species genomic data is being 
                  produced at a far greater rate than corresponding transcript 
                  data, hence in silico methods of predicting alternative 
                  splicing have to be improved. RESULTS: Here, we show that 
                  the use of Bayesian networks (BNs) allows accurate 
                  prediction of evolutionary conserved exon skipping events. 
                  At a stringent false positive rate of 0.5%, our BN achieves 
                  an improved true positive rate of 61%, compared to a 
                  previously reported 50% on the same dataset using support 
                  vector machines (SVMs). Incorporating several novel 
                  discriminative features such as intronic splicing regulatory 
                  elements leads to the improvement. Features related to mRNA 
                  secondary structure increase the prediction performance, 
                  corroborating previous findings that secondary structures 
                  are important for exon recognition. Random labelling tests 
                  rule out overfitting. Cross-validation on another dataset 
                  confirms the increased performance. When using the same 
                  dataset and the same set of features, the BN matches the 
                  performance of an SVM in earlier literature. Remarkably, we 
                  could show that about half of the exons which are labelled 
                  constitutive but receive a high probability of being 
                  alternative by the BN, are in fact alternative exons 
                  according to the latest EST data. Finally, we predict exon 
                  skipping without using conservation-based features, and 
                  achieve a true positive rate of 29% at a false positive rate 
                  of 0.5%. CONCLUSION: BNs can be used to achieve accurate 
                  identification of alternative exons and provide clues about 
                  possible dependencies between relevant features. The 
                  near-identical performance of the BN and SVM when using the 
                  same features shows that good classification depends more on 
                  features than on the choice of classifier. Conservation 
                  based features continue to be the most informative, and 
                  hence distinguishing alternative exons from constitutive 
                  ones without using conservation based features remains a 
                  challenging problem.}
}