%0 Journal Article %1 Vukusica:2007:G %A Vukusic, Ivana %A Grellscheid, Sushma Nagaraja %A Wiehe, Thomas %D 2007 %J Genomics %K Alternative Cassette Feature Intron Splice algorithms, exon, genetic matrix, programming, retention, signals splicing, %N 4 %P 471--479 %R doi:10.1016/j.ygeno.2007.01.001 %T Applying genetic programming to the prediction of alternative mRNA splice variants %V 89 %X Genetic programming (GP) can be used to classify a given gene sequence as either constitutively or alternatively spliced. We describe the principles of GP and apply it to a well-defined data set of alternatively spliced genes. A feature matrix of sequence properties, such as nucleotide composition or exon length, was passed to the GP system Discipulus To test its performance we concentrated on cassette exons (SCE) and retained introns (SIR). We analysed 27,519 constitutively spliced and 9641 cassette exons including their neighbouring introns; in addition we analysed 33316 constitutively spliced introns compared to 2712 retained introns. We find that the classifier yields highly accurate predictions on the SIR data with a sensitivity of 92.1percent and a specificity of 79.2percent. Prediction accuracies on the SCE data are lower, 47.3percent (sensitivity) and 70.9percent (specificity), indicating that alternative splicing of introns can be better captured by sequence properties than that of exons.

@article{Vukusica:2007:G, abstract = {Genetic programming (GP) can be used to classify a given gene sequence as either constitutively or alternatively spliced. We describe the principles of GP and apply it to a well-defined data set of alternatively spliced genes. A feature matrix of sequence properties, such as nucleotide composition or exon length, was passed to the GP system Discipulus To test its performance we concentrated on cassette exons (SCE) and retained introns (SIR). We analysed 27,519 constitutively spliced and 9641 cassette exons including their neighbouring introns; in addition we analysed 33316 constitutively spliced introns compared to 2712 retained introns. We find that the classifier yields highly accurate predictions on the SIR data with a sensitivity of 92.1percent and a specificity of 79.2percent. Prediction accuracies on the SCE data are lower, 47.3percent (sensitivity) and 70.9percent (specificity), indicating that alternative splicing of introns can be better captured by sequence properties than that of exons.}, added-at = {2008-06-19T17:46:40.000+0200}, author = {Vukusic, Ivana and Grellscheid, Sushma Nagaraja and Wiehe, Thomas}, biburl = {https://www.bibsonomy.org/bibtex/2c1d3c825287c6d5c37963752b14b040b/brazovayeye}, doi = {doi:10.1016/j.ygeno.2007.01.001}, interhash = {748044262f98c447142246897b595533}, intrahash = {c1d3c825287c6d5c37963752b14b040b}, journal = {Genomics}, keywords = {Alternative Cassette Feature Intron Splice algorithms, exon, genetic matrix, programming, retention, signals splicing,}, month = {April}, notes = {PMID: 17276654 [PubMed - in process]}, number = 4, pages = {471--479}, timestamp = {2008-06-19T17:53:43.000+0200}, title = {Applying genetic programming to the prediction of alternative m{RNA} splice variants}, volume = 89, year = 2007 }