Features generated for computational splice-site prediction correspond to functional elements

Rezarta Islamaj Dogan¹^,2 , Lise Getoor¹ , W John Wilbur² and Stephen M Mount³^,4

¹Computer Science Department, University of Maryland, College Park, MD 20742, USA

²National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA

³Department of Cell Biology and Molecular Genetics, University of Maryland, College Park, MD 20742, USA

⁴Center for Bioinformatics and Computational Biology, University of Maryland, College Park, MD 20742, USA

author email corresponding author email

BMC Bioinformatics 2007, 8:410doi:10.1186/1471-2105-8-410


Published:	24 October 2007

Additional files

Additional file 1:

FGA identified features that contribute to Table 2. (Table2_features_A3mer3.txt). A text file with the complete list of features associated with the branch-point interval [-40,-20], from the feature set A-3mer3. The features are ranked according to the absolute value or their assigned weight. The top-scoring 20 features of this list are shown in Table 2.

Format: TXT Size: 13KB Download file

Additional file 2:

Features that contribute to Figure 2 and other features that show similar behaviour (tetramers-of-figure2.txt). A text file with the complete list of selected features from feature set A-3mer1 [-60,-5].

Format: TXT Size: 195KB Download file

Additional file 3:

FGA identified hexamers in acceptor splice-site prediction and donor splice-site prediction (FGA-hexamers.txt). A text file with the complete list of hexamers that our method indicates they are likely to be ESEs or ESSs.

Format: TXT Size: 7KB Download file

Additional file 4:

FGA-generated features produce a significant overlap with experimentally identified ESE sequences table in [22] (ESE-ESS-overlap-sequences.xls). The first worksheet in the Excel file contains the table of experimentally identified ESE sequences in [22] and the overlap with the FGA identified hexamers from feature sets A-6mer [0,80] and D-6mer [2,82]. For each comparison an exact match is required. We compared the positively weighted hexamer sets against the ESE sequences, and the negatively weighted hexamer sets against ESS sequences. The second worksheet contains the overlap of the ESE sequences with the FGA identified hexamers that are not included in RescueESE, AstESR or ChPESE sets.

Format: XLS Size: 48KB Download file

This file can be viewed with: Microsoft Excel Viewer

Additional file 5:

FGA-generated features produce significant overlap with computationally identified lists of exonic splicing regulator signals [23,26] (candidate-ese-esr-overlap.txt). A text file with the list of FGA features overlapping with RescueESE and AstESR exonic splicing regulator lists.

Format: TXT Size: 3KB Download file