BioWeka 0.4

The new release 0.4 of BioWeka combines the packages BioWeka, XML-Stylesheets, FoldRec and BioJava 1.4 Extensions in one single distribution: bioweka-0.4.zip. This ZIP files contains

• the bioweka-0.4.jar library, its source code and documentation
• the updated GenericPropertiesCreator.props file
• the required JAR libraries for BioJava, Apache Commons (only those which are required by BioJava) and JAligner
• the FoldRec and BioJava 1.4 Extensions libraries (these BioWeka packages are not separately available any longer)
• the most recent AAindex database
• the substitution matrices from the NCBI for the usage with the aligners GlobalAligner and LocalAligner (alias JAligner)
• a patch for the converter.pl perl script of the InterProScan standalone application
• the latest release (0.4) of XML-stylesheets including the XSLT stylesheet to load MAGE-ML files directly into Weka (this BioWeka package is not separately available any longer)
• the align_learn.pl perl script for converting sequence alignments in the FASTA format to the ARFF format

Note: Weka is not included and most be downloaded separately.

In addition, there is some new functionality:

• The AlignmentScorer filter performs an all-against-all alignment using a specified Aligner and stores the scores within the data set.
• Such a data set can be used in conjunction with the new ScoreClassifier class to classify sequences based on the precomputed alignment (scores). This is a replacement for the SimpleAlignmentClassifier which reduces the time effort to do a cross validation of an alignment classification.
• Save filter to export ARFF files into another format (e.g. FASTA) from within the Explorer GUI.
• Some minor bug fixes ...