BioWeka is a Java-based extension to the Weka framework for data mining [1], and like Weka it is licensed under the GPL. It adds the following functionality to the Weka framework:

• Loading FASTA, GenBank, EMBL and Swiss-Prot sequence files
• Loading XML files, e.g. MAGE-ML, ProML and InterProScan result sets
• Loading tab-delimited microarray data, e.g. TIGR, Stanford and Spot
• Classification based on BLAST or PSI-BLAST
• Classification based on alignments (local, global and secondary structure element)
• Classification of DNA/RNA sequences based on Eclat [2]
• Translation of sequences (DNA to RNA to Protein, DNA/RNA to its reverse complement)
• Generation of the open reading frames of DNA/RNA sequences
• Analysis of amino acid properties based on the Amino Acid Index database (AAindex)
• Calculation of codon frequencies or amino acid composition
• Normalization of numeric feature vectors
• Additional Weka utilities: Merge ARFF files, save ARFF files in a sequence format and create filter pipelines

Version 0.4 has just been released.

Feedback is welcome! Send it to
bioweka-users[at]lists.sourceforge.net.

URL

http://www.bioweka.org

References:
1. http://www.cs.waikato.ac.nz/ml/weka/
2. http://mips.gsf.de/proj/est/index.jsp