@article {bioinflmu-513, title = {{BioWeka--extending the Weka framework for bioinformatics}}, journal = {Bioinformatics}, volume = {23}, number = {5}, year = {2007}, pages = {651-653}, abstract = {Given the growing amount of biological data, data mining methods have become an integral part of bioinformatics research. Unfortunately, standard data mining tools are often not sufficiently equipped for handling raw data such as e.g. amino acid sequences. One popular and freely available framework that contains many well-known data mining algorithms is the Waikato Environment for Knowledge Analysis (Weka). In the BioWeka project, we introduce various input formats for bioinformatics data and bioinformatics methods like alignments to Weka. This allows users to easily combine them with Weka{\textquoteright}s classification, clustering, validation and visualization facilities on a single platform and therefore reduces the overhead of converting data between different data formats as well as the need to write custom evaluation procedures that can deal with many different programs. We encourage users to participate in this project by adding their own components and data formats to BioWeka. Availability: The software, documentation and tutorial are available at http://www.bioweka.org.}, doi = {10.1093/bioinformatics/btl671}, author = {Jan Erik Gewehr and Martin Szugat and Ralf Zimmer} }