GAKNN is a data mining software for gene annotation data. GAKNN is built with k- Nearest Neighbour algorithm optimized by the genetic algorithm. Gene annotation datasets saved under .csv or .arff formats with Gene Ontology or FunCat categorization can use GAKNN to predict gene functions.
ktdata is a C++ library for accessing tabular data, like from CSV files. Its goals are:
1. object design
2. portability (Linux and Windows support at least)
3. high performance
4. support for common data file formats, like CSV, ARFF (Weka), etc.