BiobaseTrainingData

RNA folding training data.

Parameter training for RNA secondary structure prediction tools requires data to train on. Since there are a number of different available formats, and handling them all in the training tools is a pain, we have this library and programs. MkTrainingData transforms different formats and they all produce a common "training data" format. This format is Haskell-readable (and only partially human-readable) line-by-line. Generating additional training data is therefor easy as one can just "cat" together different training files.

Note that several features are designed around extended RNA secondary structures.

Now with some filtering and manipulation options.