úÎwx      Create  from various sources. EOne training data element. We can store sequence and known structure C (primary, secondary) as well as a predicted structure (stored, if  not.null). The 1 is how strongly this element should influence a  training system. ) is True, if the data element comes from I a source which knows about extended secondary structures, like the PDB.  Otherwise it is False. KNOTE During training, one should not penalize non-canonical predictions in L interior loops and multibranch loops, unless they hinder formation of true  pairs. ATODO at some point we will move toward pseudoknots and other fun  IImport from RNAstrand data. Each annotated pair is assumed to be of type  cWW. !Import from linearized FR3D data       9Left elements are filtered out, Right elements are kept.     IFilter out elements containing not enough base pairs (in relative terms) Error-checking filter.     Enumeratee producing  from a bytestring. Convenience function         BiobaseTrainingData-0.1.2.0Biobase.TrainingDataBiobase.TrainingData.ManipBiobase.TrainingData.FilterBiobase.TrainingData.ImportMkTrainingDatamkTrainingData TrainingDataprimary secondary predictedweightextendedKnowledgecommentsTDmanip fMinRelPairs fErrorCheckeneeTrainingDatafromFile$fMkTrainingDataRNAstrand$fMkTrainingDataLinFR3DremovePKfRemoveTriplets