DATASETS with the DISORDER-ANNOTATED PROTEINS
Each protein is represented using 3 lines:
1. > DisProtID (can be used to trace the evidence for the annotations in the DisProt database)
2. Sequence
3. Annotation of binding: "0" non-disordered (used as negative for training and evaluation); "1" disordered and DNA-binding (used as positive for training and evaluation); "2" disordered and binding a non-DNA ligand (used as negative for training and evaluation, and used to assess cross-predictions); "3" disordered and has a non-binding function (used as negative for training and evaluation); "4" disordered with no function annotation (used as negative for training and evaluation)


DATASETS with the STRUCTURE-ANNOTATED PROTEINS
Each protein is represented using 3 lines:
1. > UniProtID (can be used to trace the evidence for the annotations in the BioLip database)
2. Sequence
3. Annotation of binding: "0" non-binding (used as negative for training and evaluation); "1" DNA-binding (used as positive for training and evaluation); "2" binding a non-DNA ligand (used as negative for training and evaluation, and used to assess cross-predictions)