Datasets

Download training set
Download blind test sets used for benchmark
Download cross-validation split

Both the training set and the blind test sets are available in a format similar to a fasta file, where for each protein you have three lines showing respectively: i) the '>' character followed by the protein ID ii) the residue sequence iii) the class of each residue (1 for Interaction Site, 0 otherwise).
Inside the ISPRED_Blind_Test_Sets folder you will find all the blind sets used for benchmark (Dset335, Dset448, Hetero_TE, Homo_TE).
Inside the cross_validation folder you will find 10 text files (split0-split9), each containing the protein IDs belonging to the corresponding subset used in cross-validation.