#####################################################
#				PaleAle 5.0 datasets				#
#####################################################

> set.dataset was used in 5-fold cross-validation to train and tune the models.

>independent_test_set.dataset was used only to assess the performances of the final system and other recent predictors.

>The format of the datasets is as follows:
two lines header: 
number_of_proteins
attributes classes #45 4

Following the header are the protein records, five lines per protein:
1) pdb_id
2) length
3) encoded input # (length * 44) floats + 1 (legth/1000)
4) relative solvent accessibility
5) blank

>set.fasta and independent_test_set.fasta are the very same datasets containing only the sequences.

>This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (http://creativecommons.org/licenses/by-nc-sa/4.0/).

>Please email us at gianluca.pollastri@ucd.ie if you wish to use it for commercial or any other purposes not permitted by the CC BY-NC-SA 4.0.