ENNAACT Dataset Download
The ENNAACT dataset is available for download in FASTA format. It contains 5957 peptide sequences, of which 659 are experimentally validated anticancer peptides, and 5298 are random non-secretory peptide sequences. The ENNAACT-HARD peptides are identified appropriately in the description lines.
ENNAACT+A1 Dataset Download
The ENNAACT+A1 dataset is available for download in FASTA format. The training set contains 574 experimentally validated anticancer peptides, and 5176 random non-secretory peptide sequences. The test set contains 181 anticancer peptides and 134 non-anticancer peptide sequences.
ENNAACT+A2 Dataset Download
The AntiCP 2.0 dataset, adapted for ENNAACT benchmarking, is available for download in FASTA format. The training set contains 716 experimentally validated anticancer peptides, and 571 random non-secretory peptide sequences. The test set contains 181 anticancer peptides and 134 non-anticancer peptide sequences. The original AntiCP 2.0 datasets can be downloaded at the AntiCP 2.0 website.
ENNAACT+B Dataset Download
The ENNAACT+B dataset is available for download in FASTA format. The training set contains 507 experimentally validated anticancer peptides, and 3623 random non-secretory peptide sequences. The test set contains 236 anticancer peptides andandand 1733 non-anticancer peptide sequences.