Download training positive and negative examples, as well as cross-validation splits from the links below. Annotated FASTA-like formats report protein sequence, register annatotion (a-g for coiled coils or i for non-coiled coils), and oligomerization states (1=Parallel,2=Antiparallel,3=Trimer,4=Tetramer,i=non-coiled coils) in multiple consecutive lines for each protein.

• Training positive dataset (FASTA-like with annotations)
• Training negative dataset (FASTA)
• 10-fold cross-validation sets

Download blind test set positive and negative examples. Formats are the same as for training set.

• Blindtest positive dataset (FASTA-like with annotations)
• Blindtest negative dataset (FASTA)