pLM-Repeat: Exploiting the sequence representations of protein language models for sensitive repeat detection

deeprepeat_train_seq.fasta & deeprepeat_test_seq.fasta: sequence datasets used for training and testing the deeprepeat model

deeprepeat_weight.pt: deeprepeat model weight

repeatsdb_0.9.fasta & pdb30_after_symd4_sample.fasta: positive and negative datasets used for benchmarking HHrepID, RADAR and pLM-Repeat

afdb90_filtered_domain.csv: the filtered dataset after checking sequence and structural novelty and coiled coil fraction