name: remap
task_type: cluster

max_protein_length: 1998

cluster_dna_full: true
cluster_dna_peaks: true
cluster_protein: false

dna_full:
  input_map_path: dpacman/data_files/processed/fimo/post_fimo/fimo_hits_only/maps/dna_seqid_to_dna_sequence.json
  fasta_path: dpacman/data_files/processed/mmseqs/inputs/fimo_hits_only/dna_full.fasta
  output_dir: dpacman/data_files/processed/mmseqs/outputs/fimo_hits_only/dna_full
  mmseqs:
    min_seq_id: 0.3
    c: 0.8
    cov_mode: 0
    cluster_mode: 0

dna_peaks:
  input_map_path: dpacman/data_files/processed/fimo/post_fimo/fimo_hits_only/maps/peak_seqid_to_peak_sequence.json
  fasta_path: dpacman/data_files/processed/mmseqs/inputs/fimo_hits_only/dna_peaks.fasta
  output_dir: dpacman/data_files/processed/mmseqs/outputs/fimo_hits_only/dna_peaks
  mmseqs:
    min_seq_id: 0.3
    c: 0.8
    cov_mode: 0
    cluster_mode: 0

protein:
  input_map_path: dpacman/data_files/processed/fimo/post_fimo/fimo_hits_only/maps/tr_seqid_to_tr_sequence.json
  fasta_path: dpacman/data_files/processed/mmseqs/inputs/fimo_hits_only/protein.fasta
  output_dir: dpacman/data_files/processed/mmseqs/outputs/fimo_hits_only/protein
  mmseqs:
    min_seq_id: 0.3
    c: 0.8
    cov_mode: 0
    cluster_mode: 0

input_data_path: /vast/projects/pranam/lab/sophie/DPACMAN/dpacman/data_files/processed/fimo/post_fimo/fimo_hits_only/remap2022_crm_fimo_output_q_processed_seed0.parquet
path_to_mmseqs: /vast/projects/pranam/lab/shared/mmseqs

out_dir: na
final_csv: na