# align sequences

$ mafft sequences_for_HMM.faa > alignment_HMM.faa

# build HMM profile
## convert alignment to stockholm in Jalview, input alignment and output in .sto

$ hmmbuild protein_profile.hmm sequences_for_HMM.sto

# search into a database using HMM profile

$ hmmsearch --tblout results_table.txt protein_profile.hmm all_cyanobacteria_sequences.faa

# remove redundancy, cluster sequences, 95 % threshold

cd-hit -i protein_hits.faa -o protein_hits_r95.faa -c 0.95