awk 'BEGIN{while((getline<"omi_ids_updated.txt")>0)l[">"$1]=1}/^>/{f=!l[$1]}f' genomic.fna > filtered_without_omi.fasta
#extract subseq
seqtk subseq omi_ids.fa omi_single_id.txt > omi_single_id.fa
#cat omi and all the rest
cat omi_single_id.fa filtered_without_omi.fasta > omi_single_id_plus_all.fa
#Extract unique kmer
./uniquekmer -f omi_single_id_plus_all.fa -k 19
# Extract the kmer of omi
seqtk subseq kmercollection.fasta ../omi_single_id.txt > omi_kmer19.fa
#reformat to 19mer
reformat.sh in=omi_kmer19.fa out=omi_kmer19_formated.fa fastawrap=19
#Extract and number the kmers
perl storeKmer.pl omi_kmer19_formated.fa > omi_kmer19_formated_numbered.fa
# cat all *.rd file
cat *.rd > all_reads_hits
#count the lines in each file -- go in folder
for FILE in *; do wc -l $FILE; done > all_hits_lines.txt
