OZS

# S1 import 16S forward and reverse sequences
vim forward.fa 
vim reverse.fa 

# S2 split the files
seqkit split -i forward.fa 
seqkit split -i reverse.fa 
# S3 rename the splits
rename "forward.part_" "" *
rename "reverse.part_" "" *
# S4 combine the paired ends
for i in `ls`;do mkdir ../../02comb/${i%%.fa}; cat $i >> ../../02comb/${i%%.fa}/$i; cat ../reverse.fa.split/$i >> ../../02comb/${i%%.fa}/$i; done
# S5 merge the paired-ends
for i in `ls`;do cap3 $i/${i}.fa; done
## extract the *.fa.cap.contigs
# S6 merge the contigs
mkdir ../03final
## need a python script to combined them

import os
files = os.listdir()
f1 = open("../03final/combined.fa","w")
for file in files:
  with open(file + "/" + file + ".fa.cap.contigs") as f_r:
    for line in f_r:
      if line.startswith(">"):
        f1.write(">" + str(file) + '\n')
      else:
        f1.write(line)



# S7 taxonomy
vsearch --usearch_global full_1127_1209.fa --db ../../../../silva/SILVA_138.2_SSURef_NR99_tax_silva.fasta --id 0.97 --blast6out results.b6 --strand both --top_hits_only