estrain@2: #!/usr/bin/env python3
estrain@2: 
estrain@2: import argparse
estrain@2: import os,subprocess
estrain@2: import pickle
estrain@2: 
estrain@2: ### SeqSero Kmer
estrain@2: def parse_args():
estrain@2:     "Parse the input arguments, use '-h' for help."
estrain@2:     parser = argparse.ArgumentParser(usage='Just type "SeqSero2_update_kmer_database.py", it will update kmer database automatically')
estrain@2:     return parser.parse_args()
estrain@2: 
estrain@2: def reverse_complement(sequence):
estrain@2:     complement = {
estrain@2:         'A': 'T',
estrain@2:         'C': 'G',
estrain@2:         'G': 'C',
estrain@2:         'T': 'A',
estrain@2:         'N': 'N',
estrain@2:         'M': 'K',
estrain@2:         'R': 'Y',
estrain@2:         'W': 'W',
estrain@2:         'S': 'S',
estrain@2:         'Y': 'R',
estrain@2:         'K': 'M',
estrain@2:         'V': 'B',
estrain@2:         'H': 'D',
estrain@2:         'D': 'H',
estrain@2:         'B': 'V'
estrain@2:     }
estrain@2:     return "".join(complement[base] for base in reversed(sequence))
estrain@2: 
estrain@2: def multifasta_dict(multifasta):
estrain@2:     multifasta_list = [
estrain@2:         line.strip() for line in open(multifasta, 'r') if len(line.strip()) > 0
estrain@2:     ]
estrain@2:     headers = [i for i in multifasta_list if i[0] == '>']
estrain@2:     multifasta_dict = {}
estrain@2:     for h in headers:
estrain@2:         start = multifasta_list.index(h)
estrain@2:         for element in multifasta_list[start + 1:]:
estrain@2:             if element[0] == '>':
estrain@2:                 break
estrain@2:             else:
estrain@2:                 if h[1:] in multifasta_dict:
estrain@2:                     multifasta_dict[h[1:]] += element
estrain@2:                 else:
estrain@2:                     multifasta_dict[h[1:]] = element
estrain@2:     return multifasta_dict
estrain@2: 
estrain@2: def createKmerDict_reads(list_of_strings, kmer):
estrain@2:     kmer_table = {}
estrain@2:     for string in list_of_strings:
estrain@2:         sequence = string.strip('\n')
estrain@2:         for i in range(len(sequence) - kmer + 1):
estrain@2:             new_mer = sequence[i:i + kmer].upper()
estrain@2:             new_mer_rc = reverse_complement(new_mer)
estrain@2:             if new_mer in kmer_table:
estrain@2:                 kmer_table[new_mer.upper()] += 1
estrain@2:             else:
estrain@2:                 kmer_table[new_mer.upper()] = 1
estrain@2:             if new_mer_rc in kmer_table:
estrain@2:                 kmer_table[new_mer_rc.upper()] += 1
estrain@2:             else:
estrain@2:                 kmer_table[new_mer_rc.upper()] = 1
estrain@2:     return kmer_table
estrain@2: 
estrain@2: def multifasta_to_kmers_dict(multifasta):
estrain@2:     multi_seq_dict = multifasta_dict(multifasta)
estrain@2:     lib_dict = {}
estrain@2:     for h in multi_seq_dict:
estrain@2:         lib_dict[h] = set(
estrain@2:             [k for k in createKmerDict_reads([multi_seq_dict[h]], 27)])
estrain@2:     return lib_dict
estrain@2: 
estrain@2: def get_salmid_invA_database(ex_dir):
estrain@2:   # read invA kmer and return it
estrain@2:   a = open(ex_dir + '/invA_mers_dict', 'rb')
estrain@2:   invA_dict = pickle.load(a)
estrain@2:   try:
estrain@2:     del invA_dict['version']
estrain@2:   except:
estrain@2:     pass
estrain@2:   return invA_dict
estrain@2: 
estrain@2: def get_salmid_rpoB_database(ex_dir):
estrain@2:   # read invA kmer and return it
estrain@2:   a = open(ex_dir + '/rpoB_mers_dict', 'rb')
estrain@2:   rpoB_dict = pickle.load(a)
estrain@2:   try:
estrain@2:     del rpoB_dict['version']
estrain@2:   except:
estrain@2:     pass
estrain@2:   return rpoB_dict
estrain@2: 
estrain@2: def main():
estrain@2:   args = parse_args()
estrain@2:   ex_dir = os.path.dirname(os.path.realpath(__file__))
estrain@2:   lib_dict = multifasta_to_kmers_dict(ex_dir + '/H_and_O_and_specific_genes.fasta')
estrain@2:   invA_dict=get_salmid_invA_database(ex_dir)
estrain@2:   #rpoB_dict=get_salmid_rpoB_database(ex_dir)
estrain@2:   lib_dict_new = lib_dict.copy()
estrain@2:   #print(len(lib_dict_new))
estrain@2:   lib_dict_new.update(invA_dict)
estrain@2:   #print(len(lib_dict_new))
estrain@2:   #lib_dict_new.update(rpoB_dict)
estrain@2:   #print(len(lib_dict_new))
estrain@2:   f = open(ex_dir + '/antigens.pickle', "wb")
estrain@2:   pickle.dump(lib_dict_new, f)
estrain@2:   f.close()
estrain@2: 
estrain@2: if __name__ == '__main__':
estrain@2:   main()