def remove_similar_sequences(sequences, ratio, folder):
unique_sequences = []
unique_sequences.append(sequences[0])
for sequence in sequences[1:]:
similar = False
for unique_sequence in unique_sequences:
similarity = compare_string(sequence[1], unique_sequence[1])
if similarity>=float(ratio):
similar = True
break
if similar is False:
unique_sequences.append(sequence)
#convert 0.999 to 999 for appending to filename
file_append_ratio = ratio.split('.')[1]
strains_ratio = [unique_sequence[0] for unique_sequence in unique_sequences]
print('number of ', ratio, ' strains ', len(strains_ratio))
util.write_strains_to_csv(strains_ratio, folder + os.sep + 'unique_strains_' + file_append_ratio)
def run_dup_remover():
folder = sys.argv[1]
file1 = folder + os.sep + 'ha.afasta'
file2 = folder + os.sep + 'na.afasta'
file3 = folder + os.sep + 'm1.afasta'
file4 = folder + os.sep + 'm2.afasta'
file5 = folder + os.sep + 'np.afasta'
file6 = folder + os.sep + 'pb1.afasta'
file7 = folder + os.sep + 'pb2.afasta'
file8 = folder + os.sep + 'pa.afasta'
file9 = folder + os.sep + 'ns1.afasta'
file10 = folder + os.sep + 'ns2.afasta'
complete_sequences = concat_sequences(file1, file2, file3, file4, file5, file6, file7, file8, file9, file10)
print('number of complete sequences ', len(complete_sequences))
unique_sequences_dict = sequence_cleaner(complete_sequences)
print(unique_sequences_dict.values())
strains_100 = [strain for strain in unique_sequences_dict.values()]
util.write_strains_to_csv(strains_100, folder + os.sep + 'unique_strains_100')
print('number of sequences_100 ', len(strains_100))
def run_dup_remover():
folder = sys.argv[1]
file1 = folder + os.sep + 'ha.afasta'
file2 = folder + os.sep + 'na.afasta'
file3 = folder + os.sep + 'm1.afasta'
file4 = folder + os.sep + 'm2.afasta'
file5 = folder + os.sep + 'np.afasta'
file6 = folder + os.sep + 'pb1.afasta'
file7 = folder + os.sep + 'pb2.afasta'
file8 = folder + os.sep + 'pa.afasta'
file9 = folder + os.sep + 'ns1.afasta'
file10 = folder + os.sep + 'ns2.afasta'
complete_sequences = concat_sequences(file1, file2, file3, file4, file5, file6, file7, file8, file9, file10)
print('number of complete sequences ', len(complete_sequences))
print('length of complete sequence', len(complete_sequences[0][1]))
unique_sequences_dict = sequence_cleaner(complete_sequences)
strains_100 = [strain for strain in unique_sequences_dict.values()]
util.write_strains_to_csv(strains_100, folder + os.sep + 'unique_strains_100')
print('number of sequences_100 ', len(strains_100))
def remove_similar_sequences(sequences, ratio, folder):
unique_sequences = []
unique_sequences.append(sequences[0])
for sequence in sequences[1:]:
similar = False
for unique_sequence in unique_sequences:
similarity = compare_string(sequence[1], unique_sequence[1])
if similarity >= float(ratio):
similar = True
break
if similar is False:
unique_sequences.append(sequence)
#convert 0.999 to 999 for appending to filename
file_append_ratio = ratio.split('.')[1]
strains_ratio = [
unique_sequence[0] for unique_sequence in unique_sequences
]
print('number of ', ratio, ' strains ', len(strains_ratio))
util.write_strains_to_csv(
strains_ratio, folder + os.sep + 'unique_strains_' + file_append_ratio)
