annotate SalmID.py @ 1:f8e2c8bc540d tip

Uploaded
author estrain
date Wed, 02 Oct 2019 16:59:09 -0400
parents 18c8b4d6ab1e
children
rev   line source
estrain@0 1 #!/usr/bin/env python3
estrain@0 2
estrain@0 3
estrain@0 4 import gzip
estrain@0 5 import io
estrain@0 6 import pickle
estrain@0 7 import os
estrain@0 8 import sys
estrain@0 9
estrain@0 10 from argparse import ArgumentParser
estrain@0 11 try:
estrain@0 12 from .version import SalmID_version
estrain@0 13 except ImportError:
estrain@0 14 SalmID_version = "version unknown"
estrain@0 15
estrain@0 16
estrain@0 17 def reverse_complement(sequence):
estrain@0 18 """return the reverse complement of a nucleotide (including IUPAC ambiguous nuceotide codes)"""
estrain@0 19 complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'N': 'N', 'M': 'K', 'R': 'Y', 'W': 'W',
estrain@0 20 'S': 'S', 'Y': 'R', 'K': 'M', 'V': 'B', 'H': 'D', 'D': 'H', 'B': 'V'}
estrain@0 21 return "".join(complement[base] for base in reversed(sequence))
estrain@0 22
estrain@0 23
estrain@0 24 def parse_args():
estrain@0 25 "Parse the input arguments, use '-h' for help."
estrain@0 26 parser = ArgumentParser(description='SalmID - rapid Kmer based Salmonella identifier from sequence data')
estrain@0 27 # inputs
estrain@0 28 parser.add_argument('-v', '--version', action='version', version='%(prog)s ' + SalmID_version)
estrain@0 29 parser.add_argument(
estrain@0 30 '-i', '--input_file', type=str, required=False, default='None', metavar='your_fastqgz',
estrain@0 31 help='Single fastq.gz file input, include path to file if file is not in same directory ')
estrain@0 32 parser.add_argument(
estrain@0 33 '-e', '--extension', type=str, required=False, default='.fastq.gz', metavar='file_extension',
estrain@0 34 help='File extension, if specified without "--input_dir", SalmID will attempt to ID all files\n' +
estrain@0 35 ' with this extension in current directory, otherwise files in input directory')
estrain@0 36
estrain@0 37 parser.add_argument(
estrain@0 38 '-d', '--input_dir', type=str, required=False, default='.', metavar='directory',
estrain@0 39 help='Directory which contains data for identification, when not specified files in current directory will be analyzed.')
estrain@0 40 parser.add_argument(
estrain@0 41 '-r', '--report', type=str, required=False, default='percentage', metavar='percentage, coverage or taxonomy',
estrain@0 42 help='Report either percentage ("percentage") of clade specific kmers recovered, average kmer-coverage ("cov"), or '
estrain@0 43 'taxonomy (taxonomic species ID, plus observed mean k-mer coverages and expected coverage).')
estrain@0 44 parser.add_argument(
estrain@0 45 '-m', '--mode', type=str, required=False, default='quick', metavar='quick or thorough',
estrain@0 46 help='Quick [quick] or thorough [thorough] mode')
estrain@0 47 if len(sys.argv) == 1:
estrain@0 48 parser.print_help(sys.stderr)
estrain@0 49 sys.exit(1)
estrain@0 50 return parser.parse_args()
estrain@0 51
estrain@0 52
estrain@0 53 def get_av_read_length(file):
estrain@0 54 """Samples the first 100 reads from a fastq file and return the average read length."""
estrain@0 55 i = 1
estrain@0 56 n_reads = 0
estrain@0 57 total_length = 0
estrain@0 58 if file.endswith(".gz"):
estrain@0 59 file_content = io.BufferedReader(gzip.open(file))
estrain@0 60 else:
estrain@0 61 file_content = open(file, "r").readlines()
estrain@0 62 for line in file_content:
estrain@0 63 if i % 4 == 2:
estrain@0 64 total_length += len(line.strip())
estrain@0 65 n_reads += 1
estrain@0 66 i += 1
estrain@0 67 if n_reads == 100:
estrain@0 68 break
estrain@0 69 return total_length / 100
estrain@0 70
estrain@0 71
estrain@0 72 def createKmerDict_reads(list_of_strings, kmer):
estrain@0 73 """Count occurence of K-mers in a list of strings
estrain@0 74
estrain@0 75 Args:
estrain@0 76 list_of_strings(list of str): nucleotide sequences as a list of strings
estrain@0 77 kmer(int): length of the K-mer to count
estrain@0 78
estrain@0 79 Returns:
estrain@0 80 dict: dictionary with kmers as keys, counts for each kmer as values"""
estrain@0 81 kmer_table = {}
estrain@0 82 for string in list_of_strings:
estrain@0 83 sequence = string.strip('\n')
estrain@0 84 if len(sequence) >= kmer:
estrain@0 85 for i in range(len(sequence) - kmer + 1):
estrain@0 86 new_mer = sequence[i:i + kmer]
estrain@0 87 new_mer_rc = reverse_complement(new_mer)
estrain@0 88 if new_mer in kmer_table:
estrain@0 89 kmer_table[new_mer.upper()] += 1
estrain@0 90 else:
estrain@0 91 kmer_table[new_mer.upper()] = 1
estrain@0 92 if new_mer_rc in kmer_table:
estrain@0 93 kmer_table[new_mer_rc.upper()] += 1
estrain@0 94 else:
estrain@0 95 kmer_table[new_mer_rc.upper()] = 1
estrain@0 96 return kmer_table
estrain@0 97
estrain@0 98
estrain@0 99 def target_read_kmerizer_multi(file, k, kmerDict_1, kmerDict_2, mode):
estrain@0 100 mean_1 = None
estrain@0 101 mean_2 = None
estrain@0 102 i = 1
estrain@0 103 n_reads_1 = 0
estrain@0 104 n_reads_2 = 0
estrain@0 105 total_coverage_1 = 0
estrain@0 106 total_coverage_2 = 0
estrain@0 107 reads_1 = []
estrain@0 108 reads_2 = []
estrain@0 109 total_reads = 0
estrain@0 110 if file.endswith(".gz"):
estrain@0 111 file_content = io.BufferedReader(gzip.open(file))
estrain@0 112 else:
estrain@0 113 file_content = open(file, "r").readlines()
estrain@0 114 for line in file_content:
estrain@0 115 start = int((len(line) - k) // 2)
estrain@0 116 if i % 4 == 2:
estrain@0 117 total_reads += 1
estrain@0 118 if file.endswith(".gz"):
estrain@0 119 s1 = line[start:k + start].decode()
estrain@0 120 line = line.decode()
estrain@0 121 else:
estrain@0 122 s1 = line[start:k + start]
estrain@0 123 if s1 in kmerDict_1:
estrain@0 124 n_reads_1 += 1
estrain@0 125 total_coverage_1 += len(line)
estrain@0 126 reads_1.append(line)
estrain@0 127 if s1 in kmerDict_2:
estrain@0 128 n_reads_2 += 1
estrain@0 129 total_coverage_2 += len(line)
estrain@0 130 reads_2.append(line)
estrain@0 131 i += 1
estrain@0 132 if mode == 'quick':
estrain@0 133 if total_coverage_2 >= 800000:
estrain@0 134 break
estrain@0 135
estrain@0 136 if len(reads_1) == 0:
estrain@0 137 kmer_Dict1 = {}
estrain@0 138 else:
estrain@0 139 kmer_Dict1 = createKmerDict_reads(reads_1, k)
estrain@0 140 mers_1 = set([key for key in kmer_Dict1])
estrain@0 141 mean_1 = sum([kmer_Dict1[key] for key in kmer_Dict1]) / len(mers_1)
estrain@0 142 if len(reads_2) == 0:
estrain@0 143 kmer_Dict2 = {}
estrain@0 144 else:
estrain@0 145 kmer_Dict2 = createKmerDict_reads(reads_2, k)
estrain@0 146 mers_2 = set([key for key in kmer_Dict2])
estrain@0 147 mean_2 = sum([kmer_Dict2[key] for key in kmer_Dict2]) / len(mers_2)
estrain@0 148 return kmer_Dict1, kmer_Dict2, mean_1, mean_2, total_reads
estrain@0 149
estrain@0 150
estrain@0 151 def mean_cov_selected_kmers(iterable, kmer_dict, clade_specific_kmers):
estrain@0 152 '''
estrain@0 153 Given an iterable (list, set, dictrionary) returns mean coverage for the kmers in iterable
estrain@0 154 :param iterable: set, list or dictionary containing kmers
estrain@0 155 :param kmer_dict: dictionary with kmers as keys, kmer-frequency as value
estrain@0 156 :param clade_specific_kmers: list, dict or set of clade specific kmers
estrain@0 157 :return: mean frequency as float
estrain@0 158 '''
estrain@0 159 if len(iterable) == 0:
estrain@0 160 return 0
estrain@0 161 return sum([kmer_dict[value] for value in iterable]) / len(clade_specific_kmers)
estrain@0 162
estrain@0 163
estrain@0 164 def kmer_lists(query_fastq_gz, k,
estrain@0 165 allmers, allmers_rpoB,
estrain@0 166 uniqmers_bongori,
estrain@0 167 uniqmers_I,
estrain@0 168 uniqmers_IIa,
estrain@0 169 uniqmers_IIb,
estrain@0 170 uniqmers_IIIa,
estrain@0 171 uniqmers_IIIb,
estrain@0 172 uniqmers_IV,
estrain@0 173 uniqmers_VI,
estrain@0 174 uniqmers_VII,
estrain@0 175 uniqmers_VIII,
estrain@0 176 uniqmers_bongori_rpoB,
estrain@0 177 uniqmers_S_enterica_rpoB,
estrain@0 178 uniqmers_Escherichia_rpoB,
estrain@0 179 uniqmers_Listeria_ss_rpoB,
estrain@0 180 uniqmers_Lmono_rpoB,
estrain@0 181 mode):
estrain@0 182 dict_invA, dict_rpoB, mean_invA, mean_rpoB, total_reads = target_read_kmerizer_multi(query_fastq_gz, k, allmers,
estrain@0 183 allmers_rpoB, mode)
estrain@0 184 target_mers_invA = set([key for key in dict_invA])
estrain@0 185 target_mers_rpoB = set([key for key in dict_rpoB])
estrain@0 186 if target_mers_invA == 0:
estrain@0 187 print('No reads found matching invA, no Salmonella in sample?')
estrain@0 188 else:
estrain@0 189 p_bongori = (len(uniqmers_bongori & target_mers_invA) / len(uniqmers_bongori)) * 100
estrain@0 190 p_I = (len(uniqmers_I & target_mers_invA) / len(uniqmers_I)) * 100
estrain@0 191 p_IIa = (len(uniqmers_IIa & target_mers_invA) / len(uniqmers_IIa)) * 100
estrain@0 192 p_IIb = (len(uniqmers_IIb & target_mers_invA) / len(uniqmers_IIb)) * 100
estrain@0 193 p_IIIa = (len(uniqmers_IIIa & target_mers_invA) / len(uniqmers_IIIa)) * 100
estrain@0 194 p_IIIb = (len(uniqmers_IIIb & target_mers_invA) / len(uniqmers_IIIb)) * 100
estrain@0 195 p_VI = (len(uniqmers_VI & target_mers_invA) / len(uniqmers_VI)) * 100
estrain@0 196 p_IV = (len(uniqmers_IV & target_mers_invA) / len(uniqmers_IV)) * 100
estrain@0 197 p_VII = (len(uniqmers_VII & target_mers_invA) / len(uniqmers_VII)) * 100
estrain@0 198 p_VIII = (len(uniqmers_VIII & target_mers_invA) / len(uniqmers_VIII)) * 100
estrain@0 199 p_bongori_rpoB = (len(uniqmers_bongori_rpoB & target_mers_rpoB) / len(uniqmers_bongori_rpoB)) * 100
estrain@0 200 p_Senterica = (len(uniqmers_S_enterica_rpoB & target_mers_rpoB) / len(uniqmers_S_enterica_rpoB)) * 100
estrain@0 201 p_Escherichia = (len(uniqmers_Escherichia_rpoB & target_mers_rpoB) / len(uniqmers_Escherichia_rpoB)) * 100
estrain@0 202 p_Listeria_ss = (len(uniqmers_Listeria_ss_rpoB & target_mers_rpoB) / len(uniqmers_Listeria_ss_rpoB)) * 100
estrain@0 203 p_Lmono = (len(uniqmers_Lmono_rpoB & target_mers_rpoB) / len(uniqmers_Lmono_rpoB)) * 100
estrain@0 204 bongori_invA_cov = mean_cov_selected_kmers(uniqmers_bongori & target_mers_invA, dict_invA, uniqmers_bongori)
estrain@0 205 I_invA_cov = mean_cov_selected_kmers(uniqmers_I & target_mers_invA, dict_invA, uniqmers_I)
estrain@0 206 IIa_invA_cov = mean_cov_selected_kmers(uniqmers_IIa & target_mers_invA, dict_invA, uniqmers_IIa)
estrain@0 207 IIb_invA_cov = mean_cov_selected_kmers(uniqmers_IIb & target_mers_invA, dict_invA, uniqmers_IIb)
estrain@0 208 IIIa_invA_cov = mean_cov_selected_kmers(uniqmers_IIIa & target_mers_invA, dict_invA, uniqmers_IIIa)
estrain@0 209 IIIb_invA_cov = mean_cov_selected_kmers(uniqmers_IIIb & target_mers_invA, dict_invA, uniqmers_IIIb)
estrain@0 210 IV_invA_cov = mean_cov_selected_kmers(uniqmers_IV & target_mers_invA, dict_invA, uniqmers_IV)
estrain@0 211 VI_invA_cov = mean_cov_selected_kmers(uniqmers_VI & target_mers_invA, dict_invA, uniqmers_VI)
estrain@0 212 VII_invA_cov = mean_cov_selected_kmers(uniqmers_VII & target_mers_invA, dict_invA, uniqmers_VII)
estrain@0 213 VIII_invA_cov = mean_cov_selected_kmers(uniqmers_VIII & target_mers_invA, dict_invA, uniqmers_VIII)
estrain@0 214 S_enterica_rpoB_cov = mean_cov_selected_kmers((uniqmers_S_enterica_rpoB & target_mers_rpoB), dict_rpoB,
estrain@0 215 uniqmers_S_enterica_rpoB)
estrain@0 216 S_bongori_rpoB_cov = mean_cov_selected_kmers((uniqmers_bongori_rpoB & target_mers_rpoB), dict_rpoB,
estrain@0 217 uniqmers_bongori_rpoB)
estrain@0 218 Escherichia_rpoB_cov = mean_cov_selected_kmers((uniqmers_Escherichia_rpoB & target_mers_rpoB), dict_rpoB,
estrain@0 219 uniqmers_Escherichia_rpoB)
estrain@0 220 Listeria_ss_rpoB_cov = mean_cov_selected_kmers((uniqmers_Listeria_ss_rpoB & target_mers_rpoB), dict_rpoB,
estrain@0 221 uniqmers_Listeria_ss_rpoB)
estrain@0 222 Lmono_rpoB_cov = mean_cov_selected_kmers((uniqmers_Lmono_rpoB & target_mers_rpoB), dict_rpoB,
estrain@0 223 uniqmers_Lmono_rpoB)
estrain@0 224 coverages = [Listeria_ss_rpoB_cov, Lmono_rpoB_cov, Escherichia_rpoB_cov, S_bongori_rpoB_cov,
estrain@0 225 S_enterica_rpoB_cov, bongori_invA_cov, I_invA_cov, IIa_invA_cov, IIb_invA_cov,
estrain@0 226 IIIa_invA_cov, IIIb_invA_cov, IV_invA_cov, VI_invA_cov, VII_invA_cov, VIII_invA_cov]
estrain@0 227 locus_scores = [p_Listeria_ss, p_Lmono, p_Escherichia, p_bongori_rpoB, p_Senterica, p_bongori,
estrain@0 228 p_I, p_IIa, p_IIb, p_IIIa, p_IIIb, p_IV, p_VI, p_VII, p_VIII]
estrain@0 229 return locus_scores, coverages, total_reads
estrain@0 230
estrain@0 231
estrain@0 232 def report_taxon(locus_covs, average_read_length, number_of_reads):
estrain@0 233 list_taxa = [ 'Listeria ss', 'Listeria monocytogenes', 'Escherichia sp.', # noqa: E201
estrain@0 234 'Salmonella bongori (rpoB)', 'Salmonella enterica (rpoB)',
estrain@0 235 'Salmonella bongori (invA)', 'S. enterica subsp. enterica (invA)',
estrain@0 236 'S. enterica subsp. salamae (invA: clade a)', 'S. enterica subsp. salamae (invA: clade b)',
estrain@0 237 'S. enterica subsp. arizonae (invA)', 'S. enterica subsp. diarizonae (invA)',
estrain@0 238 'S. enterica subsp. houtenae (invA)', 'S. enterica subsp. indica (invA)',
estrain@0 239 'S. enterica subsp. VII (invA)', 'S. enterica subsp. salamae (invA: clade VIII)' ] # noqa: E202
estrain@0 240 if sum(locus_covs) < 1:
estrain@0 241 rpoB = ('No rpoB matches!', 0)
estrain@0 242 invA = ('No invA matches!', 0)
estrain@0 243 return rpoB, invA, 0.0
estrain@0 244 else:
estrain@0 245 # given list of scores get taxon
estrain@0 246 if sum(locus_covs[0:5]) > 0:
estrain@0 247 best_rpoB = max(range(len(locus_covs[1:5])), key=lambda x: locus_covs[1:5][x]) + 1
estrain@0 248 all_rpoB = max(range(len(locus_covs[0:5])), key=lambda x: locus_covs[0:5][x])
estrain@0 249 if (locus_covs[best_rpoB] != 0) & (all_rpoB == 0):
estrain@0 250 rpoB = (list_taxa[best_rpoB], locus_covs[best_rpoB])
estrain@0 251 elif (all_rpoB == 0) & (round(sum(locus_covs[1:5]), 1) < 1):
estrain@0 252 rpoB = (list_taxa[0], locus_covs[0])
estrain@0 253 else:
estrain@0 254 rpoB = (list_taxa[best_rpoB], locus_covs[best_rpoB])
estrain@0 255 else:
estrain@0 256 rpoB = ('No rpoB matches!', 0)
estrain@0 257 if sum(locus_covs[5:]) > 0:
estrain@0 258 best_invA = max(range(len(locus_covs[5:])), key=lambda x: locus_covs[5:][x]) + 5
estrain@0 259 invA = (list_taxa[best_invA], locus_covs[best_invA])
estrain@0 260 else:
estrain@0 261 invA = ('No invA matches!', 0)
estrain@0 262 if 'Listeria' in rpoB[0]:
estrain@0 263 return rpoB, invA, (average_read_length * number_of_reads) / 3000000
estrain@0 264 else:
estrain@0 265 return rpoB, invA, (average_read_length * number_of_reads) / 5000000
estrain@0 266
estrain@0 267
estrain@0 268 def main():
estrain@0 269 ex_dir = os.path.dirname(os.path.realpath(__file__))
estrain@0 270 args = parse_args()
estrain@0 271 input_file = args.input_file
estrain@0 272 if input_file != 'None':
estrain@0 273 files = [input_file]
estrain@0 274 else:
estrain@0 275 extension = args.extension
estrain@0 276 inputdir = args.input_dir
estrain@0 277 files = [inputdir + '/' + f for f in os.listdir(inputdir) if f.endswith(extension)]
estrain@0 278 report = args.report
estrain@0 279 mode = args.mode
estrain@0 280 f_invA = open(ex_dir + "/invA_mers_dict", "rb")
estrain@0 281 sets_dict_invA = pickle.load(f_invA)
estrain@0 282 f_invA.close()
estrain@0 283 allmers = sets_dict_invA['allmers']
estrain@0 284 uniqmers_I = sets_dict_invA['uniqmers_I']
estrain@0 285 uniqmers_IIa = sets_dict_invA['uniqmers_IIa']
estrain@0 286 uniqmers_IIb = sets_dict_invA['uniqmers_IIb']
estrain@0 287 uniqmers_IIIa = sets_dict_invA['uniqmers_IIIa']
estrain@0 288 uniqmers_IIIb = sets_dict_invA['uniqmers_IIIb']
estrain@0 289 uniqmers_IV = sets_dict_invA['uniqmers_IV']
estrain@0 290 uniqmers_VI = sets_dict_invA['uniqmers_VI']
estrain@0 291 uniqmers_VII = sets_dict_invA['uniqmers_VII']
estrain@0 292 uniqmers_VIII = sets_dict_invA['uniqmers_VIII']
estrain@0 293 uniqmers_bongori = sets_dict_invA['uniqmers_bongori']
estrain@0 294
estrain@0 295 f = open(ex_dir + "/rpoB_mers_dict", "rb")
estrain@0 296 sets_dict = pickle.load(f)
estrain@0 297 f.close()
estrain@0 298
estrain@0 299 allmers_rpoB = sets_dict['allmers']
estrain@0 300 uniqmers_bongori_rpoB = sets_dict['uniqmers_bongori']
estrain@0 301 uniqmers_S_enterica_rpoB = sets_dict['uniqmers_S_enterica']
estrain@0 302 uniqmers_Escherichia_rpoB = sets_dict['uniqmers_Escherichia']
estrain@0 303 uniqmers_Listeria_ss_rpoB = sets_dict['uniqmers_Listeria_ss']
estrain@0 304 uniqmers_Lmono_rpoB = sets_dict['uniqmers_L_mono']
estrain@0 305 # todo: run kmer_lists() once, create list of tuples containing data to be used fro different reports
estrain@0 306 if report == 'taxonomy':
estrain@0 307 print('file\trpoB\tinvA\texpected coverage')
estrain@0 308 for f in files:
estrain@0 309 locus_scores, coverages, reads = kmer_lists(f, 27,
estrain@0 310 allmers, allmers_rpoB,
estrain@0 311 uniqmers_bongori,
estrain@0 312 uniqmers_I,
estrain@0 313 uniqmers_IIa,
estrain@0 314 uniqmers_IIb,
estrain@0 315 uniqmers_IIIa,
estrain@0 316 uniqmers_IIIb,
estrain@0 317 uniqmers_IV,
estrain@0 318 uniqmers_VI,
estrain@0 319 uniqmers_VII,
estrain@0 320 uniqmers_VIII,
estrain@0 321 uniqmers_bongori_rpoB,
estrain@0 322 uniqmers_S_enterica_rpoB,
estrain@0 323 uniqmers_Escherichia_rpoB,
estrain@0 324 uniqmers_Listeria_ss_rpoB,
estrain@0 325 uniqmers_Lmono_rpoB,
estrain@0 326 mode)
estrain@0 327 pretty_covs = [round(cov, 1) for cov in coverages]
estrain@0 328 report = report_taxon(pretty_covs, get_av_read_length(f), reads)
estrain@0 329 print(f.split('/')[-1] + '\t' + report[0][0] + '[' + str(report[0][1]) + ']' + '\t' + report[1][0] +
estrain@0 330 '[' + str(report[1][1]) + ']' +
estrain@0 331 '\t' + str(round(report[2], 1)))
estrain@0 332 else:
estrain@0 333 print(
estrain@0 334 'file\tListeria sensu stricto (rpoB)\tL. monocytogenes (rpoB)\tEscherichia spp. (rpoB)\tS. bongori (rpoB)\tS. enterica' + # noqa: E122
estrain@0 335 '(rpoB)\tS. bongori (invA)\tsubsp. I (invA)\tsubsp. II (clade a: invA)\tsubsp. II' + # noqa: E122
estrain@0 336 ' (clade b: invA)\tsubsp. IIIa (invA)\tsubsp. IIIb (invA)\tsubsp.IV (invA)\tsubsp. VI (invA)\tsubsp. VII (invA)' + # noqa: E122
estrain@0 337 '\tsubsp. II (clade VIII : invA)')
estrain@0 338 if report == 'percentage':
estrain@0 339 for f in files:
estrain@0 340 locus_scores, coverages, reads = kmer_lists(f, 27,
estrain@0 341 allmers, allmers_rpoB,
estrain@0 342 uniqmers_bongori,
estrain@0 343 uniqmers_I,
estrain@0 344 uniqmers_IIa,
estrain@0 345 uniqmers_IIb,
estrain@0 346 uniqmers_IIIa,
estrain@0 347 uniqmers_IIIb,
estrain@0 348 uniqmers_IV,
estrain@0 349 uniqmers_VI,
estrain@0 350 uniqmers_VII,
estrain@0 351 uniqmers_VIII,
estrain@0 352 uniqmers_bongori_rpoB,
estrain@0 353 uniqmers_S_enterica_rpoB,
estrain@0 354 uniqmers_Escherichia_rpoB,
estrain@0 355 uniqmers_Listeria_ss_rpoB,
estrain@0 356 uniqmers_Lmono_rpoB,
estrain@0 357 mode)
estrain@0 358 pretty_scores = [str(round(score)) for score in locus_scores]
estrain@0 359 print(f.split('/')[-1] + '\t' + '\t'.join(pretty_scores))
estrain@0 360 else:
estrain@0 361 for f in files:
estrain@0 362 locus_scores, coverages, reads = kmer_lists(f, 27,
estrain@0 363 allmers, allmers_rpoB,
estrain@0 364 uniqmers_bongori,
estrain@0 365 uniqmers_I,
estrain@0 366 uniqmers_IIa,
estrain@0 367 uniqmers_IIb,
estrain@0 368 uniqmers_IIIa,
estrain@0 369 uniqmers_IIIb,
estrain@0 370 uniqmers_IV,
estrain@0 371 uniqmers_VI,
estrain@0 372 uniqmers_VII,
estrain@0 373 uniqmers_VIII,
estrain@0 374 uniqmers_bongori_rpoB,
estrain@0 375 uniqmers_S_enterica_rpoB,
estrain@0 376 uniqmers_Escherichia_rpoB,
estrain@0 377 uniqmers_Listeria_ss_rpoB,
estrain@0 378 uniqmers_Lmono_rpoB,
estrain@0 379 mode)
estrain@0 380 pretty_covs = [str(round(cov, 1)) for cov in coverages]
estrain@0 381 print(f.split('/')[-1] + '\t' + '\t'.join(pretty_covs))
estrain@0 382
estrain@0 383
estrain@0 384 if __name__ == '__main__':
estrain@0 385 main()
estrain@0 386