coverFiles = []
for sequence in sequences:
if sequence != '':
coverFiles.append((inPath+sequence+'/'+sequence+'_CoverDepthMatrix.txt'))
output = "replicon__gene"
outCover = outPath + refName + "_CoverMatrix.csv"
outDepth = outPath + refName + "_DepthMatrix.csv"
geneList = []
coverList = []
depthList = []
first_file = True
for file in coverFiles:
(prefix, name, ext) = splitPath(file)
output = output + "," + name[:-17]
coverFile = open(file)
count = 0
for line in coverFile:
if line.find('\n') != -1:
line = line[:-1]
cover = line.split(',')
if first_file == True:
geneList.append(cover[0])
coverList.append([])
depthList.append([])
coverList[count].append(cover[1])
depthList[count].append(cover[2])
count += 1
coverFile.close()
If HetsVCF is set to 'True', the heterozygous SNP calls will be written to a VCF
example:
python finalFilter.py <raw>.vfc <q30>.vcf <outHetFile> <HetsVCF>
Created: 24/01/2013
Modified: 13/11/2015
author: David Edwards
"""
import sys
from pipe_utils import splitPath
inFile = sys.argv[1]
outFile = sys.argv[2]
(prefix, middle, ext) = splitPath(outFile)
outHetFile = sys.argv[3] + "/" + middle[:-3] + "het.txt"
if sys.argv[4] == "True":
HetsVCF = True
else:
HetsVCF = False
vcfIn = open(inFile)
vcfOut = open(outFile, "w")
hetOut = open(outHetFile, "w")
if HetsVCF:
outHetPosFile = prefix + "/" + middle[:-3] + "het.vcf"
hetVcfOut = open(outHetPosFile, "w")
hetCount = 0
for line in vcfIn:
example:
python deriveRepStats.py <isolate>_rep_cover.txt replicon depth_fail cover_fail runType mapped_fail check_reads_mapped
Created: 29042013
Modified: 16072014
author: David Edwards
'''
import sys
from pipe_utils import splitPath
output_RepStats = ""
repCoverFile = sys.argv[1]
repCover = open(repCoverFile, "r")
(prefix, middle, ext) = splitPath(repCoverFile)
seq_name = middle[:-10]
output_RepStats += seq_name +"\t"
replicon = sys.argv[2]
if replicon.find('.') != -1:
temp_rep = replicon.split('.')
replicon = temp_rep[0]
replicon_names = []
#get % cover and depth for each replicon
depth_test_value = 0.0
for line in repCover:
entry = line.split()
replicon_names.append(entry[0])
Last Modified: 17/02/2015 - fixed locus tag designation
author: David Edwards
'''
import sys, glob
from pipe_utils import splitPath, get_key
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio.SeqFeature import SeqFeature, FeatureLocation
from Bio.Alphabet import IUPAC
outPath = sys.argv[1]
genbankName = sys.argv[2]
coverFileName = sys.argv[3]
(prefix, name, ext) = splitPath(coverFileName)
outCover = outPath + name[:-9] + "/" + name[:-9] + "_CoverDepthMatrix.txt"
geneList = []
geneCoverList = []
geneDepthList = []
totalBases = 0
repliconList =[]
records = SeqIO.parse(genbankName, "genbank")
for record in records:
feature_count = 0
for f in record.features:
if f.type == "CDS":
# if f.type == "misc_feature":
feature_count += 1
example:
python getSNPList.py <statsFile> <replicon> <output>
Created: 12052013
Modified: 15042014
author: David Edwards
'''
import sys, glob
from pipe_utils import splitPath
statsFile_name = sys.argv[1]
replicon = sys.argv[2]
outputFile_name = sys.argv[3]
outputFile = open(outputFile_name, "w")
finalList = []
(prefix, name, ext) = splitPath(statsFile_name)
vcfs = prefix + '/vcf/*_' + replicon + '_q30.vcf'
for file in glob.glob(vcfs):
(prefix, name, ext) = splitPath(file)
name = name[:(-1*(5+len(replicon)))]
statsFile = open(statsFile_name)
for sample in statsFile:
if sample.startswith("Isolate") != True:
splitSample = sample.split("\t")
if (name == splitSample[0]) and (splitSample[-1].startswith("f") != True):
vcfFile = open(file)
varList = []
mergeList = []
for line in vcfFile:
if line.startswith("#") == False:
splitLine = line.split("\t")
for line in snpList:
splitLine = line.split()
SNP.append([splitLine[0]])
snpList.close()
#populate reference calls from reference fasta
references = SeqIO.parse(reference_name, "fasta")
for reference in references:
if reference.name == replicon:
for call in range(len(SNP)):
base = reference.seq[int(SNP[call][0])-1]
SNP[call].append(base.upper())
# call bases for each SNP from consensus file of the strain
(prefix, name, ext) = splitPath(consensus_in)
if merge_prefix == '-':
warning_file = prefix[:-4] + replicon +'_'+name +'_warning.txt'
else:
warning_file = merge_prefix + replicon +'_'+name +'_warning.txt'
name = name[:-4]
consensus = SeqIO.parse(consensus_in, "fastq")
statsFile = open(stats)
for sample in statsFile:
if sample.startswith("Isolate") != True:
splitSample = sample.split("\t")
record_found = False
if (name == splitSample[0]) and (splitSample[-1].startswith("f") != True):
header = header + ',' + name
for record in consensus:
if record.name == replicon:
example:
python mergeRepStats.py <new_replicon_RepStats.tab> sdOutgroupMutiplier reads_to_replace <mergeDirectory> runType
Created: 23/10/2012
Modified: 28/10/2013 to mergeRepStats from mergeStats
15/04/2014 changed to produce outgroup.txt file if there are any outgroups to report
20/05/2014 fix to outgroup reporting
04/07/2014 change to replace_reads handling
author: David Edwards
'''
import sys, glob
from pipe_utils import splitPath
inFileName = sys.argv[1]
(inPrefix, inName, inExt) = splitPath(inFileName)
sdOutgroupMutiplier = int(sys.argv[2])
mergeFileName = sys.argv[4] + inName + inExt
replace = sys.argv[3]
runType = sys.argv[5]
outgroup_outfile_name = sys.argv[4] + inName[:-9] + '_outgroups.txt'
outgroups = []
average = 0
sd = 0
count = 0
output = ""
# Combine the two sets
# note: only need to count SNPs for 'phylogeny' runType
parser.add_option("-i", "--input_file", action="store", dest="input_file", help="allele table (required)", default="")
parser.add_option("-o", "--output_file", action="store", dest="output_file", help="name for output file (no ext, only required if '_alleles' missing from input name), Note: if '_alleles(_*)' ending present, this is removed and '_SNP_diff.nxs' added [setting for RedDog pipeline] (default: none)", default="")
parser.add_option("-d", "--directory", action="store", dest="directory", help="directory to send output files (default: none)", default="")
return parser.parse_args()
if __name__ == "__main__":
(options, args) = main()
### MAIN PROCESS
inputName = options.input_file
inputFile = open(inputName)
(prefix, name, ext) = splitPath(inputName)
strains = []
if name.find('_alleles') != -1:
split_name = name.split('_')
split = 0
refName = split_name[split]
split += 1
while split_name[split] != 'alleles':
refName += '_' + split_name[split]
split += 1
directory = options.directory
if directory == '':
if prefix != '':
outName = prefix + '/' + refName + '_SNP_diff.nxs'