def getFig3Percent(path):
fileTr = path + 'Data/transcriptType/HS_transcript_unspliced_All.txt'
fileBt = path + 'Data/transcriptType/transcriptType_All.txt'
filepG4rWt = path + 'Results/All/HS_All_G4InTranscript.txt'
filepG4rShuf = path + 'Results/All/pG4r_shuffle.csv'
dicoNbTr = {'Wt': {}, 'Shuf': {}, 'Tot': {}}
dicoBt = rF.createDictionaryBiotypeByTranscript(fileBt)
listTr = importTr(fileTr)
# we keep only transcript with a biotype known.
listTot = [tr for tr in listTr if tr in dicoBt]
dicoTrClass, dicoNbTrClass = getNumberTrinClass(dicoBt, listTot)
dicoNbTr['Tot']['Global'] = len(set(listTot))
dicoNbTr['Tot'].update(dicoNbTrClass)
listTrpG4rWt = readWtpG4r(filepG4rWt)
dicoNbTrWt = countpG4rByClass(dicoTrClass, listTrpG4rWt)
dicoNbTr['Wt']['Global'] = len(listTrpG4rWt)
dicoNbTr['Wt'].update(dicoNbTrWt)
listTrpG4rShuf = readShufpG4r(filepG4rShuf)
dicoNbTrShuf = countpG4rByClass(dicoTrClass, listTrpG4rShuf)
dicoNbTr['Shuf']['Global'] = len(listTrpG4rShuf)
dicoNbTr['Shuf'].update(dicoNbTrShuf)
return dicoNbTr
name = '>' + gene + ':junction:' + chr + ':' + coords + ':' + strand + ':' + '|'.join(
listTr)
fastaShuf[name] = seq
writeFasta(outputDir, fastaShuf, chr, 'junction')
def build_arg_parser():
parser = argparse.ArgumentParser(description='generateRandom')
GITDIR = os.getcwd() + '/'
parser.add_argument('-p', '--path', default=GITDIR)
parser.add_argument('-chr', '--chromosome', default='Y')
return parser
if __name__ == '__main__':
parser = build_arg_parser()
arg = parser.parse_args()
chr = arg.chromosome
path = arg.path
fastaFile = path + '/Fasta/'
outputDir = path + '/chr' + chr + '/'
fastaJunction = path + '/chr' + chr + '/HS_transcript_unspliced_chr' + chr + '_Sequence.txt'
print(chr)
dicoBt = rF.createDictionaryBiotypeByTranscript(
path + '/transcriptType/transcriptType_chr' + chr + '.txt')
dicoInfo = getDicoIndex(
path + '/chr' + chr + '/HS_transcript_unspliced_chr' + chr +
'_Index.txt', dicoBt)
createFasta(dicoInfo, fastaFile, chr, outputDir)
fromFasta(fastaJunction, outputDir, chr, dicoInfo)
def main(path, chromosome, specie, dicoParam):
"""Main function.
The main function contains 4 parts :
- initialization of all lists and dictionnary containing informations
- merge of all windows over thresholds. If two windows over thresolds
are separated by an other window (under thresholds) between them, it
be two differents pG4
- annotation of pG4 : on genome and transcriptom
- writing files
"""
GITDIR = os.getcwd() + '/'
ProteinCoding = createListCodingProtein()
G4DetectedInGene = {}
G4DetectedInJunction = {}
G4InTranscript = {}
G4InGenome = {}
TranscriptPerG4 = {}
directory = path + '/chr' + chromosome
# variable directory which contain the data for this chromosome
index = directory + '/' + specie + '_transcript_unspliced_chr' + \
chromosome + '_Index.txt'
# file which contain info by transcript for this chromosome
indexBiotypeTranscript = path + '/transcriptType/transcriptType_chr' + \
chromosome
# file which contain biotype of transcript for this chromosome
print "Chromosome " + chromosome
BiotypeByTranscript = \
rF.createDictionaryBiotypeByTranscript(indexBiotypeTranscript)
StrandByGene = createDictionaryStrandByGene(index)
AnnotationTranscript = rF.GetAnnotationTranscript(index, ProteinCoding,
BiotypeByTranscript)
# get g4 from the ouput of G4RNA Screener
for path, dirs, files in os.walk(directory):
# for each element of the directory to passed
for filename in files: # for each files (all csv)
inputfile = directory + '/' + filename
if ('gene_unspliced' in filename and '.csv' in filename):
G4DetectedInGene = returnG4InGene(G4DetectedInGene, inputfile,
dicoParam, StrandByGene)
elif ('Junction' in filename and '.fas' in filename):
G4DetectedInJunction = returnG4InJunction(
G4DetectedInJunction, inputfile, dicoParam, StrandByGene)
listeG4InGeneEntire = getlisteG4InGene(G4DetectedInGene)
listeG4InGeneJunction = getlisteG4InGene(G4DetectedInJunction)
G4InTranscript, G4InGenome, TranscriptPerG4 = getInfoAboutpG4(
index, BiotypeByTranscript, listeG4InGeneEntire, G4InTranscript,
G4InGenome, TranscriptPerG4, AnnotationTranscript, G4DetectedInGene,
ProteinCoding, 'Transcript')
G4InTranscript, G4InGenome, TranscriptPerG4 = getInfoAboutpG4(
index, BiotypeByTranscript, listeG4InGeneJunction, G4InTranscript,
G4InGenome, TranscriptPerG4, AnnotationTranscript,
G4DetectedInJunction, ProteinCoding, 'Junction')
extractionG4InTranscript(GITDIR + 'results/perChromosome', specie,
chromosome, G4InTranscript)
extractionG4InGenome(GITDIR + 'results/perChromosome', specie, chromosome,
G4InGenome)
extractionTranscriptPerG4(GITDIR + 'results/perChromosome', specie,
chromosome, TranscriptPerG4)
print "\t Done."