_gene['Product'] = feature.qualifiers["product"] _genes[str(genename)] = _gene _gene = {} return _genes # ## Initialise TSS data into an array growthfile = "F:\Google Drive\Birkbeck\Project\RNAseq\Cortes sup mat\mmc2expogrowth.xlsx" arrestfile = "F:\Google Drive\Birkbeck\Project\RNAseq\Cortes sup mat\mmc6arrest.xlsx" datagrow = exceldata(growthfile, 5) dataarrest = exceldata(arrestfile, 4) fgrow, rgrow = extractTSS(datagrow) farrest, rarrest = extractTSS(dataarrest) ### Initialise SPIRE and GenBank data into dictionaries spire_entries = spireextract("mtb.txt") codingregions = GENBANKparse("M.tb H37Rv BCT 2013-Jun-13.gb") ### Initialise dictionaries and variables for use below possiblestartsgrow = defaultdict(list) possiblestartsarrest = defaultdict(list) downpossiblestartsgrow = defaultdict(list) downpossiblestartsarrest = defaultdict(list) spread = 200 ilength = 5 for key, value in spire_entries.items(): ### Extract information from a SPIRE match matchat = re.search('\((\d*):(\d*)', key) matchstart = int(matchat.group(1)) matchend = int(matchat.group(2)) matchloc = re.search('(\w*)\sof.*', value['Feature']).group(1)
_genes[str(genename)] = _gene _gene = {} return _genes ### Initialise TSS data into an array growthfile = "F:\Google Drive\Birkbeck\Project\RNAseq\Cortes sup mat\mmc2expogrowth.xlsx" arrestfile = "F:\Google Drive\Birkbeck\Project\RNAseq\Cortes sup mat\mmc6arrest.xlsx" datagrow = exceldata(growthfile, 5) dataarrest = exceldata(arrestfile, 4) fgrow, rgrow = extractTSS(datagrow) farrest, rarrest = extractTSS(dataarrest) ### Initialise SPIRE and GenBank data into dictionaries # TODO: Analyse which SPIRE output and which GenBank file to use!!!!! spire_entries = spireextract("M.tb H37Rv CON 2014-Jul-11_modified SPIRE minusHypo.txt") codingregions = GENBANKparse("M.tb H37Rv CON 2014-Jul-11_modified.gb") ### Initialise dictionaries and variables for use below possiblestartsgrow = defaultdict(list) possiblestartsarrest = defaultdict(list) downpossiblestartsgrow = defaultdict(list) downpossiblestartsarrest = defaultdict(list) spread = 200 ilength = 5 for key, value in spire_entries.items(): ### Extract information from a SPIRE match matchat = re.search('\((\d*):(\d*)', key) matchstart = int(matchat.group(1)) matchend = int(matchat.group(2)) matchloc = re.search('(\w*)\sof.*', value['Feature']).group(1)