def ppsOut2ppOut(inFile, outFile, taxonomicRanks, databaseFile):
"""
Transforms a PPS output file into a file in the PP format.
@param inFile: input file in the PPS format (first column: seq name, last column: ncbi taxon id)
@param outFile: output file in the PP format
@param taxonomicRanks: taxonomic ranks (starting from superkingdom)
@param databaseFile: database file in the sqlite3 format
"""
taxonomy = Taxonomy(databaseFile, taxonomicRanks)
outBuff = csv.OutFileBuffer(outFile)
namesList = csv.getColumnAsList(inFile,
entryModifyFunction=None,
colNum=0,
sep='\t',
comment='#')
valCol = 1
ncbidsList = csv.getColumnAsList(inFile,
entryModifyFunction=None,
colNum=valCol,
sep='\t',
comment='#')
while True: # this is not efficient!
valCol += 1
tmpList = csv.getColumnAsList(inFile,
entryModifyFunction=None,
colNum=valCol,
sep='\t',
comment='#')
if len(tmpList) == len(namesList):
ncbidsList = tmpList
else:
break
header = str('#PPS file transformed to PP format, input file: ' +
str(inFile) + '\n#ID' + '\t' + 'root')
for rank in taxonomicRanks:
header += str('\t' + rank)
outBuff.writeText(str(header + '\n'))
for i in range(len(namesList)):
name = namesList[i]
ncbid = ncbidsList[i]
taxPathDict = taxonomy.getPathToRoot(int(ncbid))
buff = str(name)
if taxPathDict is None:
buff += str('\t')
else:
buff += str('\t' + 'root')
for rank in taxonomicRanks:
if (taxPathDict is not None) and (rank in taxPathDict) and (
not taxPathDict[rank].isCopy()):
buff += str('\t' + taxPathDict[rank].name)
else:
buff += '\t'
outBuff.writeText(str(buff + '\n'))
outBuff.close()
taxonomy.close()
def main01():
#config = Config(open(os.path.normpath('/Users/ivan/Documents/work/binning/tests/CowRumen/01/config.cfg')), 'pPPS')
#config = Config(open(os.path.normpath('/net/metagenomics/projects/PPSmg/tests/V35/config.cfg')), 'pPPS')
#configMl = Config2(config, 'MLTreeMap')
#configPPS = Config2(config, 'PPS')
#read sequences
#sequences = Sequences(config)
#write ids file
#sequences.writeSequences(config.get('inputIdsFastaFile'))
#taxonomy = Taxonomy(config.get('databaseFile'), config.get('taxonomicRanks').split(','))
taxonomicRanks = 'superkingdom,phylum,class,order,family,genus,species'.split(',')
taxonomy = Taxonomy('/Users/ivan/Documents/work/binning/taxonomy/20120828/ncbitax_sqlite.db', taxonomicRanks)
#ppsOut2ppOut('D:\\VM\\tmp\\simMC_AMD\\AMD.Arachne.genus', 'D:\\VM\\tmp\\simMC_AMD\\AMD.Arachne.genus.PP.out', taxonomy, config.get('taxonomicRanks').split(','))
#ppsOut2ppOut('/Users/ivan/Documents/work/binning/data/CowRumen/cowRumenOrderNcbids.txt',
# '/Users/ivan/Documents/work/binning/data/CowRumen/cowRumenOrderNcbids.PP.txt', taxonomy, config.get('taxonomicRanks').split(','))
#ppsOut2ppOut('/net/metagenomics/projects/PPSmg/data/V35/contigsMappedBlast1000LabelsSpecies.txt',
# '/net/metagenomics/projects/PPSmg/data/V35/contigsMappedBlast1000LabelsSpecies.PP.txt', taxonomy, config.get('taxonomicRanks').split(','))
ppsOut2ppOut('/Users/ivan/Documents/work/binning/data/simMC/fromJohannes/contigs.genus.tax',
'/Users/ivan/Documents/work/binning/data/simMC/fromJohannes/contigs.genus.PP.tax', taxonomy, taxonomicRanks)
#readPPSOutput(sequences, taxonomy, config.get('inputIdsFastaFile'))
#sequences.writePlacements(str(config.get('inputIdsFastaFile') + '.pOUT'), config.get('taxonomicRanks').split(','))
#toRealNames(config, sequences)
taxonomy.close()
def ppsOut2ppOut(inFile, outFile, taxonomicRanks, databaseFile):
"""
Transforms a PPS output file into a file in the PP format.
@param inFile: input file in the PPS format (first column: seq name, last column: ncbi taxon id)
@param outFile: output file in the PP format
@param taxonomicRanks: taxonomic ranks (starting from superkingdom)
@param databaseFile: database file in the sqlite3 format
"""
taxonomy = Taxonomy(databaseFile, taxonomicRanks)
outBuff = csv.OutFileBuffer(outFile)
namesList = csv.getColumnAsList(inFile, entryModifyFunction=None, colNum=0, sep='\t', comment='#')
valCol = 1
ncbidsList = csv.getColumnAsList(inFile, entryModifyFunction=None, colNum=valCol, sep='\t', comment='#')
while True: # this is not efficient!
valCol += 1
tmpList = csv.getColumnAsList(inFile, entryModifyFunction=None, colNum=valCol, sep='\t', comment='#')
if len(tmpList) == len(namesList):
ncbidsList = tmpList
else:
break
header = str('#PPS file transformed to PP format, input file: ' + str(inFile) + '\n#ID' + '\t' + 'root')
for rank in taxonomicRanks:
header += str('\t' + rank)
outBuff.writeText(str(header + '\n'))
for i in range(len(namesList)):
name = namesList[i]
ncbid = ncbidsList[i]
taxPathDict = taxonomy.getPathToRoot(int(ncbid))
buff = str(name)
if taxPathDict is None:
buff += str('\t')
else:
buff += str('\t' + 'root')
for rank in taxonomicRanks:
if (taxPathDict is not None) and (rank in taxPathDict) and (not taxPathDict[rank].isCopy()):
buff += str('\t' + taxPathDict[rank].name)
else:
buff += '\t'
outBuff.writeText(str(buff + '\n'))
outBuff.close()
taxonomy.close()
def main01():
#config = Config(open(os.path.normpath('/Users/ivan/Documents/work/binning/tests/CowRumen/01/config.cfg')), 'pPPS')
#config = Config(open(os.path.normpath('/net/metagenomics/projects/PPSmg/tests/V35/config.cfg')), 'pPPS')
#configMl = Config2(config, 'MLTreeMap')
#configPPS = Config2(config, 'PPS')
#read sequences
#sequences = Sequences(config)
#write ids file
#sequences.writeSequences(config.get('inputIdsFastaFile'))
#taxonomy = Taxonomy(config.get('databaseFile'), config.get('taxonomicRanks').split(','))
taxonomicRanks = 'superkingdom,phylum,class,order,family,genus,species'.split(
',')
taxonomy = Taxonomy(
'/Users/ivan/Documents/work/binning/taxonomy/20120828/ncbitax_sqlite.db',
taxonomicRanks)
#ppsOut2ppOut('D:\\VM\\tmp\\simMC_AMD\\AMD.Arachne.genus', 'D:\\VM\\tmp\\simMC_AMD\\AMD.Arachne.genus.PP.out', taxonomy, config.get('taxonomicRanks').split(','))
#ppsOut2ppOut('/Users/ivan/Documents/work/binning/data/CowRumen/cowRumenOrderNcbids.txt',
# '/Users/ivan/Documents/work/binning/data/CowRumen/cowRumenOrderNcbids.PP.txt', taxonomy, config.get('taxonomicRanks').split(','))
#ppsOut2ppOut('/net/metagenomics/projects/PPSmg/data/V35/contigsMappedBlast1000LabelsSpecies.txt',
# '/net/metagenomics/projects/PPSmg/data/V35/contigsMappedBlast1000LabelsSpecies.PP.txt', taxonomy, config.get('taxonomicRanks').split(','))
ppsOut2ppOut(
'/Users/ivan/Documents/work/binning/data/simMC/fromJohannes/contigs.genus.tax',
'/Users/ivan/Documents/work/binning/data/simMC/fromJohannes/contigs.genus.PP.tax',
taxonomy, taxonomicRanks)
#readPPSOutput(sequences, taxonomy, config.get('inputIdsFastaFile'))
#sequences.writePlacements(str(config.get('inputIdsFastaFile') + '.pOUT'), config.get('taxonomicRanks').split(','))
#toRealNames(config, sequences)
taxonomy.close()
def test():
markerGeneName = 'rpsC' #'rpsI' #'rpsS' # 'rpsK'
annotationDir = os.path.normpath(
'D:/A_Phylo/A_Metagenomic/data/markerGenes/annotation')
outDir = os.path.normpath(
'D:/A_Phylo/A_Metagenomic/data/markerGenes/mGenesExtracted')
taxonomy = Taxonomy(
os.path.normpath(
'D:/A_Phylo/A_Metagenomic/data/ncbiTaxonomy20111007/ncbitax_sqlite.db'
), [
'superkingdom', 'phylum', 'class', 'order', 'family', 'genus',
'species'
])
relaxGeneNames = False
recSkipCount = 0
firstErrorStop = False
createGeneDb(markerGeneName, annotationDir, outDir, taxonomy,
relaxGeneNames, recSkipCount, firstErrorStop)
def main():
parser = argparse.ArgumentParser(
description='''Creates database for a marker gene''', epilog=''' ''')
parser.add_argument('-m',
'--marker-gene-name',
action='store',
nargs=1,
required=True,
help='The name of a specific marker gene.',
dest='marker')
parser.add_argument(
'-a',
'--annotation-dir',
action='store',
nargs=1,
required=True,
help='The name of the directory that contains annotation files.',
dest='annotationDir')
parser.add_argument(
'-o',
'--output-dir',
action='store',
nargs=1,
required=True,
help='The name of the directory where the output files will be stored.',
dest='outDir')
parser.add_argument('-t',
'--taxonomyDb',
action='store',
nargs=1,
required=True,
help='Taxonomy database file (SQLite).',
dest='taxonomyDb')
parser.add_argument(
'-r',
'--relax-gene-names',
action='store_true',
help=
'If enabled, the script doesn`t control if the gene names are correct.',
dest='relaxGeneNames')
parser.add_argument(
'-s',
'--rec-skip',
action='store',
nargs=1,
help=
'The number of records that will be skipped at the beginning of the annotation file.',
dest='recSkip')
parser.add_argument('-p',
'--print-first-error',
action='store_true',
help='The script stops after first error occurs',
dest='firstErrorStop')
args = parser.parse_args()
markerGeneName = str(args.marker[0])
annotationDir = os.path.normpath(str(args.annotationDir[0]))
outDir = os.path.normpath(str(args.outDir[0]))
taxonomy = Taxonomy(os.path.normpath(str(args.taxonomyDb[0])), [
'superkingdom', 'phylum', 'class', 'order', 'family', 'genus',
'species'
])
if args.recSkip:
recSkip = int(args.recSkip[0])
else:
recSkip = 0
if args.firstErrorStop:
firstErrorStop = True
else:
firstErrorStop = False
if args.relaxGeneNames:
relaxGeneNames = True
else:
relaxGeneNames = False
createGeneDb(markerGeneName, annotationDir, outDir, taxonomy,
relaxGeneNames, recSkip, firstErrorStop)
entry += str('\t' + taxPathDict[rank].name)
else:
entry += '\t'
f.write(entry)
except Exception:
print "Cannot create a file or write to it:", outFile
raise
finally:
f.close()
if __name__ == "__main__":
#test 2
#ppsOutFile = 'D:\A_Phylo\A_Metagenomic\data\humanGut\PPS_contigs.txt'
#outPPOutFile = 'D:\A_Phylo\A_Metagenomic\data\humanGut\PPS_PP_contigs.txt'
#ppsOutFile = 'C:/Documents and Settings/Administrator/Desktop/temp/johdroPred/inputTW.fas.ids04.lP'
ppsOutFile = 'C:/Documents and Settings/Administrator/Desktop/temp/johdroPred/inputTW.fas.ids05.lP'
#outPPOutFile = 'C:/Documents and Settings/Administrator/Desktop/temp/johdroPred/inputTW.fas.ids04.lP.PP.out'
outPPOutFile = 'C:/Documents and Settings/Administrator/Desktop/temp/johdroPred/inputTW.fas.ids05.lP.PP.out'
config = Config(open(os.path.normpath('D:\\A_Phylo\\A_Metagenomic\\pPPS\\workspace\\pPPS\\config01.cfg')), 'pPPS')
databaseFile = os.path.normpath(config.get('databaseFile'))
taxonomicRanks = config.get('taxonomicRanks').split(',')
taxonomy = Taxonomy(databaseFile, taxonomicRanks)
ppsOutToPPOut(ppsOutFile, outPPOutFile, taxonomicRanks, taxonomy)
#test 1
#scafContigFile = 'D:/A_Phylo/A_Metagenomic/reindeer/data/scaffolds-contigs.tab'
#scafPPSOutFile = 'D:/A_Phylo/A_Metagenomic/reindeer/predictions/pps04/scaffoldsOut/SRM_Scaffolds_namesOnly.fna.PP.out'
#contigPPSOutFile = 'D:/A_Phylo/A_Metagenomic/reindeer/predictions/pps04/scaffoldsOut/SRM_Scaffolds_namesOnly.fna.PP.out_contigs'
#scafToContigOutput(scafContigFile, scafPPSOutFile, contigPPSOutFile)