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 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()