def run(self, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, minMarkers, completenessThreshold, contaminationThreshold): print 'Ubiquity threshold: ' + str(ubiquityThreshold) print 'Single-copy threshold: ' + str(singleCopyThreshold) print 'Min. genomes: ' + str(minGenomes) print 'Most specific taxonomic rank: ' + str(mostSpecificRank) print 'Min markers: ' + str(minMarkers) print 'Completeness threshold: ' + str(completenessThreshold) print 'Contamination threshold: ' + str(contaminationThreshold) img = IMG() markerset = MarkerSet() lineages = img.lineagesByCriteria(minGenomes, mostSpecificRank) degenerateGenomes = {} for lineage in lineages: genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final') print '' print 'Lineage ' + lineage + ' contains ' + str(len(genomeIds)) + ' genomes.' # get table of PFAMs and do some initial filtering to remove PFAMs that are # clearly not going to pass the ubiquity and single-copy thresholds countTable = img.countTable(genomeIds) countTable = img.filterTable(genomeIds, countTable, ubiquityThreshold*0.9, singleCopyThreshold*0.9) markerGenes = markerset.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) if len(markerGenes) < minMarkers: continue geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) for genomeId in genomeIds: completeness, contamination = markerset.genomeCheck(colocatedSets, genomeId, countTable) if completeness < completenessThreshold or contamination > contaminationThreshold: degenerateGenomes[genomeId] = degenerateGenomes.get(genomeId, []) + [[lineage.split(';')[-1].strip(), len(genomeIds), len(colocatedSets), completeness, contamination]] # write out degenerate genomes metadata = img.genomeMetadata('Final') fout = open('./data/degenerate_genomes.tsv', 'w') fout.write('Genome Id\tTaxonomy\tGenome Size (Gbps)\tScaffolds\tBiotic Relationships\tStatus\tLineage\t# genomes\tMarker set size\tCompleteness\tContamination\n') for genomeId, data in degenerateGenomes.iteritems(): fout.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy']) + '\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6) + '\t' + str(metadata[genomeId]['scaffold count'])) fout.write('\t' + metadata[genomeId]['biotic relationships'] + '\t' + metadata[genomeId]['status']) for d in data: fout.write('\t' + d[0] + '\t' + str(d[1]) + '\t' + str(d[2]) + '\t%.3f\t%.3f' % (d[3], d[4])) fout.write('\n') fout.close()
def run(self, ubiquityThreshold, singleCopyThreshold, rank): img = IMG() markerset = MarkerSet() print('Reading metadata.') metadata = img.genomeMetadata() print(' Genomes with metadata: ' + str(len(metadata))) # calculate marker set for each lineage at the specified rank sortedLineages = img.lineagesSorted(metadata, rank) markerGeneLists = {} for lineage in sortedLineages: taxonomy = lineage.split(';') if len(taxonomy) != rank + 1: continue genomeIds = img.genomeIdsByTaxonomy(lineage, metadata, 'Final') countTable = img.countTable(genomeIds) if len(genomeIds) < 3: continue print('Lineage ' + lineage + ' contains ' + str(len(genomeIds)) + ' genomes.') markerGenes = markerset.markerGenes( genomeIds, countTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) print(' Marker genes: ' + str(len(markerGenes))) print('') markerGeneLists[lineage] = markerGenes # calculate union of marker gene list for higher taxonomic groups for r in range(rank - 1, -1, -1): print('Processing rank ' + str(r)) rankMarkerGeneLists = {} for lineage, markerGenes in markerGeneLists.iteritems(): taxonomy = lineage.split(';') if len(taxonomy) != r + 2: continue curLineage = '; '.join(taxonomy[0:r + 1]) if curLineage not in rankMarkerGeneLists: rankMarkerGeneLists[curLineage] = markerGenes else: curMarkerGenes = rankMarkerGeneLists[curLineage] curMarkerGenes = curMarkerGenes.intersection(markerGenes) rankMarkerGeneLists[curLineage] = curMarkerGenes # combine marker gene list dictionaries markerGeneLists.update(rankMarkerGeneLists)
def run( self, ubiquityThreshold, singleCopyThreshold, minGenomes, minMarkers, mostSpecificRank, distThreshold, genomeThreshold, ): img = IMG() markerset = MarkerSet() lineages = img.lineagesSorted(mostSpecificRank) fout = open("./data/colocated.tsv", "w", 1) fout.write("Lineage\t# genomes\t# markers\t# co-located sets\tCo-located markers\n") lineageCount = 0 for lineage in lineages: lineageCount += 1 genomeIds = img.genomeIdsByTaxonomy(lineage, "Final") if len(genomeIds) < minGenomes: continue countTable = img.countTable(genomeIds) markerGenes = markerset.markerGenes( genomeIds, countTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds) ) geneDistTable = img.geneDistTable(genomeIds, markerGenes) colocatedGenes = markerset.colocatedGenes(geneDistTable, distThreshold, genomeThreshold) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) if len(colocatedSets) < minMarkers: continue print "\nLineage " + lineage + " contains " + str(len(genomeIds)) + " genomes (" + str( lineageCount ) + " of " + str(len(lineages)) + ")." print " Marker genes: " + str(len(markerGenes)) print " Co-located gene sets: " + str(len(colocatedSets)) fout.write( lineage + "\t" + str(len(genomeIds)) + "\t" + str(len(markerGenes)) + "\t" + str(len(colocatedSets)) ) for cs in colocatedSets: fout.write("\t" + ", ".join(cs)) fout.write("\n") fout.close()
def run(self, ubiquityThreshold, singleCopyThreshold, rank): img = IMG() markerset = MarkerSet() print 'Reading metadata.' metadata = img.genomeMetadata() print ' Genomes with metadata: ' + str(len(metadata)) # calculate marker set for each lineage at the specified rank sortedLineages = img.lineagesSorted(metadata, rank) markerGeneLists = {} for lineage in sortedLineages: taxonomy = lineage.split(';') if len(taxonomy) != rank+1: continue genomeIds = img.genomeIdsByTaxonomy(lineage, metadata, 'Final') countTable = img.countTable(genomeIds) if len(genomeIds) < 3: continue print 'Lineage ' + lineage + ' contains ' + str(len(genomeIds)) + ' genomes.' markerGenes = markerset.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) print ' Marker genes: ' + str(len(markerGenes)) print '' markerGeneLists[lineage] = markerGenes # calculate union of marker gene list for higher taxonomic groups for r in xrange(rank-1, -1, -1): print 'Processing rank ' + str(r) rankMarkerGeneLists = {} for lineage, markerGenes in markerGeneLists.iteritems(): taxonomy = lineage.split(';') if len(taxonomy) != r+2: continue curLineage = '; '.join(taxonomy[0:r+1]) if curLineage not in rankMarkerGeneLists: rankMarkerGeneLists[curLineage] = markerGenes else: curMarkerGenes = rankMarkerGeneLists[curLineage] curMarkerGenes = curMarkerGenes.intersection(markerGenes) rankMarkerGeneLists[curLineage] = curMarkerGenes # combine marker gene list dictionaries markerGeneLists.update(rankMarkerGeneLists)
def run(self, ubiquityThreshold, singleCopyThreshold, minGenomes, minMarkers, mostSpecificRank, distThreshold, genomeThreshold): img = IMG() markerset = MarkerSet() lineages = img.lineagesSorted(mostSpecificRank) fout = open('./data/colocated.tsv', 'w', 1) fout.write( 'Lineage\t# genomes\t# markers\t# co-located sets\tCo-located markers\n' ) lineageCount = 0 for lineage in lineages: lineageCount += 1 genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final') if len(genomeIds) < minGenomes: continue countTable = img.countTable(genomeIds) markerGenes = markerset.markerGenes( genomeIds, countTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable, distThreshold, genomeThreshold) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) if len(colocatedSets) < minMarkers: continue print '\nLineage ' + lineage + ' contains ' + str(len( genomeIds)) + ' genomes (' + str(lineageCount) + ' of ' + str( len(lineages)) + ').' print ' Marker genes: ' + str(len(markerGenes)) print ' Co-located gene sets: ' + str(len(colocatedSets)) fout.write(lineage + '\t' + str(len(genomeIds)) + '\t' + str(len(markerGenes)) + '\t' + str(len(colocatedSets))) for cs in colocatedSets: fout.write('\t' + ', '.join(cs)) fout.write('\n') fout.close()
def run(self, ubiquityThreshold, singleCopyThreshold, minGenomes, minMarkers, mostSpecificRank, distThreshold, genomeThreshold): img = IMG() markerset = MarkerSet() lineages = img.lineagesSorted(mostSpecificRank) fout = open('./data/colocated.tsv', 'w', 1) fout.write('Lineage\t# genomes\t# markers\t# co-located sets\tCo-located markers\n') lineageCount = 0 for lineage in lineages: lineageCount += 1 genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final') if len(genomeIds) < minGenomes: continue countTable = img.countTable(genomeIds) markerGenes = markerset.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable, distThreshold, genomeThreshold) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) if len(colocatedSets) < minMarkers: continue print '\nLineage ' + lineage + ' contains ' + str(len(genomeIds)) + ' genomes (' + str(lineageCount) + ' of ' + str(len(lineages)) + ').' print ' Marker genes: ' + str(len(markerGenes)) print ' Co-located gene sets: ' + str(len(colocatedSets)) fout.write(lineage + '\t' + str(len(genomeIds)) + '\t' + str(len(markerGenes)) + '\t' + str(len(colocatedSets))) for cs in colocatedSets: fout.write('\t' + ', '.join(cs)) fout.write('\n') fout.close()
class MarkerSetStability(object): def __init__(self): self.img = IMG() self.markerset = MarkerSet() def __processLineage(self, metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, queueIn, queueOut): """Assess stability of marker set for a specific named taxonomic group.""" while True: lineage = queueIn.get(block=True, timeout=None) if lineage == None: break genomeIds = self.img.genomeIdsByTaxonomy(lineage, metadata, 'trusted') changeMarkerSetSize = {} markerGenes = [] if len(genomeIds) >= minGenomes: # calculate marker set for all genomes in lineage geneCountTable = self.img.geneCountTable(genomeIds) markerGenes = self.markerset.markerGenes( genomeIds, geneCountTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) tigrToRemove = self.img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove for selectPer in range(50, 101, 5): numGenomesToSelect = int( float(selectPer) / 100 * len(genomeIds)) perChange = [] for _ in range(0, 10): # calculate marker set for subset of genomes subsetGenomeIds = random.sample( genomeIds, numGenomesToSelect) geneCountTable = self.img.geneCountTable( subsetGenomeIds) subsetMarkerGenes = self.markerset.markerGenes( subsetGenomeIds, geneCountTable, ubiquityThreshold * numGenomesToSelect, singleCopyThreshold * numGenomesToSelect) tigrToRemove = self.img.identifyRedundantTIGRFAMs( subsetMarkerGenes) subsetMarkerGenes = subsetMarkerGenes - tigrToRemove perChange.append( float( len( markerGenes.symmetric_difference( subsetMarkerGenes))) * 100.0 / len(markerGenes)) changeMarkerSetSize[selectPer] = [ mean(perChange), std(perChange) ] queueOut.put((lineage, len(genomeIds), len(markerGenes), changeMarkerSetSize)) def __storeResults(self, outputFile, totalLineages, writerQueue): """Store results to file.""" fout = open(outputFile, 'w') fout.write( 'Lineage\t# genomes\t# markers\tsubsample %\tmean % change\tstd % change\n' ) numProcessedLineages = 0 while True: lineage, numGenomes, numMarkerGenes, changeMarkerSetSize = writerQueue.get( block=True, timeout=None) if lineage == None: break numProcessedLineages += 1 statusStr = ' Finished processing %d of %d (%.2f%%) lineages.' % ( numProcessedLineages, totalLineages, float(numProcessedLineages) * 100 / totalLineages) sys.stdout.write('%s\r' % statusStr) sys.stdout.flush() for selectPer in sorted(changeMarkerSetSize.keys()): fout.write('%s\t%d\t%d\t%d\t%f\t%f\n' % (lineage, numGenomes, numMarkerGenes, selectPer, changeMarkerSetSize[selectPer][0], changeMarkerSetSize[selectPer][1])) sys.stdout.write('\n') fout.close() def run(self, outputFile, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, numThreads): """Calculate stability of marker sets for named taxonomic groups.""" print(' Calculating stability of marker sets:') random.seed(1) # process each sequence in parallel workerQueue = mp.Queue() writerQueue = mp.Queue() metadata = self.img.genomeMetadata() lineages = self.img.lineagesByCriteria(metadata, minGenomes, mostSpecificRank) #lineages = ['Bacteria'] #lineages += ['Bacteria;Proteobacteria'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae;Escherichia'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae;Escherichia;coli'] #lineages = ['Archaea'] #lineages += ['Archaea;Euryarchaeota'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia;Methanosarcinales'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia;Methanosarcinales;Methanosarcinaceae'] for lineage in lineages: workerQueue.put(lineage) for _ in range(numThreads): workerQueue.put(None) calcProc = [ mp.Process(target=self.__processLineage, args=(metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, workerQueue, writerQueue)) for _ in range(numThreads) ] writeProc = mp.Process(target=self.__storeResults, args=(outputFile, len(lineages), writerQueue)) writeProc.start() for p in calcProc: p.start() for p in calcProc: p.join() writerQueue.put((None, None, None, None)) writeProc.join()
def run(self, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, minMarkers, completenessThreshold, contaminationThreshold): print 'Ubiquity threshold: ' + str(ubiquityThreshold) print 'Single-copy threshold: ' + str(singleCopyThreshold) print 'Min. genomes: ' + str(minGenomes) print 'Most specific taxonomic rank: ' + str(mostSpecificRank) print 'Min markers: ' + str(minMarkers) print 'Completeness threshold: ' + str(completenessThreshold) print 'Contamination threshold: ' + str(contaminationThreshold) img = IMG() markerset = MarkerSet() lineages = img.lineagesByCriteria(minGenomes, mostSpecificRank) degenerateGenomes = {} for lineage in lineages: genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final') print '' print 'Lineage ' + lineage + ' contains ' + str( len(genomeIds)) + ' genomes.' # get table of PFAMs and do some initial filtering to remove PFAMs that are # clearly not going to pass the ubiquity and single-copy thresholds countTable = img.countTable(genomeIds) countTable = img.filterTable(genomeIds, countTable, ubiquityThreshold * 0.9, singleCopyThreshold * 0.9) markerGenes = markerset.markerGenes( genomeIds, countTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) if len(markerGenes) < minMarkers: continue geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) for genomeId in genomeIds: completeness, contamination = markerset.genomeCheck( colocatedSets, genomeId, countTable) if completeness < completenessThreshold or contamination > contaminationThreshold: degenerateGenomes[genomeId] = degenerateGenomes.get( genomeId, []) + [[ lineage.split(';')[-1].strip(), len(genomeIds), len(colocatedSets), completeness, contamination ]] # write out degenerate genomes metadata = img.genomeMetadata('Final') fout = open('./data/degenerate_genomes.tsv', 'w') fout.write( 'Genome Id\tTaxonomy\tGenome Size (Gbps)\tScaffolds\tBiotic Relationships\tStatus\tLineage\t# genomes\tMarker set size\tCompleteness\tContamination\n' ) for genomeId, data in degenerateGenomes.iteritems(): fout.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy']) + '\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6) + '\t' + str(metadata[genomeId]['scaffold count'])) fout.write('\t' + metadata[genomeId]['biotic relationships'] + '\t' + metadata[genomeId]['status']) for d in data: fout.write('\t' + d[0] + '\t' + str(d[1]) + '\t' + str(d[2]) + '\t%.3f\t%.3f' % (d[3], d[4])) fout.write('\n') fout.close()
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold, numBins, numRndGenomes): img = IMG() markerSet = MarkerSet() metadata = img.genomeMetadata() lineageGenomeIds = img.genomeIdsByTaxonomy(taxonomyStr, metadata) # build marker set from finished prokaryotic genomes genomeIds = [] for genomeId in lineageGenomeIds: if metadata[genomeId]['status'] == 'Finished' and ( metadata[genomeId]['taxonomy'][0] == 'Bacteria' or metadata[genomeId]['taxonomy'][0] == 'Archaea'): genomeIds.append(genomeId) genomeIds = set(genomeIds) - img.genomesWithMissingData(genomeIds) print 'Lineage ' + taxonomyStr + ' contains ' + str( len(genomeIds)) + ' genomes.' # get marker set countTable = img.countTable(genomeIds) countTable = img.filterTable(genomeIds, countTable, 0.9 * ubiquityThreshold, 0.9 * singleCopyThreshold) markerGenes = markerSet.markerGenes( genomeIds, countTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) tigrToRemove = img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) print 'Number of marker genes: ' + str(len(markerGenes)) # randomly set genomes to plot if numRndGenomes != -1: genomeIds = random.sample(list(genomeIds), numRndGenomes) genomeIds = set(genomeIds) # plot distribution of marker genes filename = 'geneDistribution.' + taxonomyStr.replace( ';', '_') + '.' + str(ubiquityThreshold) + '-' + str( singleCopyThreshold) + '.tsv' fout = open(filename, 'w') fout.write( 'Genome ID\tLineage\tNumber of Genes\tUniformity\tDistribution\n') matrix = [] rowLabels = [] for genomeId in genomeIds: binSize = float(metadata[genomeId]['genome size']) / numBins binCounts = [0] * numBins pts = [] for _, data in geneDistTable[genomeId].iteritems(): for genePos in data: binNum = int(genePos[1] / binSize) binCounts[binNum] += 1 pts.append(genePos[1]) matrix.append(binCounts) u = markerSet.uniformity(metadata[genomeId]['genome size'], pts) fout.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy']) + '\t' + str(len(geneDistTable[genomeId])) + '\t%.3f' % u) for b in xrange(0, numBins): fout.write('\t' + str(binCounts[b])) fout.write('\n') rowLabels.append('%.2f' % u + ', ' + str(genomeId) + ' - ' + '; '.join(metadata[genomeId]['taxonomy'][0:5])) fout.close() # plot data heatmap = Heatmap() plotFilename = 'geneDistribution.' + taxonomyStr.replace( ';', '_') + '.' + str(ubiquityThreshold) + '-' + str( singleCopyThreshold) + '.png' heatmap.plot(plotFilename, matrix, rowLabels, 0.6)
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold, numBins, numRndGenomes): img = IMG() markerSet = MarkerSet() metadata = img.genomeMetadata() lineageGenomeIds = img.genomeIdsByTaxonomy(taxonomyStr, metadata) # build marker set from finished prokaryotic genomes genomeIds = [] for genomeId in lineageGenomeIds: if metadata[genomeId]['status'] == 'Finished' and (metadata[genomeId]['taxonomy'][0] == 'Bacteria' or metadata[genomeId]['taxonomy'][0] == 'Archaea'): genomeIds.append(genomeId) genomeIds = set(genomeIds) - img.genomesWithMissingData(genomeIds) print 'Lineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) + ' genomes.' # get marker set countTable = img.countTable(genomeIds) countTable = img.filterTable(genomeIds, countTable, 0.9*ubiquityThreshold, 0.9*singleCopyThreshold) markerGenes = markerSet.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) tigrToRemove = img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6) print 'Number of marker genes: ' + str(len(markerGenes)) # randomly set genomes to plot if numRndGenomes != -1: genomeIds = random.sample(list(genomeIds), numRndGenomes) genomeIds = set(genomeIds) # plot distribution of marker genes filename = 'geneDistribution.' + taxonomyStr.replace(';','_') + '.' + str(ubiquityThreshold) + '-' + str(singleCopyThreshold) + '.tsv' fout = open(filename, 'w') fout.write('Genome ID\tLineage\tNumber of Genes\tUniformity\tDistribution\n') matrix = [] rowLabels = [] for genomeId in genomeIds: binSize = float(metadata[genomeId]['genome size']) / numBins binCounts = [0]*numBins pts = [] for _, data in geneDistTable[genomeId].iteritems(): for genePos in data: binNum = int(genePos[1] / binSize) binCounts[binNum] += 1 pts.append(genePos[1]) matrix.append(binCounts) u = markerSet.uniformity(metadata[genomeId]['genome size'], pts) fout.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy']) + '\t' + str(len(geneDistTable[genomeId])) + '\t%.3f' % u) for b in xrange(0, numBins): fout.write('\t' + str(binCounts[b])) fout.write('\n') rowLabels.append('%.2f' % u + ', ' + str(genomeId) + ' - ' + '; '.join(metadata[genomeId]['taxonomy'][0:5])) fout.close() # plot data heatmap = Heatmap() plotFilename = 'geneDistribution.' + taxonomyStr.replace(';','_') + '.' + str(ubiquityThreshold) + '-' + str(singleCopyThreshold) + '.png' heatmap.plot(plotFilename, matrix, rowLabels, 0.6)
class MarkerSetStabilityTest(object): def __init__(self): self.img = IMG() self.markerset = MarkerSet() def __processLineage(self, metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, queueIn, queueOut): """Assess stability of marker set for a specific named taxonomic group.""" while True: lineage = queueIn.get(block=True, timeout=None) if lineage == None: break genomeIds = self.img.genomeIdsByTaxonomy(lineage, metadata, 'trusted') markerGenes = [] perChange = [] numGenomesToSelect = int(0.9 * len(genomeIds)) if len(genomeIds) >= minGenomes: # calculate marker set for all genomes in lineage geneCountTable = self.img.geneCountTable(genomeIds) markerGenes = self.markerset.markerGenes( genomeIds, geneCountTable, ubiquityThreshold * len(genomeIds), singleCopyThreshold * len(genomeIds)) tigrToRemove = self.img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove for _ in range(0, 100): # calculate marker set for subset of genomes subsetGenomeIds = random.sample(genomeIds, numGenomesToSelect) geneCountTable = self.img.geneCountTable(subsetGenomeIds) subsetMarkerGenes = self.markerset.markerGenes( subsetGenomeIds, geneCountTable, ubiquityThreshold * numGenomesToSelect, singleCopyThreshold * numGenomesToSelect) tigrToRemove = self.img.identifyRedundantTIGRFAMs( subsetMarkerGenes) subsetMarkerGenes = subsetMarkerGenes - tigrToRemove perChange.append( float( len( markerGenes.symmetric_difference( subsetMarkerGenes))) * 100.0 / len(markerGenes)) if perChange != []: queueOut.put( (lineage, len(genomeIds), len(markerGenes), numGenomesToSelect, mean(perChange), std(perChange))) else: queueOut.put((lineage, len(genomeIds), len(markerGenes), numGenomesToSelect, -1, -1)) def __storeResults(self, outputFile, totalLineages, writerQueue): """Store results to file.""" fout = open(outputFile, 'w') fout.write( 'Lineage\t# genomes\t# markers\t# sampled genomes\tmean % change\tstd % change\n' ) numProcessedLineages = 0 while True: lineage, numGenomes, numMarkerGenes, numSampledGenomes, meanPerChange, stdPerChange = writerQueue.get( block=True, timeout=None) if lineage == None: break numProcessedLineages += 1 statusStr = ' Finished processing %d of %d (%.2f%%) lineages.' % ( numProcessedLineages, totalLineages, float(numProcessedLineages) * 100 / totalLineages) sys.stdout.write('%s\r' % statusStr) sys.stdout.flush() fout.write('%s\t%d\t%d\t%d\t%f\t%f\n' % (lineage, numGenomes, numMarkerGenes, numSampledGenomes, meanPerChange, stdPerChange)) sys.stdout.write('\n') fout.close() def run(self, outputFile, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, numThreads): """Calculate stability of marker sets for named taxonomic groups.""" print(' Testing stability of marker sets:') random.seed(1) # process each sequence in parallel workerQueue = mp.Queue() writerQueue = mp.Queue() metadata = self.img.genomeMetadata() lineages = self.img.lineagesByCriteria(metadata, minGenomes, mostSpecificRank) for lineage in lineages: workerQueue.put(lineage) for _ in range(numThreads): workerQueue.put(None) calcProc = [ mp.Process(target=self.__processLineage, args=(metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, workerQueue, writerQueue)) for _ in range(numThreads) ] writeProc = mp.Process(target=self.__storeResults, args=(outputFile, len(lineages), writerQueue)) writeProc.start() for p in calcProc: p.start() for p in calcProc: p.join() writerQueue.put((None, None, None, None, None, None)) writeProc.join()
class MarkerSetStability(object): def __init__(self): self.img = IMG() self.markerset = MarkerSet() def __processLineage(self, metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, queueIn, queueOut): """Assess stability of marker set for a specific named taxonomic group.""" while True: lineage = queueIn.get(block=True, timeout=None) if lineage == None: break genomeIds = self.img.genomeIdsByTaxonomy(lineage, metadata, 'trusted') changeMarkerSetSize = {} markerGenes = [] if len(genomeIds) >= minGenomes: # calculate marker set for all genomes in lineage geneCountTable = self.img.geneCountTable(genomeIds) markerGenes = self.markerset.markerGenes(genomeIds, geneCountTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) tigrToRemove = self.img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove for selectPer in xrange(50, 101, 5): numGenomesToSelect = int(float(selectPer)/100 * len(genomeIds)) perChange = [] for _ in xrange(0, 10): # calculate marker set for subset of genomes subsetGenomeIds = random.sample(genomeIds, numGenomesToSelect) geneCountTable = self.img.geneCountTable(subsetGenomeIds) subsetMarkerGenes = self.markerset.markerGenes(subsetGenomeIds, geneCountTable, ubiquityThreshold*numGenomesToSelect, singleCopyThreshold*numGenomesToSelect) tigrToRemove = self.img.identifyRedundantTIGRFAMs(subsetMarkerGenes) subsetMarkerGenes = subsetMarkerGenes - tigrToRemove perChange.append(float(len(markerGenes.symmetric_difference(subsetMarkerGenes)))*100.0 / len(markerGenes)) changeMarkerSetSize[selectPer] = [mean(perChange), std(perChange)] queueOut.put((lineage, len(genomeIds), len(markerGenes), changeMarkerSetSize)) def __storeResults(self, outputFile, totalLineages, writerQueue): """Store results to file.""" fout = open(outputFile, 'w') fout.write('Lineage\t# genomes\t# markers\tsubsample %\tmean % change\tstd % change\n') numProcessedLineages = 0 while True: lineage, numGenomes, numMarkerGenes, changeMarkerSetSize = writerQueue.get(block=True, timeout=None) if lineage == None: break numProcessedLineages += 1 statusStr = ' Finished processing %d of %d (%.2f%%) lineages.' % (numProcessedLineages, totalLineages, float(numProcessedLineages)*100/totalLineages) sys.stdout.write('%s\r' % statusStr) sys.stdout.flush() for selectPer in sorted(changeMarkerSetSize.keys()): fout.write('%s\t%d\t%d\t%d\t%f\t%f\n' % (lineage, numGenomes, numMarkerGenes, selectPer, changeMarkerSetSize[selectPer][0], changeMarkerSetSize[selectPer][1])) sys.stdout.write('\n') fout.close() def run(self, outputFile, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, numThreads): """Calculate stability of marker sets for named taxonomic groups.""" print ' Calculating stability of marker sets:' random.seed(1) # process each sequence in parallel workerQueue = mp.Queue() writerQueue = mp.Queue() metadata = self.img.genomeMetadata() lineages = self.img.lineagesByCriteria(metadata, minGenomes, mostSpecificRank) #lineages = ['Bacteria'] #lineages += ['Bacteria;Proteobacteria'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae;Escherichia'] #lineages += ['Bacteria;Proteobacteria;Gammaproteobacteria;Enterobacteriales;Enterobacteriaceae;Escherichia;coli'] #lineages = ['Archaea'] #lineages += ['Archaea;Euryarchaeota'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia;Methanosarcinales'] #lineages += ['Archaea;Euryarchaeota;Methanomicrobia;Methanosarcinales;Methanosarcinaceae'] for lineage in lineages: workerQueue.put(lineage) for _ in range(numThreads): workerQueue.put(None) calcProc = [mp.Process(target = self.__processLineage, args = (metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, workerQueue, writerQueue)) for _ in range(numThreads)] writeProc = mp.Process(target = self.__storeResults, args = (outputFile, len(lineages), writerQueue)) writeProc.start() for p in calcProc: p.start() for p in calcProc: p.join() writerQueue.put((None, None, None, None)) writeProc.join()
def run(self, ubiquityThreshold, singleCopyThreshold, trustedCompleteness, trustedContamination, genomeCompleteness, genomeContamination): img = IMG() markerset = MarkerSet() metadata = img.genomeMetadata() trustedOut = open('./data/trusted_genomes.tsv', 'w') trustedOut.write('Genome Id\tLineage\tGenome size (Mbps)\tScaffold count\tBiotic Relationship\tStatus\tCompleteness\tContamination\n') filteredOut = open('./data/filtered_genomes.tsv', 'w') filteredOut.write('Genome Id\tLineage\tGenome size (Mbps)\tScaffold count\tBiotic Relationship\tStatus\tCompleteness\tContamination\n') allGenomeIds = set() allTrustedGenomeIds = set() for lineage in ['Archaea', 'Bacteria']: # get all genomes in lineage and build gene count table print '\nBuilding gene count table.' allLineageGenomeIds = img.genomeIdsByTaxonomy(lineage, metadata, 'All') countTable = img.countTable(allLineageGenomeIds) countTable = img.filterTable(allLineageGenomeIds, countTable, 0.9*ubiquityThreshold, 0.9*singleCopyThreshold) # get all genomes from specific lineage allGenomeIds = allGenomeIds.union(allLineageGenomeIds) print 'Lineage ' + lineage + ' contains ' + str(len(allLineageGenomeIds)) + ' genomes.' # tabulate genomes from each phylum allPhylumCounts = {} for genomeId in allLineageGenomeIds: taxon = metadata[genomeId]['taxonomy'][1] allPhylumCounts[taxon] = allPhylumCounts.get(taxon, 0) + 1 # identify marker set for genomes markerGenes = markerset.markerGenes(allLineageGenomeIds, countTable, ubiquityThreshold*len(allLineageGenomeIds), singleCopyThreshold*len(allLineageGenomeIds)) print ' Marker genes: ' + str(len(markerGenes)) geneDistTable = img.geneDistTable(allLineageGenomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable, metadata) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) print ' Marker set size: ' + str(len(colocatedSets)) # identifying trusted genomes (highly complete, low contamination genomes) trustedGenomeIds = set() for genomeId in allLineageGenomeIds: completeness, contamination = markerset.genomeCheck(colocatedSets, genomeId, countTable) if completeness >= trustedCompleteness and contamination <= trustedContamination: trustedGenomeIds.add(genomeId) allTrustedGenomeIds.add(genomeId) trustedOut.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy'])) trustedOut.write('\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6)) trustedOut.write('\t' + str(metadata[genomeId]['scaffold count'])) trustedOut.write('\t' + metadata[genomeId]['biotic relationships']) trustedOut.write('\t' + metadata[genomeId]['status']) trustedOut.write('\t%.3f\t%.3f' % (completeness, contamination) + '\n') else: filteredOut.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy'])) filteredOut.write('\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6)) filteredOut.write('\t' + str(metadata[genomeId]['scaffold count'])) filteredOut.write('\t' + metadata[genomeId]['biotic relationships']) filteredOut.write('\t' + metadata[genomeId]['status']) filteredOut.write('\t%.3f\t%.3f' % (completeness, contamination) + '\n') print ' Trusted genomes: ' + str(len(trustedGenomeIds)) # determine status of trusted genomes statusBreakdown = {} for genomeId in trustedGenomeIds: statusBreakdown[metadata[genomeId]['status']] = statusBreakdown.get(metadata[genomeId]['status'], 0) + 1 print ' Trusted genome status breakdown: ' for status, count in statusBreakdown.iteritems(): print ' ' + status + ': ' + str(count) # determine status of retained genomes proposalNameBreakdown = {} for genomeId in trustedGenomeIds: proposalNameBreakdown[metadata[genomeId]['proposal name']] = proposalNameBreakdown.get(metadata[genomeId]['proposal name'], 0) + 1 print ' Retained genome proposal name breakdown: ' for pn, count in proposalNameBreakdown.iteritems(): if 'KMG' in pn or 'GEBA' in pn or 'HMP' in pn: print ' ' + pn + ': ' + str(count) print ' Filtered genomes by phylum:' trustedPhylumCounts = {} for genomeId in trustedGenomeIds: taxon = metadata[genomeId]['taxonomy'][1] trustedPhylumCounts[taxon] = trustedPhylumCounts.get(taxon, 0) + 1 for phylum, count in allPhylumCounts.iteritems(): print phylum + ': %d of %d' % (trustedPhylumCounts.get(phylum, 0), count) trustedOut.close() filteredOut.close() # write out lineage statistics for genome distribution allStats = {} trustedStats = {} for r in xrange(0, 6): # Domain to Genus for genomeId, data in metadata.iteritems(): taxaStr = '; '.join(data['taxonomy'][0:r+1]) allStats[taxaStr] = allStats.get(taxaStr, 0) + 1 if genomeId in allTrustedGenomeIds: trustedStats[taxaStr] = trustedStats.get(taxaStr, 0) + 1 sortedLineages = img.lineagesSorted() fout = open('./data/lineage_stats.tsv', 'w') fout.write('Lineage\tGenomes with metadata\tTrusted genomes\n') for lineage in sortedLineages: fout.write(lineage + '\t' + str(allStats.get(lineage, 0))+ '\t' + str(trustedStats.get(lineage, 0))+ '\n') fout.close()
def run(self, ubiquityThreshold, singleCopyThreshold, trustedCompleteness, trustedContamination, genomeCompleteness, genomeContamination): img = IMG() markerset = MarkerSet() metadata = img.genomeMetadata() trustedOut = open('./data/trusted_genomes.tsv', 'w') trustedOut.write( 'Genome Id\tLineage\tGenome size (Mbps)\tScaffold count\tBiotic Relationship\tStatus\tCompleteness\tContamination\n' ) filteredOut = open('./data/filtered_genomes.tsv', 'w') filteredOut.write( 'Genome Id\tLineage\tGenome size (Mbps)\tScaffold count\tBiotic Relationship\tStatus\tCompleteness\tContamination\n' ) allGenomeIds = set() allTrustedGenomeIds = set() for lineage in ['Archaea', 'Bacteria']: # get all genomes in lineage and build gene count table print '\nBuilding gene count table.' allLineageGenomeIds = img.genomeIdsByTaxonomy( lineage, metadata, 'All') countTable = img.countTable(allLineageGenomeIds) countTable = img.filterTable(allLineageGenomeIds, countTable, 0.9 * ubiquityThreshold, 0.9 * singleCopyThreshold) # get all genomes from specific lineage allGenomeIds = allGenomeIds.union(allLineageGenomeIds) print 'Lineage ' + lineage + ' contains ' + str( len(allLineageGenomeIds)) + ' genomes.' # tabulate genomes from each phylum allPhylumCounts = {} for genomeId in allLineageGenomeIds: taxon = metadata[genomeId]['taxonomy'][1] allPhylumCounts[taxon] = allPhylumCounts.get(taxon, 0) + 1 # identify marker set for genomes markerGenes = markerset.markerGenes( allLineageGenomeIds, countTable, ubiquityThreshold * len(allLineageGenomeIds), singleCopyThreshold * len(allLineageGenomeIds)) print ' Marker genes: ' + str(len(markerGenes)) geneDistTable = img.geneDistTable(allLineageGenomeIds, markerGenes, spacingBetweenContigs=1e6) colocatedGenes = markerset.colocatedGenes(geneDistTable, metadata) colocatedSets = markerset.colocatedSets(colocatedGenes, markerGenes) print ' Marker set size: ' + str(len(colocatedSets)) # identifying trusted genomes (highly complete, low contamination genomes) trustedGenomeIds = set() for genomeId in allLineageGenomeIds: completeness, contamination = markerset.genomeCheck( colocatedSets, genomeId, countTable) if completeness >= trustedCompleteness and contamination <= trustedContamination: trustedGenomeIds.add(genomeId) allTrustedGenomeIds.add(genomeId) trustedOut.write(genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy'])) trustedOut.write( '\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6)) trustedOut.write('\t' + str(metadata[genomeId]['scaffold count'])) trustedOut.write( '\t' + metadata[genomeId]['biotic relationships']) trustedOut.write('\t' + metadata[genomeId]['status']) trustedOut.write('\t%.3f\t%.3f' % (completeness, contamination) + '\n') else: filteredOut.write( genomeId + '\t' + '; '.join(metadata[genomeId]['taxonomy'])) filteredOut.write( '\t%.2f' % (float(metadata[genomeId]['genome size']) / 1e6)) filteredOut.write( '\t' + str(metadata[genomeId]['scaffold count'])) filteredOut.write( '\t' + metadata[genomeId]['biotic relationships']) filteredOut.write('\t' + metadata[genomeId]['status']) filteredOut.write('\t%.3f\t%.3f' % (completeness, contamination) + '\n') print ' Trusted genomes: ' + str(len(trustedGenomeIds)) # determine status of trusted genomes statusBreakdown = {} for genomeId in trustedGenomeIds: statusBreakdown[metadata[genomeId] ['status']] = statusBreakdown.get( metadata[genomeId]['status'], 0) + 1 print ' Trusted genome status breakdown: ' for status, count in statusBreakdown.iteritems(): print ' ' + status + ': ' + str(count) # determine status of retained genomes proposalNameBreakdown = {} for genomeId in trustedGenomeIds: proposalNameBreakdown[metadata[genomeId][ 'proposal name']] = proposalNameBreakdown.get( metadata[genomeId]['proposal name'], 0) + 1 print ' Retained genome proposal name breakdown: ' for pn, count in proposalNameBreakdown.iteritems(): if 'KMG' in pn or 'GEBA' in pn or 'HMP' in pn: print ' ' + pn + ': ' + str(count) print ' Filtered genomes by phylum:' trustedPhylumCounts = {} for genomeId in trustedGenomeIds: taxon = metadata[genomeId]['taxonomy'][1] trustedPhylumCounts[taxon] = trustedPhylumCounts.get(taxon, 0) + 1 for phylum, count in allPhylumCounts.iteritems(): print phylum + ': %d of %d' % (trustedPhylumCounts.get( phylum, 0), count) trustedOut.close() filteredOut.close() # write out lineage statistics for genome distribution allStats = {} trustedStats = {} for r in xrange(0, 6): # Domain to Genus for genomeId, data in metadata.iteritems(): taxaStr = '; '.join(data['taxonomy'][0:r + 1]) allStats[taxaStr] = allStats.get(taxaStr, 0) + 1 if genomeId in allTrustedGenomeIds: trustedStats[taxaStr] = trustedStats.get(taxaStr, 0) + 1 sortedLineages = img.lineagesSorted() fout = open('./data/lineage_stats.tsv', 'w') fout.write('Lineage\tGenomes with metadata\tTrusted genomes\n') for lineage in sortedLineages: fout.write(lineage + '\t' + str(allStats.get(lineage, 0)) + '\t' + str(trustedStats.get(lineage, 0)) + '\n') fout.close()
class MarkerSetStabilityTest(object): def __init__(self): self.img = IMG() self.markerset = MarkerSet() def __processLineage(self, metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, queueIn, queueOut): """Assess stability of marker set for a specific named taxonomic group.""" while True: lineage = queueIn.get(block=True, timeout=None) if lineage == None: break genomeIds = self.img.genomeIdsByTaxonomy(lineage, metadata, 'trusted') markerGenes = [] perChange = [] numGenomesToSelect = int(0.9*len(genomeIds)) if len(genomeIds) >= minGenomes: # calculate marker set for all genomes in lineage geneCountTable = self.img.geneCountTable(genomeIds) markerGenes = self.markerset.markerGenes(genomeIds, geneCountTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds)) tigrToRemove = self.img.identifyRedundantTIGRFAMs(markerGenes) markerGenes = markerGenes - tigrToRemove for _ in xrange(0, 100): # calculate marker set for subset of genomes subsetGenomeIds = random.sample(genomeIds, numGenomesToSelect) geneCountTable = self.img.geneCountTable(subsetGenomeIds) subsetMarkerGenes = self.markerset.markerGenes(subsetGenomeIds, geneCountTable, ubiquityThreshold*numGenomesToSelect, singleCopyThreshold*numGenomesToSelect) tigrToRemove = self.img.identifyRedundantTIGRFAMs(subsetMarkerGenes) subsetMarkerGenes = subsetMarkerGenes - tigrToRemove perChange.append(float(len(markerGenes.symmetric_difference(subsetMarkerGenes)))*100.0 / len(markerGenes)) if perChange != []: queueOut.put((lineage, len(genomeIds), len(markerGenes), numGenomesToSelect, mean(perChange), std(perChange))) else: queueOut.put((lineage, len(genomeIds), len(markerGenes), numGenomesToSelect, -1, -1)) def __storeResults(self, outputFile, totalLineages, writerQueue): """Store results to file.""" fout = open(outputFile, 'w') fout.write('Lineage\t# genomes\t# markers\t# sampled genomes\tmean % change\tstd % change\n') numProcessedLineages = 0 while True: lineage, numGenomes, numMarkerGenes, numSampledGenomes, meanPerChange, stdPerChange = writerQueue.get(block=True, timeout=None) if lineage == None: break numProcessedLineages += 1 statusStr = ' Finished processing %d of %d (%.2f%%) lineages.' % (numProcessedLineages, totalLineages, float(numProcessedLineages)*100/totalLineages) sys.stdout.write('%s\r' % statusStr) sys.stdout.flush() fout.write('%s\t%d\t%d\t%d\t%f\t%f\n' % (lineage, numGenomes, numMarkerGenes, numSampledGenomes, meanPerChange, stdPerChange)) sys.stdout.write('\n') fout.close() def run(self, outputFile, ubiquityThreshold, singleCopyThreshold, minGenomes, mostSpecificRank, numThreads): """Calculate stability of marker sets for named taxonomic groups.""" print ' Testing stability of marker sets:' random.seed(1) # process each sequence in parallel workerQueue = mp.Queue() writerQueue = mp.Queue() metadata = self.img.genomeMetadata() lineages = self.img.lineagesByCriteria(metadata, minGenomes, mostSpecificRank) for lineage in lineages: workerQueue.put(lineage) for _ in range(numThreads): workerQueue.put(None) calcProc = [mp.Process(target = self.__processLineage, args = (metadata, ubiquityThreshold, singleCopyThreshold, minGenomes, workerQueue, writerQueue)) for _ in range(numThreads)] writeProc = mp.Process(target = self.__storeResults, args = (outputFile, len(lineages), writerQueue)) writeProc.start() for p in calcProc: p.start() for p in calcProc: p.join() writerQueue.put((None, None, None, None, None, None)) writeProc.join()