def run(self, taxonomyStr, minThreshold, maxThreshold, stepSize):
img = IMG()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print 'Lineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) + ' genomes.'
markerSetSizes = []
countTable = img.countTable(genomeIds)
for threshold in arange(maxThreshold, minThreshold, -stepSize):
markerGenes = img.markerGenes(genomeIds, countTable, threshold*len(genomeIds), threshold*len(genomeIds))
geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
markerSetSizes.append(len(colocatedSets))
print ' Threshold = %.2f, marker set size = %d' % (threshold, len(markerGenes))
# plot data
plot = LinePlot()
plotFilename = './images/markerSetSize.' + taxonomyStr.replace(';','_') + '.png'
title = taxonomyStr.replace(';', '; ')
plot.plot(plotFilename, arange(maxThreshold, minThreshold, -stepSize), markerSetSizes, 'Threshold', 'Marker Set Size', title)
def run(self, taxonomyStr, minThreshold, maxThreshold, stepSize):
img = IMG()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print('Lineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) + ' genomes.')
markerSetSizes = []
countTable = img.countTable(genomeIds)
for threshold in arange(maxThreshold, minThreshold, -stepSize):
markerGenes = img.markerGenes(genomeIds, countTable, threshold*len(genomeIds), threshold*len(genomeIds))
geneDistTable = img.geneDistTable(genomeIds, markerGenes, spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
markerSetSizes.append(len(colocatedSets))
print(' Threshold = %.2f, marker set size = %d' % (threshold, len(markerGenes)))
# plot data
plot = LinePlot()
plotFilename = './images/markerSetSize.' + taxonomyStr.replace(';','_') + '.png'
title = taxonomyStr.replace(';', '; ')
plot.plot(plotFilename, arange(maxThreshold, minThreshold, -stepSize), markerSetSizes, 'Threshold', 'Marker Set Size', title)
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold,
percentCompletion, numReplicates, numGenomes, contigLen):
img = IMG()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print('\nLineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) +
' genomes.')
# build marker genes and colocated marker sets
countTable = img.countTable(genomeIds)
markerGenes = img.markerGenes(genomeIds, countTable,
ubiquityThreshold * len(genomeIds),
singleCopyThreshold * len(genomeIds))
print(' Marker genes: ' + str(len(markerGenes)))
geneDistTable = img.geneDistTable(genomeIds,
markerGenes,
spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
print(' Co-located gene sets: ' + str(len(colocatedSets)))
# random sample genomes
if numGenomes == -1:
rndGenomeIds = genomeIds
else:
rndGenomeIds = random.sample(genomeIds, numGenomes)
# estimate completion for each genome using both the marker genes and marker sets
metadata = img.genomeMetadata('Final')
plotLabels = []
plotData = []
for genomeId in rndGenomeIds:
mgCompletion = []
msCompletion = []
for _ in range(0, numReplicates):
startPartialGenomeContigs = img.sampleGenome(
metadata[genomeId]['genome size'], percentCompletion,
contigLen)
# calculate completion with marker genes
containedMarkerGenes = img.containedMarkerGenes(
markerGenes, geneDistTable[genomeId],
startPartialGenomeContigs, contigLen)
mgCompletion.append(
float(len(containedMarkerGenes)) / len(markerGenes) -
percentCompletion)
# calculate completion with marker set
comp = 0.0
for cs in colocatedSets:
present = 0
for contigId in cs:
if contigId in containedMarkerGenes:
present += 1
comp += float(present) / len(cs)
msCompletion.append(comp / len(colocatedSets) -
percentCompletion)
plotData.append(mgCompletion)
plotData.append(msCompletion)
species = ' '.join(
metadata[genomeId]['taxonomy'][ranksByLabel['Genus']:])
plotLabels.append(species + ' (' + genomeId + ')')
plotLabels.append('')
# plot data
boxPlot = BoxPlot()
plotFilename = './images/sim.MGvsMS.' + taxonomyStr.replace(
';', '_') + '.' + str(percentCompletion) + '.errorbar.png'
title = taxonomyStr.replace(
';', '; ') + '\n' + 'Percent completion = %.2f' % percentCompletion
boxPlot.plot(plotFilename, plotData, plotLabels,
r'$\Delta$' + ' Percent Completion', '', False, title)
def run(self, taxonomyStr, mostSpecificRank, minGenomes, ubiquityThreshold,
singleCopyThreshold, percentCompletion, numReplicates, numGenomes,
contigLen):
img = IMG()
lineages = []
taxon = taxonomyStr.split(';')
for r in range(0, len(taxon)):
lineages.append(';'.join(taxon[0:r + 1]))
# get all marker sets
markerGenes = []
geneDistTable = []
colocatedSets = []
for lineage in lineages:
genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final')
print('\nLineage ' + lineage + ' contains ' + str(len(genomeIds)) +
' genomes.')
# build marker genes and colocated marker sets
countTable = img.countTable(genomeIds)
mg = img.markerGenes(genomeIds, countTable,
ubiquityThreshold * len(genomeIds),
singleCopyThreshold * len(genomeIds))
print(' Marker genes: ' + str(len(mg)))
mdt = img.geneDistTable(genomeIds, mg, spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(mdt)
cs = img.colocatedSets(colocatedGenes, mg)
print(' Co-located gene sets: ' + str(len(cs)))
markerGenes.append(mg)
geneDistTable.append(mdt)
colocatedSets.append(cs)
# random sample genomes
if numGenomes == -1:
rndGenomeIds = genomeIds
else:
rndGenomeIds = random.sample(genomeIds, numGenomes)
# estimate completion for each genome using both the marker genes and marker sets
metadata = img.genomeMetadata('Final')
plotLabels = []
plotData = []
for genomeId in rndGenomeIds:
completion = [[] for _ in range(len(lineages))]
for _ in range(0, numReplicates):
startPartialGenomeContigs = img.sampleGenome(
metadata[genomeId]['genome size'], percentCompletion,
contigLen)
# calculate completion with marker set
for i in range(len(lineages)):
containedMarkerGenes = img.containedMarkerGenes(
markerGenes[i], geneDistTable[i][genomeId],
startPartialGenomeContigs, contigLen)
comp = 0.0
for cs in colocatedSets[i]:
present = 0
for contigId in cs:
if contigId in containedMarkerGenes:
present += 1
comp += float(present) / len(cs)
completion[i].append(comp / len(colocatedSets[i]) -
percentCompletion)
plotLabels.append(genomeId + ' - ' + lineages[i])
for d in completion:
plotData.append(d)
# plot data
boxPlot = BoxPlot()
plotFilename = './images/sim.lineages.' + taxonomyStr.replace(
';', '_') + '.' + str(percentCompletion) + '.errorbar.png'
title = taxonomyStr.replace(
';', '; ') + '\n' + 'Percent completion = %.2f' % percentCompletion
boxPlot.plot(plotFilename, plotData, plotLabels,
r'$\Delta$' + ' Percent Completion', '', False, title)
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold, percentCompletion, numReplicates, numGenomes, contigLen):
img = IMG()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print '\nLineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) + ' genomes.'
# build marker genes and colocated marker sets
countTable = img.countTable(genomeIds)
markerGenes = img.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds))
print ' Marker genes: ' + str(len(markerGenes))
geneDistTable = img.geneDistTable(genomeIds, markerGenes)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
print ' Co-located gene sets: ' + str(len(colocatedSets))
# random sample genomes
if numGenomes == -1:
rndGenomeIds = genomeIds
else:
rndGenomeIds = random.sample(genomeIds, numGenomes)
# estimate completion for each genome using both the marker genes and marker sets
metadata = img.genomeMetadata('Final')
plotLabels = []
plotData = []
for genomeId in rndGenomeIds:
mgCompletion = []
msCompletion = []
for _ in xrange(0, numReplicates):
startPartialGenomeContigs = img.sampleGenome(metadata[genomeId]['genome size'], percentCompletion, contigLen)
# calculate completion with marker genes
containedMarkerGenes = img.containedMarkerGenes(markerGenes, geneDistTable[genomeId], startPartialGenomeContigs, contigLen)
mgCompletion.append(float(len(containedMarkerGenes))/len(markerGenes) - percentCompletion)
# calculate completion with marker set
comp = 0.0
for cs in colocatedSets:
present = 0
for contigId in cs:
if contigId in containedMarkerGenes:
present += 1
comp += float(present) / len(cs)
msCompletion.append(comp / len(colocatedSets) - percentCompletion)
plotData.append(mgCompletion)
plotData.append(msCompletion)
species = ' '.join(metadata[genomeId]['taxonomy'][ranksByLabel['Genus']:])
plotLabels.append(species + ' (' + genomeId + ')')
plotLabels.append('')
# plot data
boxPlot = BoxPlot()
plotFilename = './images/sim.MGvsMS.' + taxonomyStr.replace(';','_') + '.' + str(percentCompletion) + '.errorbar.png'
title = taxonomyStr.replace(';', '; ') + '\n' + 'Percent completion = %.2f' % percentCompletion
boxPlot.plot(plotFilename, plotData, plotLabels, r'$\Delta$' + ' Percent Completion', '', False, title)
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold,
replicates, minGenomes, maxGenomes, stepSize):
img = IMG()
markergenes = MarkerGenes()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print('Lineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) +
' genomes.')
if len(genomeIds) < minGenomes:
sys.stderr.write('[Error] Insufficent number of genomes.\n')
sys.exit()
print('')
print('Ubiquity threshold: ' + str(ubiquityThreshold))
print('Single-copy threshold: ' + str(singleCopyThreshold))
meanMarkerSetSize = []
stdMarkerSetSize = []
markerSetSizes = []
if maxGenomes == -1:
maxGenomes = len(genomeIds)
if maxGenomes > len(genomeIds):
maxGenomes = len(genomeIds)
countTable = img.countTable(genomeIds)
countTable = img.filterTable(genomeIds, countTable)
for numGenomes in range(minGenomes, maxGenomes, stepSize):
markerSetSize = []
for _ in range(0, replicates):
genomeIdSubset = random.sample(genomeIds, numGenomes)
markerGenes = markergenes.identify(
genomeIdSubset, countTable,
ubiquityThreshold * len(genomeIdSubset),
singleCopyThreshold * len(genomeIdSubset))
geneDistTable = img.geneDistTable(genomeIdSubset,
markerGenes,
spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
markerSetSize.append(len(colocatedSets))
markerSetSizes.append(markerSetSize)
m = mean(markerSetSize)
meanMarkerSetSize.append(m)
s = std(markerSetSize)
stdMarkerSetSize.append(s)
print('')
print('Genomes: ' + str(numGenomes) + ', Ubiquity > ' +
str(int(ubiquityThreshold * len(genomeIdSubset))) +
', Single-copy > ' +
str(int(singleCopyThreshold * len(genomeIdSubset))))
print('Mean: %.2f +/- %.2f' % (m, s))
print('Min: %d, Max: %d' %
(min(markerSetSize), max(markerSetSize)))
# plot data
errorBar = ErrorBar()
plotFilename = './images/markerset.' + taxonomyStr.replace(
';', '_') + '.' + str(ubiquityThreshold) + '-' + str(
singleCopyThreshold) + '.errorbar.png'
title = taxonomyStr.replace(
';', '; '
) + '\n' + 'Ubiquity = %.2f' % ubiquityThreshold + ', Single-copy = %.2f' % singleCopyThreshold
errorBar.plot(plotFilename, arange(minGenomes, maxGenomes, stepSize),
meanMarkerSetSize, stdMarkerSetSize, 'Number of Genomes',
'Marker Set Size', title)
boxPlot = BoxPlot()
plotFilename = './images/markerset.' + taxonomyStr.replace(
';', '_') + '.' + str(ubiquityThreshold) + '-' + str(
singleCopyThreshold) + '.boxplot.png'
boxPlot.plot(plotFilename, markerSetSizes,
arange(minGenomes, maxGenomes, stepSize),
'Number of Genomes', 'Marker Set Size', True, title)
def run(self, taxonomyStr, ubiquityThreshold, singleCopyThreshold, replicates, minGenomes, maxGenomes, stepSize):
img = IMG()
markergenes = MarkerGenes()
genomeIds = img.genomeIdsByTaxonomy(taxonomyStr, 'Final')
print 'Lineage ' + taxonomyStr + ' contains ' + str(len(genomeIds)) + ' genomes.'
if len(genomeIds) < minGenomes:
sys.stderr.write('[Error] Insufficent number of genomes.\n')
sys.exit()
print ''
print 'Ubiquity threshold: ' + str(ubiquityThreshold)
print 'Single-copy threshold: ' + str(singleCopyThreshold)
meanMarkerSetSize = []
stdMarkerSetSize = []
markerSetSizes = []
if maxGenomes == -1:
maxGenomes = len(genomeIds)
if maxGenomes > len(genomeIds):
maxGenomes = len(genomeIds)
countTable = img.countTable(genomeIds)
countTable = img.filterTable(genomeIds, countTable)
for numGenomes in xrange(minGenomes, maxGenomes, stepSize):
markerSetSize = []
for _ in xrange(0, replicates):
genomeIdSubset = random.sample(genomeIds, numGenomes)
markerGenes = markergenes.identify(genomeIdSubset, countTable, ubiquityThreshold*len(genomeIdSubset), singleCopyThreshold*len(genomeIdSubset))
geneDistTable = img.geneDistTable(genomeIdSubset, markerGenes, spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(geneDistTable)
colocatedSets = img.colocatedSets(colocatedGenes, markerGenes)
markerSetSize.append(len(colocatedSets))
markerSetSizes.append(markerSetSize)
m = mean(markerSetSize)
meanMarkerSetSize.append(m)
s = std(markerSetSize)
stdMarkerSetSize.append(s)
print ''
print 'Genomes: ' + str(numGenomes) + ', Ubiquity > ' + str(int(ubiquityThreshold*len(genomeIdSubset))) + ', Single-copy > ' + str(int(singleCopyThreshold*len(genomeIdSubset)))
print 'Mean: %.2f +/- %.2f' % (m, s)
print 'Min: %d, Max: %d' %(min(markerSetSize), max(markerSetSize))
# plot data
errorBar = ErrorBar()
plotFilename = './images/markerset.' + taxonomyStr.replace(';','_') + '.' + str(ubiquityThreshold) + '-' + str(singleCopyThreshold) + '.errorbar.png'
title = taxonomyStr.replace(';', '; ') + '\n' + 'Ubiquity = %.2f' % ubiquityThreshold + ', Single-copy = %.2f' % singleCopyThreshold
errorBar.plot(plotFilename, arange(minGenomes, maxGenomes, stepSize), meanMarkerSetSize, stdMarkerSetSize, 'Number of Genomes', 'Marker Set Size', title)
boxPlot = BoxPlot()
plotFilename = './images/markerset.' + taxonomyStr.replace(';','_') + '.' + str(ubiquityThreshold) + '-' + str(singleCopyThreshold) + '.boxplot.png'
boxPlot.plot(plotFilename, markerSetSizes, arange(minGenomes, maxGenomes, stepSize), 'Number of Genomes', 'Marker Set Size', True, title)
def run(self, taxonomyStr, mostSpecificRank, minGenomes, ubiquityThreshold, singleCopyThreshold, percentCompletion, numReplicates, numGenomes, contigLen):
img = IMG()
lineages = []
taxon = taxonomyStr.split(';')
for r in xrange(0, len(taxon)):
lineages.append(';'.join(taxon[0:r+1]))
# get all marker sets
markerGenes = []
geneDistTable = []
colocatedSets = []
for lineage in lineages:
genomeIds = img.genomeIdsByTaxonomy(lineage, 'Final')
print '\nLineage ' + lineage + ' contains ' + str(len(genomeIds)) + ' genomes.'
# build marker genes and colocated marker sets
countTable = img.countTable(genomeIds)
mg = img.markerGenes(genomeIds, countTable, ubiquityThreshold*len(genomeIds), singleCopyThreshold*len(genomeIds))
print ' Marker genes: ' + str(len(mg))
mdt = img.geneDistTable(genomeIds, mg, spacingBetweenContigs=1e6)
colocatedGenes = img.colocatedGenes(mdt)
cs = img.colocatedSets(colocatedGenes, mg)
print ' Co-located gene sets: ' + str(len(cs))
markerGenes.append(mg)
geneDistTable.append(mdt)
colocatedSets.append(cs)
# random sample genomes
if numGenomes == -1:
rndGenomeIds = genomeIds
else:
rndGenomeIds = random.sample(genomeIds, numGenomes)
# estimate completion for each genome using both the marker genes and marker sets
metadata = img.genomeMetadata('Final')
plotLabels = []
plotData = []
for genomeId in rndGenomeIds:
completion = [[] for _ in xrange(len(lineages))]
for _ in xrange(0, numReplicates):
startPartialGenomeContigs = img.sampleGenome(metadata[genomeId]['genome size'], percentCompletion, contigLen)
# calculate completion with marker set
for i in xrange(len(lineages)):
containedMarkerGenes = img.containedMarkerGenes(markerGenes[i], geneDistTable[i][genomeId], startPartialGenomeContigs, contigLen)
comp = 0.0
for cs in colocatedSets[i]:
present = 0
for contigId in cs:
if contigId in containedMarkerGenes:
present += 1
comp += float(present) / len(cs)
completion[i].append(comp / len(colocatedSets[i]) - percentCompletion)
plotLabels.append(genomeId + ' - ' + lineages[i])
for d in completion:
plotData.append(d)
# plot data
boxPlot = BoxPlot()
plotFilename = './images/sim.lineages.' + taxonomyStr.replace(';','_') + '.' + str(percentCompletion) + '.errorbar.png'
title = taxonomyStr.replace(';', '; ') + '\n' + 'Percent completion = %.2f' % percentCompletion
boxPlot.plot(plotFilename, plotData, plotLabels, r'$\Delta$' + ' Percent Completion', '', False, title)
