def run(self):
img = IMG()
fout = open('./data/evaluate_prodigal.txt', 'w', 1)
# get list of all marker genes
markerset = MarkerSet()
pfamMarkers, tigrMarkers = markerset.getCalculatedMarkerGenes()
print('PFAM marker genes: ' + str(len(tigrMarkers)))
print('TIGR marker genes: ' + str(len(pfamMarkers)))
print('')
# run HMMs on each of the finished genomes
genomeIds = img.genomeIds('Finished')
for genomeId in genomeIds:
print(genomeId + ':')
fout.write(genomeId + ':\n')
self.runProdigal(genomeId)
self.runGeneMark(genomeId)
self.runPFAM(genomeId)
self.runTIGRFAM(genomeId)
self.compareResults(genomeId, pfamMarkers, tigrMarkers, fout)
fout.close()
def run(self, minGenomes, minMarkerSets):
img = IMG()
pfam = PFAM()
# get list of all marker genes
markerset = MarkerSet()
pfamIds, tigrIds = markerset.getCalculatedMarkerGenes()
print 'TIGR marker genes: ' + str(len(tigrIds))
print 'PFAM marker genes: ' + str(len(pfamIds))
# get all PFAM HMMs that are in the same clan
# as any of the marker genes
pfamIdToClanId = pfam.pfamIdToClanId()
clans = set()
for pfamId in pfamIds:
if pfamId.replace('PF', 'pfam') in pfamIdToClanId:
clans.add(pfamIdToClanId[pfamId])
for pfamId, clanId in pfamIdToClanId.iteritems():
if clanId in clans:
pfamIds.add(pfamId)
print ' PFAM HMMs require to cover marker gene clans: ' + str(
len(pfamIds))
# get name of each PFAM HMM
fout = open('./hmm/pfam.keyfile.txt', 'w')
pfamNames = []
for line in open(img.pfamHMMs):
if 'NAME' in line:
name = line[line.find(' '):].strip()
elif 'ACC' in line:
acc = line[line.find(' '):line.rfind('.')].strip()
if acc.replace('PF', 'pfam') in pfamIds:
pfamNames.append(name)
fout.write(name + '\n')
fout.close()
print 'PFAM names: ' + str(len(pfamNames))
# extract each PFAM HMM
os.system('hmmfetch -f ' + img.pfamHMMs +
' ./hmm/pfam.keyfile.txt > ./hmm/pfam_markers.hmm')
# get name of each PFAM HMM
fout = open('./hmm/tigr.keyfile.txt', 'w')
for tigrId in tigrIds:
fout.write(tigrId + '\n')
fout.close()
# extract each PFAM HMM
os.system('hmmfetch -f ' + img.tigrHMMs +
' ./hmm/tigr.keyfile.txt > ./hmm/tigr_markers.hmm')
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,
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 __init__(self):
self.img = IMG()
self.markerset = MarkerSet()
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):
img = IMG()
markerset = MarkerSet()
print('Reading metadata.')
metadata = img.genomeMetadata('Final')
print('Getting marker genes.')
pfamMarkers, tigrMarkers = markerset.getLineageMarkerGenes('Archaea')
markerGenes = pfamMarkers.union(tigrMarkers)
print(' Marker genes: ' + str(len(markerGenes)))
print('Getting genomes of interest.')
genomeIds = img.genomeIdsByTaxonomy('Archaea', 'Final')
print(' Genomes: ' + str(len(genomeIds)))
print('Getting position of each marker gene.')
geneDistTable = img.geneDistTable(genomeIds,
markerGenes,
spacingBetweenContigs=1e6)
spearmanValues = []
pearsonValues = []
genomeIds = list(genomeIds)
for i in range(0, len(genomeIds)):
print(str(i + 1) + ' of ' + str(len(genomeIds)))
geneOrderI = []
maskI = []
for markerGenesId in markerGenes:
if markerGenesId in geneDistTable[genomeIds[i]]:
geneOrderI.append(
float(geneDistTable[genomeIds[i]][markerGenesId][0][0])
/ metadata[genomeIds[i]]['genome size'])
maskI.append(0)
else:
geneOrderI.append(-1)
maskI.append(1)
for j in range(i + 1, len(genomeIds)):
geneOrderJ = []
maskJ = []
for markerGenesId in markerGenes:
if markerGenesId in geneDistTable[genomeIds[j]]:
geneOrderJ.append(
float(geneDistTable[genomeIds[j]][markerGenesId][0]
[0]) / metadata[genomeIds[j]]['genome size'])
maskJ.append(0)
else:
geneOrderJ.append(-1)
maskJ.append(1)
# test all translations
bestSpearman = 0
bestPearson = 0
for _ in range(0, len(markerGenes)):
maskedI = []
maskedJ = []
for k in range(0, len(maskI)):
if maskI[k] == 0 and maskJ[k] == 0:
maskedI.append(geneOrderI[k])
maskedJ.append(geneOrderJ[k])
r, _ = spearmanr(maskedI, maskedJ)
if abs(r) > bestSpearman:
bestSpearman = abs(r)
r, _ = pearsonr(maskedI, maskedJ)
if abs(r) > bestPearson:
bestPearson = abs(r)
geneOrderJ = geneOrderJ[1:] + [geneOrderJ[0]]
maskJ = maskJ[1:] + [maskJ[0]]
spearmanValues.append(bestSpearman)
pearsonValues.append(bestPearson)
print('Spearman: %.2f +/- %.2f: ' %
(mean(spearmanValues), std(spearmanValues)))
print('Pearson: %.2f +/- %.2f: ' %
(mean(pearsonValues), std(pearsonValues)))
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, 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()
