def run(self, outputFile):
img = IMG()
print 'Identifying all IMG prokaryotic genomes with valid data.'
metadata = img.genomeMetadata()
genomeIds = img.genomeIdsByTaxonomy('prokaryotes', metadata)
genomeMissingData = img.genomesWithMissingData(genomeIds)
genomeIds -= genomeMissingData
print ' Identified %d valid genomes.' % (len(genomeIds))
print 'Calculating gene copy number for each genome.'
countTable = img.geneCountTable(genomeIds)
counts = []
for _, count in countTable['pfam00318'].iteritems():
counts.append(count)
print len(genomeIds)
print len(counts)
print mean(counts)
fout = open(outputFile, 'w')
fout.write(str(countTable))
fout.close()
print 'Gene count dictionary to: ' + outputFile
def run(self, outputFile):
img = IMG()
print('Identifying all IMG prokaryotic genomes with valid data.')
metadata = img.genomeMetadata()
genomeIds = img.genomeIdsByTaxonomy('prokaryotes', metadata)
genomeMissingData = img.genomesWithMissingData(genomeIds)
genomeIds -= genomeMissingData
print(' Identified %d valid genomes.' % (len(genomeIds)))
print('Calculating gene copy number for each genome.')
countTable = img.geneCountTable(genomeIds)
counts = []
for _, count in countTable['pfam00318'].iteritems():
counts.append(count)
print(len(genomeIds))
print(len(counts))
print(mean(counts))
fout = open(outputFile, 'w')
fout.write(str(countTable))
fout.close()
print('Gene count dictionary to: ' + outputFile)
