def printTable(assembliesList, caption, options):
print '''
\\rowcolors{1}{tableShade}{white}
\\begin{FPtable}
\caption[Contig path statistics.]{Contig path statistics. %s}
\\tiny
\\centering
\\begin{tabular}{| r | p{.75in} | p{.75in} | p{.4in} | p{.4in} | p{.5in} | p{.5in} || c |}
\\hline
ID & Intra chromosomal joins & Inter chromosomal joins & Insertions & Deletions & Insertion and deletion & Insertion at ends & \(\sum\) errors \\\\
\\hline
\\hline''' % (caption) # hom/het sw & scf & ctgE+ctgN
i = 0
for row in assembliesList:
i += 1
if options.showAssemblyNumbers:
s = '%s.%s' % (lgn.idMap[row.ID[0]], row.ID[1:])
else:
s = '%s' % (lgn.idMap[row.ID[0]])
sys.stdout.write('%s' % s)
# sys.stdout.write( ' & %s & %s' % ( lgn.prettyNumber(row.valuesDict['totalHomoToHeteroSwitches']),
# lgn.prettyNumber( row.valuesDict['totalScaffoldGaps'] +
# row.valuesDict['totalBleedingHeartScaffoldGaps'] ) ))
# sys.stdout.write( ' & %s' % ( lgn.prettyNumber( row.valuesDict['totalContigEnds'] +
# row.valuesDict['totalContigEndsWithNs'] )))
#sys.stdout.write( ' & %.4f' % ( row.valuesDict['errorsPerContig']))
#sys.stdout.write( ' & %.2e' % ( row.valuesDict['errorsPerMappedBase']))
for v in [
'totalErrorsHaplotypeToHaplotypeSameChromosome',
'totalErrorsHaplotypeToHaplotypeDifferentChromosome',
'totalErrorsHaplotypeToInsertion',
'totalErrorsHaplotypeToDeletion',
'totalErrorsHaplotypeToInsertionAndDeletion',
'totalErrorsContigEndsWithInsert'
]:
sys.stdout.write(' & %s' % (lgn.prettyNumber(row.valuesDict[v])))
#sys.stdout.write( ' & %s' % ( lgn.prettyNumber( row.valuesDict['totalErrorsNonSpecific'])))
sys.stdout.write(' & %s \\\\\n' % lgn.prettyNumber(row.totalErrors))
if not i % options.mod and i != len(assembliesList):
print '\\hline'
print '''\\hline
def printLine( a, kind, options ):
if options.showAssemblyNumbers:
s = '%s.%s' % (lgn.idMap[a.ID[0]], a.ID[1:])
else:
s = '%s' % (lgn.idMap[a.ID[0]])
sys.stdout.write( '%s' % s )
if kind == 'hom':
for k in [ 'totalCallsInHomozygous',
'totalCorrectInHomozygous', 'totalErrorsInHomozygous' ]:
sys.stdout.write( ' & %s -- %s' % ( lgn.prettyNumber( a.subStatsLower[ k ]), lgn.prettyNumber( a.subStatsUpper[ k ])))
sys.stdout.write( ' \\\\\n' )
elif kind == 'het':
for k in [ 'totalCallsInHeterozygous',
'totalCorrectInHeterozygous', 'totalErrorsInHeterozygous' ]:
sys.stdout.write( ' & %s -- %s' % ( lgn.prettyNumber( a.subStatsLower[ k ]), lgn.prettyNumber( a.subStatsUpper[ k ])))
sys.stdout.write( ' \\\\\n' )
elif kind == 'indel':
for k in [ 'totalCallsInOneHaplotypeOnly',
'totalCorrectInOneHaplotypeOnly', 'totalErrorsInOneHaplotypeOnly' ]:
sys.stdout.write( ' & %s -- %s' % ( lgn.prettyNumber( a.subStatsLower[ k ]), lgn.prettyNumber( a.subStatsUpper[ k ])))
sys.stdout.write( ' \\\\\n' )
def printLine(a, kind, options):
if options.showAssemblyNumbers:
s = '%s.%s' % (lgn.idMap[a.ID[0]], a.ID[1:])
else:
s = '%s' % (lgn.idMap[a.ID[0]])
sys.stdout.write('%s' % s)
if kind == 'hom':
for k in [
'totalCallsInHomozygous', 'totalCorrectInHomozygous',
'totalErrorsInHomozygous'
]:
sys.stdout.write(' & %s -- %s' % (lgn.prettyNumber(
a.subStatsLower[k]), lgn.prettyNumber(a.subStatsUpper[k])))
sys.stdout.write(' \\\\\n')
elif kind == 'het':
for k in [
'totalCallsInHeterozygous', 'totalCorrectInHeterozygous',
'totalErrorsInHeterozygous'
]:
sys.stdout.write(' & %s -- %s' % (lgn.prettyNumber(
a.subStatsLower[k]), lgn.prettyNumber(a.subStatsUpper[k])))
sys.stdout.write(' \\\\\n')
elif kind == 'indel':
for k in [
'totalCallsInOneHaplotypeOnly',
'totalCorrectInOneHaplotypeOnly',
'totalErrorsInOneHaplotypeOnly'
]:
sys.stdout.write(' & %s -- %s' % (lgn.prettyNumber(
a.subStatsLower[k]), lgn.prettyNumber(a.subStatsUpper[k])))
sys.stdout.write(' \\\\\n')
def printTable( assembliesList, caption, options ):
print '''
\\rowcolors{1}{tableShade}{white}
\\begin{FPtable}
\caption[Contig path statistics.]{Contig path statistics. %s}
\\tiny
\\centering
\\begin{tabular}{| r | p{.75in} | p{.75in} | p{.4in} | p{.4in} | p{.5in} | p{.5in} || c |}
\\hline
ID & Intra chromosomal joins & Inter chromosomal joins & Insertions & Deletions & Insertion and deletion & Insertion at ends & \(\sum\) errors \\\\
\\hline
\\hline''' % ( caption ) # hom/het sw & scf & ctgE+ctgN
i = 0
for row in assembliesList:
i += 1
if options.showAssemblyNumbers:
s = '%s.%s' % (lgn.idMap[row.ID[0]], row.ID[1:])
else:
s = '%s' % (lgn.idMap[row.ID[0]])
sys.stdout.write( '%s' % s )
# sys.stdout.write( ' & %s & %s' % ( lgn.prettyNumber(row.valuesDict['totalHomoToHeteroSwitches']),
# lgn.prettyNumber( row.valuesDict['totalScaffoldGaps'] +
# row.valuesDict['totalBleedingHeartScaffoldGaps'] ) ))
# sys.stdout.write( ' & %s' % ( lgn.prettyNumber( row.valuesDict['totalContigEnds'] +
# row.valuesDict['totalContigEndsWithNs'] )))
#sys.stdout.write( ' & %.4f' % ( row.valuesDict['errorsPerContig']))
#sys.stdout.write( ' & %.2e' % ( row.valuesDict['errorsPerMappedBase']))
for v in [ 'totalErrorsHaplotypeToHaplotypeSameChromosome',
'totalErrorsHaplotypeToHaplotypeDifferentChromosome',
'totalErrorsHaplotypeToInsertion',
'totalErrorsHaplotypeToDeletion',
'totalErrorsHaplotypeToInsertionAndDeletion',
'totalErrorsContigEndsWithInsert' ]:
sys.stdout.write( ' & %s' % ( lgn.prettyNumber( row.valuesDict[v] )))
#sys.stdout.write( ' & %s' % ( lgn.prettyNumber( row.valuesDict['totalErrorsNonSpecific'])))
sys.stdout.write( ' & %s \\\\\n' % lgn.prettyNumber( row.totalErrors ))
if not i % options.mod and i != len( assembliesList ):
print '\\hline'
print '''\\hline
def isMaxFormat(n, m):
if n == m:
return '\\textbf{ %s }' % lgn.prettyNumber(n)
else:
return '%s' % lgn.prettyNumber(n)
def isMaxFormat( n, m ):
if n == m:
return '\\textbf{ %s }' % lgn.prettyNumber( n )
else:
return '%s' % lgn.prettyNumber( n )
def outputDict( assembliesDict, options ):
sortOrder = sorted( assembliesDict, key = lambda x: int(x[1:]) ) # number
sortOrder = sorted( sortOrder, key = lambda x: assembliesDict[x].id[0] ) # letter
fileOrder = []
if not options.noContigs:
fileOrder += ['contigsOverlapGene', 'contigsOverlap' ]
# if options.scaffolds:
# fileOrder += ['scaffoldsOverlapGene', 'scaffoldsOverlap']
annotOrderGenes = ['transcripts'] # 'cds'
annotOrder = ['cds', 'utr', 'nxe+nge', 'repeat'] # 'island'
fileNameMap = {'contigsOverlapGene':'COG', 'contigsOverlap':'CO'}
annotNameMap = {'transcripts':'xcript', 'cds':'cds', 'utr':'utr',
'nxe+nge':'nxe+nge', 'repeat':'repeat'}
# print the header
sys.stdout.write('#ID')
i = -1
for f in fileOrder:
i += 1
if f.endswith('OverlapGene'):
order = annotOrderGenes
else:
order = annotOrder
for a in order:
if options.bases:
if options.aveHaps:
totalStr = lgn.prettyNumber( assembliesDict[sortOrder[0]].valuesDict[f][a][1].baseLength +
assembliesDict[sortOrder[0]].valuesDict[f][a][2].baseLength )
else:
totalStr = '%s, %s' % ( lgn.prettyNumber(assembliesDict[sortOrder[0]].valuesDict[f][a][1].baseLength),
lgn.prettyNumber(assembliesDict[sortOrder[0]].valuesDict[f][a][2].baseLength ))
else:
if options.aveHaps:
totalStr = lgn.prettyNumber( assembliesDict[sortOrder[0]].valuesDict[f][a][1].samples +
assembliesDict[sortOrder[0]].valuesDict[f][a][2].samples )
else:
totalStr = '%s, %s' % ( lgn.prettyNumber(assembliesDict[sortOrder[0]].valuesDict[f][a][1].samples),
lgn.prettyNumber(assembliesDict[sortOrder[0]].valuesDict[f][a][2].samples) )
sys.stdout.write('\t%s-%s (%s)' % (fileNameMap[f], annotNameMap[a], totalStr))
sys.stdout.write('\n')
for assembly in sortOrder:
if options.hideAssemblyNumbers:
nameStr = '%s' % (lgn.idMap[assembliesDict[assembly].id[0]])
else:
nameStr = '%s.%s' % (lgn.idMap[assembliesDict[assembly].id[0]], assembliesDict[assembly].id[1:])
sys.stdout.write('%s' % nameStr)
for filetype in fileOrder:
if filetype.endswith('OverlapGene'):
order = annotOrderGenes
else:
order = annotOrder
for annot in order:
aveHap = IntervalsTag()
for hap in assembliesDict[assembly].valuesDict[filetype][annot]:
it = assembliesDict[assembly].valuesDict[filetype][annot][hap]
if options.bases:
fracStr = '%.2f' % ( float( it.totalComplete ) / it.baseLength )
numer = it.complete
denom = it.samples
else:
fracStr = '%.2f' % ( float( it.complete ) / it.samples )
numer = it.complete
denom = it.samples
if fracStr == '1.00' and ( numer != denom ):
fracStr = '0.99'
if not options.aveHaps:
sys.stdout.write('\thapA%d %s'
% (hap, fracStr))
else:
aveHap.complete += it.complete
aveHap.samples += it.samples
aveHap.totalComplete += it.totalComplete
aveHap.baseLength += it.baseLength
if options.aveHaps:
if options.bases:
fracStr = '%.2f' % ( float( aveHap.totalComplete ) / aveHap.baseLength )
numer = aveHap.totalComplete
denom = aveHap.baseLength
else:
fracStr = '%.2f' % ( float( aveHap.complete ) / aveHap.samples )
numer = aveHap.complete
denom = aveHap.samples
if fracStr == '1.00' and ( numer != denom ):
fracStr = '0.99'
sys.stdout.write('\t%s' % fracStr)
sys.stdout.write('\n')
def outputDict(assembliesDict, options):
sortOrder = sorted(assembliesDict, key=lambda x: int(x[1:])) # number
sortOrder = sorted(sortOrder,
key=lambda x: assembliesDict[x].id[0]) # letter
fileOrder = []
if not options.noContigs:
fileOrder += ['contigsOverlapGene', 'contigsOverlap']
# if options.scaffolds:
# fileOrder += ['scaffoldsOverlapGene', 'scaffoldsOverlap']
annotOrderGenes = ['transcripts'] # 'cds'
annotOrder = ['cds', 'utr', 'nxe+nge', 'repeat'] # 'island'
fileNameMap = {'contigsOverlapGene': 'COG', 'contigsOverlap': 'CO'}
annotNameMap = {
'transcripts': 'xcript',
'cds': 'cds',
'utr': 'utr',
'nxe+nge': 'nxe+nge',
'repeat': 'repeat'
}
# print the header
sys.stdout.write('#ID')
i = -1
for f in fileOrder:
i += 1
if f.endswith('OverlapGene'):
order = annotOrderGenes
else:
order = annotOrder
for a in order:
if options.bases:
if options.aveHaps:
totalStr = lgn.prettyNumber(assembliesDict[
sortOrder[0]].valuesDict[f][a][1].baseLength +
assembliesDict[sortOrder[0]].
valuesDict[f][a][2].baseLength)
else:
totalStr = '%s, %s' % (lgn.prettyNumber(assembliesDict[
sortOrder[0]].valuesDict[f][a][1].baseLength),
lgn.prettyNumber(
assembliesDict[sortOrder[0]].
valuesDict[f][a][2].baseLength))
else:
if options.aveHaps:
totalStr = lgn.prettyNumber(assembliesDict[
sortOrder[0]].valuesDict[f][a][1].samples +
assembliesDict[sortOrder[0]].
valuesDict[f][a][2].samples)
else:
totalStr = '%s, %s' % (lgn.prettyNumber(assembliesDict[
sortOrder[0]].valuesDict[f][a][1].samples),
lgn.prettyNumber(
assembliesDict[sortOrder[0]].
valuesDict[f][a][2].samples))
sys.stdout.write('\t%s-%s (%s)' %
(fileNameMap[f], annotNameMap[a], totalStr))
sys.stdout.write('\n')
for assembly in sortOrder:
if options.hideAssemblyNumbers:
nameStr = '%s' % (lgn.idMap[assembliesDict[assembly].id[0]])
else:
nameStr = '%s.%s' % (lgn.idMap[assembliesDict[assembly].id[0]],
assembliesDict[assembly].id[1:])
sys.stdout.write('%s' % nameStr)
for filetype in fileOrder:
if filetype.endswith('OverlapGene'):
order = annotOrderGenes
else:
order = annotOrder
for annot in order:
aveHap = IntervalsTag()
for hap in assembliesDict[assembly].valuesDict[filetype][
annot]:
it = assembliesDict[assembly].valuesDict[filetype][annot][
hap]
if options.bases:
fracStr = '%.2f' % (float(it.totalComplete) /
it.baseLength)
numer = it.complete
denom = it.samples
else:
fracStr = '%.2f' % (float(it.complete) / it.samples)
numer = it.complete
denom = it.samples
if fracStr == '1.00' and (numer != denom):
fracStr = '0.99'
if not options.aveHaps:
sys.stdout.write('\thapA%d %s' % (hap, fracStr))
else:
aveHap.complete += it.complete
aveHap.samples += it.samples
aveHap.totalComplete += it.totalComplete
aveHap.baseLength += it.baseLength
if options.aveHaps:
if options.bases:
fracStr = '%.2f' % (float(aveHap.totalComplete) /
aveHap.baseLength)
numer = aveHap.totalComplete
denom = aveHap.baseLength
else:
fracStr = '%.2f' % (float(aveHap.complete) /
aveHap.samples)
numer = aveHap.complete
denom = aveHap.samples
if fracStr == '1.00' and (numer != denom):
fracStr = '0.99'
sys.stdout.write('\t%s' % fracStr)
sys.stdout.write('\n')
