def getConsensusTaxForBlobs(self, taxrule, blast_order):
'''
- Based on taxrule ("A" or "B") and the blast_order (list in order in which blast files where specified)
it calculates the consensus taxonomy for each blob
- if taxrule == A:
- it puts all taxonomic groups in a dict with their summed scores as values
- if a taxonomic group occurs in hits of more than one BLAST file, the highest score is used
- if taxrule == B:
- taxonomic groups are put in the dict with their summed scores as values IF they come from the first BLAST file
- If there was no hit then take the taxonomic groups from the next one
- The highest scoring taxonomic group is selected as consensus taxonomy for each blob
'''
for contig_name in self.contigs:
dict_for_tax_merging = {}
for blast_lib in blast_order:
for tax, score in sorted(self.contigs[contig_name].tax[blast_lib].items(), key=lambda x: x[1], reverse=True):
# loops through tax/score with decreasing score
if taxrule == 'A':
if not tax in dict_for_tax_merging:
dict_for_tax_merging[tax] = score
else:
if score > dict_for_tax_merging[tax]:
dict_for_tax_merging[tax] = score
elif taxrule == 'B':
if blast_lib == blast_order[0]:
# First blast_lib
dict_for_tax_merging[tax] = score
else:
if len(dict_for_tax_merging) <= 1 and ('no-hit' in dict_for_tax_merging):
dict_for_tax_merging[tax] = score
tax = keyWithMaxVal(dict_for_tax_merging)
self.contigs[contig_name].tax['tax'] = {}
self.contigs[contig_name].tax['tax'][tax]=dict_for_tax_merging[tax]
self.blast_libs.append('tax')
def getConsensusTaxForBlobs(self, taxrule, blast_order):
'''
- Based on taxrule ("A" or "B") and the blast_order (list in order in which blast files where specified)
it calculates the consensus taxonomy for each blob
- if taxrule == A:
- it puts all taxonomic groups in a dict with their summed scores as values
- if a taxonomic group occurs in hits of more than one BLAST file, the highest score is used
- if taxrule == B:
- taxonomic groups are put in the dict with their summed scores as values IF they come from the first BLAST file
- If there was no hit then take the taxonomic groups from the next one
- The highest scoring taxonomic group is selected as consensus taxonomy for each blob
'''
for contig_name in self.contigs:
dict_for_tax_merging = {}
for blast_lib in blast_order:
for tax, score in sorted(
self.contigs[contig_name].tax[blast_lib].items(),
key=lambda x: x[1],
reverse=True):
# loops through tax/score with decreasing score
if taxrule == 'A':
if not tax in dict_for_tax_merging:
dict_for_tax_merging[tax] = score
else:
if score > dict_for_tax_merging[tax]:
dict_for_tax_merging[tax] = score
elif taxrule == 'B':
if blast_lib == blast_order[0]:
# First blast_lib
dict_for_tax_merging[tax] = score
else:
if len(dict_for_tax_merging) <= 1 and (
'no-hit' in dict_for_tax_merging):
dict_for_tax_merging[tax] = score
tax = keyWithMaxVal(dict_for_tax_merging)
self.contigs[contig_name].tax['tax'] = {}
self.contigs[contig_name].tax['tax'][tax] = dict_for_tax_merging[
tax]
self.blast_libs.append('tax')
def getStats(self):
'''
Calculates all different kind of stats for each taxonomic group based on each BLAST file and the consensus...
'''
self.stats['count'] = {}
self.stats['span'] = {}
self.stats['n50'] = {}
self.stats['lengths'] = {}
self.stats['gc'] = {}
self.stats['cov'] = {}
self.stats['total_count'] = 0
self.stats['total_span'] = 0
self.stats['total_n50'] = 0
self.stats['total_lengths'] = []
self.stats['total_cov'] = {}
self.stats['total_gc'] = {'raw': [], 'mean': 0.0, 'stdev': 0.0}
self.stats['cov_libs'] = []
for contig_name in self.contigs:
blob = self.contigs[contig_name]
self.stats['total_count'] += 1
self.stats['total_span'] += blob.length
self.stats['total_lengths'].append(blob.length)
self.stats['total_gc']['raw'].append(blob.gc)
for blast_lib in self.blast_libs:
bestTax = keyWithMaxVal(blob.tax[blast_lib])
if not blast_lib in self.stats['count']:
self.stats['count'][blast_lib] = {}
self.stats['span'][blast_lib] = {}
self.stats['lengths'][blast_lib] = {}
self.stats['gc'][blast_lib] = {}
self.stats['cov'][blast_lib] = {}
self.stats['count'][
blast_lib][bestTax] = self.stats['count'][blast_lib].get(
bestTax, 0) + 1
self.stats['span'][
blast_lib][bestTax] = self.stats['span'][blast_lib].get(
bestTax, 0) + blob.length
if not bestTax in self.stats['gc'][blast_lib]:
self.stats['gc'][blast_lib][bestTax] = {
'raw': [],
'mean': 0.0,
'stdev': 0.0
}
self.stats['lengths'][blast_lib][bestTax] = []
self.stats['gc'][blast_lib][bestTax]['raw'].append(blob.gc)
self.stats['lengths'][blast_lib][bestTax].append(blob.length)
for cov_lib, cov in blob.covs.items():
if not cov_lib in self.stats['cov'][blast_lib]:
self.stats['total_cov'][cov_lib] = {
'raw': [],
'mean': 0.0,
'stdev': 0.0
}
self.stats['cov'][blast_lib][cov_lib] = {}
if not bestTax in self.stats['cov'][blast_lib][cov_lib]:
self.stats['cov'][blast_lib][cov_lib][bestTax] = {
'raw': [],
'mean': 0.0,
'stdev': 0.0
}
self.stats['cov'][blast_lib][cov_lib][bestTax][
'raw'].append(cov)
for cov_lib, cov in blob.covs.items():
self.stats['total_cov'][cov_lib]['raw'].append(cov)
for blast_lib in self.blast_libs:
# calculate N50
for tax, list_of_lengths in self.stats['lengths'][blast_lib].items(
):
if not blast_lib in self.stats['n50']:
self.stats['n50'][blast_lib] = {}
self.stats['n50'][blast_lib][tax] = n50(list_of_lengths)
self.stats['total_n50'] = n50(self.stats['total_lengths'])
# calculate total gc mean/stdev
for tax in self.stats['gc'][blast_lib]:
self.stats['gc'][blast_lib][tax]['mean'] = "{0:.2f}".format(
numpy.mean(self.stats['gc'][blast_lib][tax]['raw']))
self.stats['gc'][blast_lib][tax]['stdev'] = "{0:.2f}".format(
numpy.std(self.stats['gc'][blast_lib][tax]['raw']))
# calculate total cov mean/stdev
for cov_lib in self.stats['cov'][blast_lib]:
self.stats['total_cov'][cov_lib]['mean'] = "{0:.2f}".format(
numpy.mean(self.stats['total_cov'][cov_lib]['raw']))
self.stats['total_cov'][cov_lib]['stdev'] = "{0:.2f}".format(
numpy.std(self.stats['total_cov'][cov_lib]['raw']))
# calculate tax-specific cov mean/stdev
for tax in self.stats['cov'][blast_lib][cov_lib]:
self.stats['cov'][blast_lib][cov_lib][tax][
'mean'] = "{0:.2f}".format(
numpy.mean(self.stats['cov'][blast_lib][cov_lib]
[tax]['raw']))
self.stats['cov'][blast_lib][cov_lib][tax][
'stdev'] = "{0:.2f}".format(
numpy.std(self.stats['cov'][blast_lib][cov_lib]
[tax]['raw']))
self.stats['total_gc']['mean'] = "{0:.2f}".format(
numpy.mean(self.stats['total_gc']['raw']))
self.stats['total_gc']['stdev'] = "{0:.2f}".format(
numpy.std(self.stats['total_gc']['raw']))
def getStats(self):
'''
Calculates all different kind of stats for each taxonomic group based on each BLAST file and the consensus...
'''
self.stats['count'] = {}
self.stats['span']= {}
self.stats['n50']= {}
self.stats['lengths']= {}
self.stats['gc']= {}
self.stats['cov'] = {}
self.stats['total_count'] = 0
self.stats['total_span'] = 0
self.stats['total_n50'] = 0
self.stats['total_lengths'] = []
self.stats['total_cov'] = {}
self.stats['total_gc'] = {'raw' : [], 'mean' : 0.0, 'stdev' : 0.0}
self.stats['cov_libs'] = []
for contig_name in self.contigs:
blob = self.contigs[contig_name]
self.stats['total_count'] += 1
self.stats['total_span'] += blob.length
self.stats['total_lengths'].append(blob.length)
self.stats['total_gc']['raw'].append(blob.gc)
for blast_lib in self.blast_libs:
bestTax = keyWithMaxVal(blob.tax[blast_lib])
if not blast_lib in self.stats['count']:
self.stats['count'][blast_lib] = {}
self.stats['span'][blast_lib] = {}
self.stats['lengths'][blast_lib] = {}
self.stats['gc'][blast_lib] = {}
self.stats['cov'][blast_lib] = {}
self.stats['count'][blast_lib][bestTax] = self.stats['count'][blast_lib].get(bestTax, 0) + 1
self.stats['span'][blast_lib][bestTax] = self.stats['span'][blast_lib].get(bestTax, 0) + blob.length
if not bestTax in self.stats['gc'][blast_lib]:
self.stats['gc'][blast_lib][bestTax] = {'raw' : [], 'mean' : 0.0, 'stdev' : 0.0}
self.stats['lengths'][blast_lib][bestTax] = []
self.stats['gc'][blast_lib][bestTax]['raw'].append(blob.gc)
self.stats['lengths'][blast_lib][bestTax].append(blob.length)
for cov_lib, cov in blob.covs.items():
if not cov_lib in self.stats['cov'][blast_lib]:
self.stats['total_cov'][cov_lib] = {'raw' : [], 'mean' : 0.0, 'stdev' : 0.0}
self.stats['cov'][blast_lib][cov_lib]={}
if not bestTax in self.stats['cov'][blast_lib][cov_lib]:
self.stats['cov'][blast_lib][cov_lib][bestTax] = {'raw' : [], 'mean' : 0.0, 'stdev' : 0.0}
self.stats['cov'][blast_lib][cov_lib][bestTax]['raw'].append(cov)
for cov_lib, cov in blob.covs.items():
self.stats['total_cov'][cov_lib]['raw'].append(cov)
for blast_lib in self.blast_libs:
# calculate N50
for tax, list_of_lengths in self.stats['lengths'][blast_lib].items():
if not blast_lib in self.stats['n50']:
self.stats['n50'][blast_lib] = {}
self.stats['n50'][blast_lib][tax] = n50(list_of_lengths)
self.stats['total_n50'] = n50(self.stats['total_lengths'])
# calculate total gc mean/stdev
for tax in self.stats['gc'][blast_lib]:
self.stats['gc'][blast_lib][tax]['mean'] = "{0:.2f}".format(numpy.mean(self.stats['gc'][blast_lib][tax]['raw']))
self.stats['gc'][blast_lib][tax]['stdev'] = "{0:.2f}".format(numpy.std(self.stats['gc'][blast_lib][tax]['raw']))
# calculate total cov mean/stdev
for cov_lib in self.stats['cov'][blast_lib]:
self.stats['total_cov'][cov_lib]['mean'] = "{0:.2f}".format(numpy.mean(self.stats['total_cov'][cov_lib]['raw']))
self.stats['total_cov'][cov_lib]['stdev'] = "{0:.2f}".format(numpy.std(self.stats['total_cov'][cov_lib]['raw']))
# calculate tax-specific cov mean/stdev
for tax in self.stats['cov'][blast_lib][cov_lib]:
self.stats['cov'][blast_lib][cov_lib][tax]['mean'] = "{0:.2f}".format(numpy.mean(self.stats['cov'][blast_lib][cov_lib][tax]['raw']))
self.stats['cov'][blast_lib][cov_lib][tax]['stdev'] = "{0:.2f}".format(numpy.std(self.stats['cov'][blast_lib][cov_lib][tax]['raw']))
self.stats['total_gc']['mean'] = "{0:.2f}".format(numpy.mean(self.stats['total_gc']['raw']))
self.stats['total_gc']['stdev'] = "{0:.2f}".format(numpy.std(self.stats['total_gc']['raw']))