def compute_library_bias(isnvs, inBam, inConsFasta) :
''' For each variant, compute read counts in each library and p-value for
library bias; append them to string for each variant.
Format is allele:totalF:totalR:1stLibFCount:1stLibRCount:2ndLibFCount:...:p-val.
Library counts are in alphabetical order of library IDs.
Note: Total was computed by vphaser, library counts by samtools mpileup,
so total might not be sum of library counts.
'''
alleleCol = 7 # First column of output with allele counts
samtoolsTool = SamtoolsTool()
rgs_by_lib = sorted((rg['LB'],rg['ID'])
for rg in samtoolsTool.getReadGroups(inBam).values())
rgs_by_lib = itertools.groupby(rgs_by_lib, lambda x: x[0])
libBams = []
header_sam = util.file.mkstempfname('.sam')
samtoolsTool.dumpHeader(inBam, header_sam)
for lib,rgs in rgs_by_lib:
rgs = list(id for lb,id in rgs)
# Create libBam containing all the readgroups in rgs.
# In samtools 1.1, this can be done by including -r multiple times on
# a single command line, but that doesn't work in 0.1.19, so instead
# extract readgroups one by one and then concatenate.
rgBams = []
for id in rgs :
rgBam = util.file.mkstempfname('.bam')
samtoolsTool.view(['-b', '-r', id], inBam, rgBam)
samtoolsTool.index(rgBam)
if samtoolsTool.count(rgBam) > 0:
rgBams.append(rgBam)
else:
# most samtools functions don't like empty input bams, so skip them
os.unlink(rgBam)
if rgBams:
if len(rgBams) > 1:
libBam = util.file.mkstempfname('.bam')
samtoolsTool.merge(rgBams, libBam, ['-f', '-1', '-h', header_sam])
for bam in rgBams :
os.unlink(bam)
else:
# samtools merge cannot deal with only one (or zero) input bams
libBam = rgBams[0]
samtoolsTool.index(libBam)
n_reads = samtoolsTool.count(libBam)
log.debug("LB:%s has %s reads in %s read groups (%s)",
lib, n_reads, len(rgs), ', '.join(rgs))
libBams.append(libBam)
for row in isnvs :
consensusAllele = row[3]
pos = int(row[1]) if consensusAllele != 'i' else int(row[1]) - 1
chrom = row[0]
libCounts = [get_mpileup_allele_counts(libBam, chrom, pos, inConsFasta)
for libBam in libBams]
numAlleles = len(row) - alleleCol
countsMatrix = [[0] * numAlleles for lib in libBams]
libCountsByAllele = []
for alleleInd in range(numAlleles) :
allele = row[alleleCol + alleleInd].split(':')[0]
libCountsByAllele.append([])
for libAlleleCounts, countsRow in zip(libCounts, countsMatrix) :
f, r = libAlleleCounts.get(allele, [0, 0])
libCountsByAllele[-1].append([f, r])
countsRow[alleleInd] += f + r
for alleleInd in range(numAlleles) :
contingencyTable = [
[ countsRow[alleleInd] for countsRow in countsMatrix],
[sum(countsRow) - countsRow[alleleInd] for countsRow in countsMatrix]]
rowSums = map(sum, contingencyTable)
dofs = len(libCounts) - 1
if dofs < 1 :
pval = 1.0
elif min(rowSums) ** dofs / dofs < 10000 :
# At this cutoff, fisher_exact should take <~ 0.1 sec
pval = fisher_exact(contingencyTable)
else :
pval = chi2_contingency(contingencyTable)
row[alleleCol + alleleInd] = str(AlleleFieldParser(None,
*(row[alleleCol + alleleInd].split(':') +
[pval, libCountsByAllele[alleleInd]])))
yield row
for bam in libBams:
os.unlink(bam)
os.unlink(header_sam)
