def test_goodFiles(tmpdir, bamFile):
d = tmpdir.mkdir('dir')
p = d.join('test.bam')
header = {'HD': {'VN': '1.0'}, 'SQ': [{'LN': 1000, 'SN': 'ref'}]}
outFile = pysam.AlignmentFile(str(p), "wb", header=header)
a = pysam.AlignedSegment()
a.query_name = "read1"
a.query_sequence = "AAAAATTTTT"
a.reference_id = 0
a.reference_start = 32
a.mapping_quality = 20
a.cigar = ((0, 10), )
#a.query_qualities = pysam.qualitystring_to_array("((((((((((")
outFile.write(a)
outFile.close()
pysam.index(str(p))
count = 0
for col in countbases.countBasesInFile(str(p)):
if count < 5:
assert col['+']['A'] == 1
assert col['+']['G'] + col['+']['T'] + col['+']['C'] == 0
assert col['n'] == 1
else:
assert col['+']['T'] == 1
assert col['+']['G'] + col['+']['A'] + col['+']['C'] == 0
assert col['n'] == 1
assert col['pos'] == count + 32
count += 1
bases = ['A', 'C', 'G', 'T']
strands = ['+', '-']
predictedStrandCounts = {
'+': {
'A': [0, 0, 0, 0, 2, 2, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'C': [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1],
'G': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0],
'T': [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0],
},
'-': {
'A': [0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'C': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'G': [1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'T': [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0]
}
}
n = [1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 1, 1, 1, 1]
#predictedCounts=[predictedStrandCounts['+'][base]+predictedStrandCounts['-'][base] for base in bases]
pos = range(28, 46)
ii = 0
for col in countbases.countBasesInFile(str(bamFile)):
for base in bases:
for strand in strands:
#print str(pos[count])+base + strand
assert col[strand][base] == predictedStrandCounts[strand][
base][ii]
assert col['pos'] == pos[ii]
assert col['n'] == n[ii]
ii += 1
def test_goodFiles(tmpdir,bamFile):
d = tmpdir.mkdir('dir')
p = d.join('test.bam')
header = { 'HD': {'VN': '1.0'}, 'SQ': [{'LN': 1000, 'SN': 'ref'}] }
outFile=pysam.AlignmentFile(str(p),"wb",header=header)
a = pysam.AlignedSegment()
a.query_name = "read1"
a.query_sequence="AAAAATTTTT"
a.reference_id = 0
a.reference_start = 32
a.mapping_quality = 20
a.cigar = ((0,10), )
#a.query_qualities = pysam.qualitystring_to_array("((((((((((")
outFile.write(a)
outFile.close()
pysam.index(str(p))
count=0
for col in countbases.countBasesInFile(str(p)):
if count<5:
assert col['+']['A']==1
assert col['+']['G']+col['+']['T']+col['+']['C']==0
assert col['n']==1
else:
assert col['+']['T']==1
assert col['+']['G']+col['+']['A']+col['+']['C']==0
assert col['n']==1
assert col['pos']==count+32
count+=1
bases=['A','C','G','T']
strands=['+','-']
predictedStrandCounts={'+':{
'A':[0,0,0,0,2,2,2,2,2,0,0,0,0,0,0,0,0,0],
'C':[0,0,0,0,0,0,0,0,0,1,1,1,1,1,0,0,0,1],
'G':[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0],
'T':[0,0,0,0,0,0,0,0,0,1,1,1,1,1,0,0,0,0],
},'-':{
'A':[0,0,0,0,1,1,1,1,1,0,0,0,0,0,0,0,0,0],
'C':[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],
'G':[1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0],
'T':[0,0,0,0,0,0,0,0,0,1,0,0,0,0,0,0,0,0]
}}
n= [1,1,1,1,3,3,3,3,3,3,2,2,2,2,1,1,1,1]
#predictedCounts=[predictedStrandCounts['+'][base]+predictedStrandCounts['-'][base] for base in bases]
pos=range(28,46)
ii=0
for col in countbases.countBasesInFile(str(bamFile)):
for base in bases:
for strand in strands:
#print str(pos[count])+base + strand
assert col[strand][base]==predictedStrandCounts[strand][base][ii]
assert col['pos']==pos[ii]
assert col['n']==n[ii]
ii+=1
def test_badFiles(tmpdir):
d = tmpdir.mkdir('dir')
p = d.join('test.txt')
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(d)))
#doesn't exist yet
with pytest.raises(IOError):
next(countbases.countBasesInFile(str(p)))
#incorrectly formatted file
p.write("test")
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(p)))
#make unreadable
os.chmod(str(p),os.stat(str(p)).st_mode & ~stat.S_IREAD)
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(p)))
def test_badFiles(tmpdir):
d = tmpdir.mkdir('dir')
p = d.join('test.txt')
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(d)))
#doesn't exist yet
with pytest.raises(IOError):
next(countbases.countBasesInFile(str(p)))
#incorrectly formatted file
p.write("test")
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(p)))
#make unreadable
os.chmod(str(p), os.stat(str(p)).st_mode & ~stat.S_IREAD)
with pytest.raises(ValueError):
next(countbases.countBasesInFile(str(p)))
def test_main(capsys,tmpdir,bamFile):
with pytest.raises(SystemExit):
countbases.main()
out, err=capsys.readouterr()
assert 'usage' in err
with pytest.raises(SystemExit):
countbases.main(['-h'])
out, err=capsys.readouterr()
assert 'usage' in out
countbases.main(['-v',str(bamFile)])
out, err=capsys.readouterr()
assert 'Arguments' in err
compare=countbases.countBasesInFile(str(bamFile))
for ii,jj in zip(out.split('\n')[1:],compare):
ii=ii.split(',')
assert ii[0]==jj['ref']
assert int(ii[1])==jj['pos']
assert int(ii[2])==jj['n']
assert int(ii[3])==jj['+']['A']+jj['-']['A']
assert int(ii[4])==jj['+']['C']+jj['-']['C']
assert int(ii[5])==jj['+']['G']+jj['-']['G']
assert int(ii[6])==jj['+']['T']+jj['-']['T']
countbases.main(['-s',str(bamFile)])
out, err=capsys.readouterr()
for ii,jj in zip(out.split('\n')[1:],compare):
ii=ii.split(',')
assert ii[0]==jj['ref']
assert int(ii[1])==jj['pos']
assert int(ii[2])==jj['n']
assert int(ii[3])==jj['+']['A']
assert int(ii[5])==jj['+']['C']
assert int(ii[7])==jj['+']['G']
assert int(ii[9])==jj['+']['T']
assert int(ii[4])==jj['-']['A']
assert int(ii[6])==jj['-']['C']
assert int(ii[8])==jj['-']['G']
assert int(ii[10])==jj['-']['T']
def test_main(capsys, tmpdir, bamFile):
with pytest.raises(SystemExit):
countbases.main()
out, err = capsys.readouterr()
assert 'usage' in err
with pytest.raises(SystemExit):
countbases.main(['-h'])
out, err = capsys.readouterr()
assert 'usage' in out
countbases.main(['-v', str(bamFile)])
out, err = capsys.readouterr()
assert 'Arguments' in err
compare = countbases.countBasesInFile(str(bamFile))
for ii, jj in zip(out.split('\n')[1:], compare):
ii = ii.split(',')
assert ii[0] == jj['ref']
assert int(ii[1]) == jj['pos']
assert int(ii[2]) == jj['n']
assert int(ii[3]) == jj['+']['A'] + jj['-']['A']
assert int(ii[4]) == jj['+']['C'] + jj['-']['C']
assert int(ii[5]) == jj['+']['G'] + jj['-']['G']
assert int(ii[6]) == jj['+']['T'] + jj['-']['T']
countbases.main(['-s', str(bamFile)])
out, err = capsys.readouterr()
for ii, jj in zip(out.split('\n')[1:], compare):
ii = ii.split(',')
assert ii[0] == jj['ref']
assert int(ii[1]) == jj['pos']
assert int(ii[2]) == jj['n']
assert int(ii[3]) == jj['+']['A']
assert int(ii[5]) == jj['+']['C']
assert int(ii[7]) == jj['+']['G']
assert int(ii[9]) == jj['+']['T']
assert int(ii[4]) == jj['-']['A']
assert int(ii[6]) == jj['-']['C']
assert int(ii[8]) == jj['-']['G']
assert int(ii[10]) == jj['-']['T']
