def setUp(self,**kwargs):
TestBase.setUp(self)
dnaseq = testutil.datafile('dnaseq.fasta')
tryannot = testutil.tempdatafile('tryannot')
db = seqdb.BlastDB(dnaseq)
try:
db.__doc__ = 'little dna'
worldbase.Bio.Test.dna = db
annoDB = seqdb.AnnotationDB({1:('seq1',5,10,'fred'),
2:('seq1',-60,-50,'bob'),
3:('seq2',-20,-10,'mary')},
db,
sliceAttrDict=dict(id=0, start=1, stop=2,
name=3))
annoDB.__doc__ = 'trivial annotation'
worldbase.Bio.Test.annoDB = annoDB
nlmsa = cnestedlist.NLMSA(tryannot,'w',pairwiseMode=True,
bidirectional=False)
try:
for annID in annoDB:
nlmsa.addAnnotation(annoDB[annID])
nlmsa.build(verbose=False)
nlmsa.__doc__ = 'trivial map'
worldbase.Bio.Test.map = nlmsa
worldbaseSchema.Bio.Test.map = metabase.ManyToManyRelation(db,
annoDB,bindAttrs=('exons',))
worldbase.commit()
worldbase.clear_cache()
finally:
nlmsa.close()
finally:
db.close()
def test_run_gunzip(self):
'test uncompress_file gunzip'
zipfile = testutil.datafile('test.gz')
outfile = testutil.tempdatafile('test3.out')
uncompress_file(zipfile, newpath=outfile)
h = testutil.get_file_md5(outfile)
self.assertEqual(h.hexdigest(), '1db5a21a01ba465fd26c3203d6589b0e')
def test_do_gunzip(self):
'test do_gunzip'
zipfile = testutil.datafile('test.gz')
outfile = testutil.tempdatafile('test4.out')
do_gunzip(zipfile, outfile)
h = testutil.get_file_md5(outfile)
self.assertEqual(h.hexdigest(), '1db5a21a01ba465fd26c3203d6589b0e')
def test_run_unzip(self):
'test uncompress_file unzip'
zipfile = testutil.datafile('test.zip')
outfile = testutil.tempdatafile('test.out')
uncompress_file(zipfile, newpath=outfile, singleFile=True)
h = testutil.get_file_md5(outfile)
self.assertEqual(h.hexdigest(), '12ada4c51ccb4c7277c16f1a3c000b90')
def test_do_unzip(self):
'test do_unzip'
zipfile = testutil.datafile('test.zip')
outfile = testutil.tempdatafile('test2.out')
do_unzip(zipfile, outfile, singleFile=True)
h = testutil.get_file_md5(outfile)
self.assertEqual(h.hexdigest(), '12ada4c51ccb4c7277c16f1a3c000b90')
def test_do_gunzip(self):
"test do_gunzip"
zipfile = testutil.datafile("test.gz")
outfile = testutil.tempdatafile("test4.out")
do_gunzip(zipfile, outfile)
h = testutil.get_file_md5(outfile)
self.assertEqual(h.hexdigest(), "1db5a21a01ba465fd26c3203d6589b0e")
def setUp(self, **kwargs):
TestBase.setUp(self)
dnaseq = testutil.datafile('dnaseq.fasta')
tryannot = testutil.tempdatafile('tryannot')
db = seqdb.BlastDB(dnaseq)
try:
db.__doc__ = 'little dna'
self.pygrData.Bio.Test.dna = db
annoDB = seqdb.AnnotationDB({1: ('seq1', 5, 10, 'fred'),
2: ('seq1', -60, -50, 'bob'),
3: ('seq2', -20, -10, 'mary')},
db,
sliceAttrDict=dict(id=0, start=1, stop=2,
name=3))
annoDB.__doc__ = 'trivial annotation'
self.pygrData.Bio.Test.annoDB = annoDB
nlmsa = cnestedlist.NLMSA(tryannot, 'w', pairwiseMode=True,
bidirectional=False)
try:
for annID in annoDB:
nlmsa.addAnnotation(annoDB[annID])
nlmsa.build()
nlmsa.__doc__ = 'trivial map'
self.pygrData.Bio.Test.map = nlmsa
self.schema.Bio.Test.map = metabase.ManyToManyRelation(db,
annoDB, bindAttrs=('exons', ))
self.metabase.commit()
self.metabase.clear_cache()
finally:
nlmsa.close()
finally:
db.close()
def setUp(self, **kwargs):
TestBase.setUp(self)
dnaseq = testutil.datafile("dnaseq.fasta")
tryannot = testutil.tempdatafile("tryannot")
db = seqdb.BlastDB(dnaseq)
try:
db.__doc__ = "little dna"
self.pygrData.Bio.Test.dna = db
annoDB = seqdb.AnnotationDB(
{1: ("seq1", 5, 10, "fred"), 2: ("seq1", -60, -50, "bob"), 3: ("seq2", -20, -10, "mary")},
db,
sliceAttrDict=dict(id=0, start=1, stop=2, name=3),
)
annoDB.__doc__ = "trivial annotation"
self.pygrData.Bio.Test.annoDB = annoDB
nlmsa = cnestedlist.NLMSA(tryannot, "w", pairwiseMode=True, bidirectional=False)
try:
for annID in annoDB:
nlmsa.addAnnotation(annoDB[annID])
nlmsa.build()
nlmsa.__doc__ = "trivial map"
self.pygrData.Bio.Test.map = nlmsa
self.schema.Bio.Test.map = metabase.ManyToManyRelation(db, annoDB, bindAttrs=("exons",))
self.metabase.commit()
self.metabase.clear_cache()
finally:
nlmsa.close()
finally:
db.close()
def test_empty2(self):
"NLMSA Empty 2"
blasthits = testutil.tempdatafile('blasthits2')
msa = cnestedlist.NLMSA(blasthits, mode='w', pairwiseMode=True)
try:
msa.build()
raise AssertionError('failed to trap empty alignment!')
except nlmsa_utils.EmptyAlignmentError:
pass
def test_empty(self):
"NLMSA Empty"
blasthits = testutil.tempdatafile("blasthits")
msa = cnestedlist.NLMSA(blasthits, "memory", pairwiseMode=True)
try:
msa.build()
raise AssertionError("failed to trap empty alignment!")
except nlmsa_utils.EmptyAlignmentError:
pass
def test_headerfile_write_fail(self):
subdb = SequenceFileDB(self.dbfile)
try:
del subdb.filepath # remove 'filepath' attribute for test
db = PrefixUnionDict({'prefix': subdb})
assert len(db) == 2
assert 'prefix.seq1' in db
output = testutil.tempdatafile('prefixUnionDict-write-fail.txt')
try:
db.writeHeaderFile(output)
except AttributeError:
pass
finally:
subdb.close() # closes both db and subdb
def test_headerfile_write_fail(self):
subdb = SequenceFileDB(self.dbfile)
try:
del subdb.filepath # remove 'filepath' attribute for test
db = PrefixUnionDict({'prefix': subdb})
assert len(db) == 2
assert 'prefix.seq1' in db
output = testutil.tempdatafile('prefixUnionDict-write-fail.txt')
try:
db.writeHeaderFile(output)
except AttributeError:
pass
finally:
subdb.close() # closes both db and subdb
def all_vs_all_blast_save():
"""
Creates the blast files used during testing.
Must be called before running the tests
"""
tempdir = testutil.TempDir("blast-test")
testutil.change_pygrdatapath(tempdir.path)
sp_hbb1 = testutil.datafile("sp_hbb1")
all_vs_all = testutil.tempdatafile("all_vs_all")
sp = seqdb.BlastDB(sp_hbb1)
msa = cnestedlist.NLMSA(all_vs_all, mode="w", pairwiseMode=True, bidirectional=False)
# get strong homologs, save alignment in msa for every sequence
reader = islice(sp.iteritems(), None)
for id, s in reader:
sp.blast(s, msa, expmax=1e-10, verbose=False)
# done constructing the alignment, so build the alignment db indexes
msa.build(saveSeqDict=True)
db = msa.seqDict.dicts.keys()[0]
working, result = {}, {}
for k in db.values():
edges = msa[k].edges(minAlignSize=12, pIdentityMin=0.5)
for t in edges:
assert len(t[0]) >= 12
tmpdict = dict(
map(lambda x: (x, None), [(str(t[0]), str(t[1]), t[2].pIdentity(trapOverflow=False)) for t in edges])
)
result[repr(k)] = tmpdict.keys()
result[repr(k)].sort()
# save it into worldbase
data = testutil.TestData()
data.__doc__ = "sp_allvall"
data.result = result
worldbase.Bio.Blast = data
worldbase.commit()
def test_headerfile_write(self):
header = testutil.datafile('prefixUnionDict-2.txt')
db = PrefixUnionDict(filename=header)
try:
assert len(db) == 4
assert 'a.seq1' in db
assert 'b.seq1' in db
output = testutil.tempdatafile('prefixUnionDict-write.txt')
db.writeHeaderFile(output)
finally:
close_pud_dicts(db)
db2 = PrefixUnionDict(filename=output,
trypath=[os.path.dirname(header)])
try:
assert len(db2) == 4
assert 'a.seq1' in db2
assert 'b.seq1' in db2
finally:
close_pud_dicts(db2)
def test_headerfile_write(self):
header = testutil.datafile('prefixUnionDict-2.txt')
db = PrefixUnionDict(filename=header)
try:
assert len(db) == 4
assert 'a.seq1' in db
assert 'b.seq1' in db
output = testutil.tempdatafile('prefixUnionDict-write.txt')
db.writeHeaderFile(output)
finally:
close_pud_dicts(db)
db2 = PrefixUnionDict(filename=output,
trypath=[os.path.dirname(header)])
try:
assert len(db2) == 4
assert 'a.seq1' in db2
assert 'b.seq1' in db2
finally:
close_pud_dicts(db2)
def test_build(self):
"NLMSA build"
testnlmsa = testutil.tempdatafile('testnlmsa')
msa = cnestedlist.NLMSA(testnlmsa, mode='w', pairwiseMode=True,
bidirectional=False)