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 populate_swissprot():
"Populate the current worldbase with swissprot data"
# build BlastDB out of the sequences
sp_hbb1 = testutil.datafile('sp_hbb1')
sp = seqdb.BlastDB(sp_hbb1)
sp.__doc__ = 'little swissprot'
worldbase.Bio.Seq.Swissprot.sp42 = sp
# also store a fragment
hbb = sp['HBB1_TORMA']
ival = hbb[10:35]
ival.__doc__ = 'fragment'
worldbase.Bio.Seq.frag = ival
# build a mapping to itself
m = mapping.Mapping(sourceDB=sp, targetDB=sp)
trypsin = sp['PRCA_ANAVA']
m[hbb] = trypsin
m.__doc__ = 'map sp to itself'
worldbase.Bio.Seq.spmap = m
# create an annotation database and bind as exons attribute
worldbase.schema.Bio.Seq.spmap = metabase.OneToManyRelation(
sp, sp, bindAttrs=('buddy', ))
annoDB = seqdb.AnnotationDB({1: ('HBB1_TORMA', 10, 50)},
sp,
sliceAttrDict=dict(id=0, start=1, stop=2))
exon = annoDB[1]
# generate the names where these will be stored
tempdir = testutil.TempDir('exonAnnot')
filename = tempdir.subfile('cnested')
nlmsa = cnestedlist.NLMSA(filename,
'w',
pairwiseMode=True,
bidirectional=False)
nlmsa.addAnnotation(exon)
nlmsa.build()
annoDB.__doc__ = 'a little annotation db'
nlmsa.__doc__ = 'a little map'
worldbase.Bio.Annotation.annoDB = annoDB
worldbase.Bio.Annotation.map = nlmsa
worldbase.schema.Bio.Annotation.map = \
metabase.ManyToManyRelation(sp, annoDB, bindAttrs=('exons', ))
def test_mysqlannot(self):
'Test building an AnnotationDB from MySQL'
from pygr import seqdb, cnestedlist, sqlgraph
dm2 = pygr.Data.getResource('TEST.Seq.Genome.dm2')
# BUILD ANNOTATION DATABASE FOR REFSEQ EXONS: MYSQL VERSION
exon_slices = sqlgraph.SQLTableClustered(
'%s.pygr_refGene_exonAnnot%s_dm2' % (testInputDB,
smallSamplePostfix),
clusterKey='chromosome', maxCache=0)
exon_db = seqdb.AnnotationDB(exon_slices, dm2,
sliceAttrDict=dict(id='chromosome',
gene_id='name',
exon_id='exon_id'))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'refGene_exonAnnot_SQL_dm2'), 'w',
pairwiseMode=True, bidirectional=False)
for id in exon_db:
msa.addAnnotation(exon_db[id])
exon_db.clear_cache() # not really necessary; cache should autoGC
exon_slices.clear_cache()
msa.build()
exon_db.__doc__ = 'SQL Exon Annotation Database for dm2'
pygr.Data.addResource('TEST.Annotation.SQL.dm2.exons', exon_db)
msa.__doc__ = 'SQL NLMSA Exon for dm2'
pygr.Data.addResource('TEST.Annotation.NLMSA.SQL.dm2.exons', msa)
exon_schema = pygr.Data.ManyToManyRelation(dm2, exon_db,
bindAttrs=('exon2', ))
exon_schema.__doc__ = 'SQL Exon Schema for dm2'
pygr.Data.addSchema('TEST.Annotation.NLMSA.SQL.dm2.exons', exon_schema)
# BUILD ANNOTATION DATABASE FOR REFSEQ SPLICES: MYSQL VERSION
splice_slices = sqlgraph.SQLTableClustered(
'%s.pygr_refGene_spliceAnnot%s_dm2' % (testInputDB,
smallSamplePostfix),
clusterKey='chromosome', maxCache=0)
splice_db = seqdb.AnnotationDB(splice_slices, dm2,
sliceAttrDict=dict(id='chromosome',
gene_id='name',
splice_id='splice_id'))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'refGene_spliceAnnot_SQL_dm2'),
'w', pairwiseMode=True, bidirectional=False)
for id in splice_db:
msa.addAnnotation(splice_db[id])
splice_db.clear_cache() # not really necessary; cache should autoGC
splice_slices.clear_cache()
msa.build()
splice_db.__doc__ = 'SQL Splice Annotation Database for dm2'
pygr.Data.addResource('TEST.Annotation.SQL.dm2.splices', splice_db)
msa.__doc__ = 'SQL NLMSA Splice for dm2'
pygr.Data.addResource('TEST.Annotation.NLMSA.SQL.dm2.splices', msa)
splice_schema = pygr.Data.ManyToManyRelation(dm2, splice_db,
bindAttrs=('splice2', ))
splice_schema.__doc__ = 'SQL Splice Schema for dm2'
pygr.Data.addSchema('TEST.Annotation.NLMSA.SQL.dm2.splices',
splice_schema)
# BUILD ANNOTATION DATABASE FOR MOST CONSERVED ELEMENTS FROM UCSC:
# MYSQL VERSION
ucsc_slices = sqlgraph.SQLTableClustered(
'%s.pygr_phastConsElements15way%s_dm2' % (testInputDB,
smallSamplePostfix),
clusterKey='chromosome', maxCache=0)
ucsc_db = seqdb.AnnotationDB(ucsc_slices, dm2,
sliceAttrDict=dict(id='chromosome',
gene_id='name',
ucsc_id='ucsc_id'))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'phastConsElements15way_SQL_dm2'),
'w', pairwiseMode=True, bidirectional=False)
for id in ucsc_db:
msa.addAnnotation(ucsc_db[id])
ucsc_db.clear_cache() # not really necessary; cache should autoGC
ucsc_slices.clear_cache()
msa.build()
ucsc_db.__doc__ = 'SQL Most Conserved Elements for dm2'
pygr.Data.addResource('TEST.Annotation.UCSC.SQL.dm2.mostconserved',
ucsc_db)
msa.__doc__ = 'SQL NLMSA for Most Conserved Elements for dm2'
pygr.Data.addResource(
'TEST.Annotation.UCSC.NLMSA.SQL.dm2.mostconserved', msa)
ucsc_schema = pygr.Data.ManyToManyRelation(dm2, ucsc_db,
bindAttrs=('element2', ))
ucsc_schema.__doc__ = \
'SQL Schema for UCSC Most Conserved Elements for dm2'
pygr.Data.addSchema('TEST.Annotation.UCSC.NLMSA.SQL.dm2.mostconserved',
ucsc_schema)
pygr.Data.save()
pygr.Data.clear_cache()
# QUERY TO EXON AND SPLICES ANNOTATION DATABASE
dm2 = pygr.Data.getResource('TEST.Seq.Genome.dm2')
exonmsa = pygr.Data.getResource('TEST.Annotation.NLMSA.SQL.dm2.exons')
splicemsa = \
pygr.Data.getResource('TEST.Annotation.NLMSA.SQL.dm2.splices')
conservedmsa = \
pygr.Data.getResource('TEST.Annotation.UCSC.NLMSA.SQL.dm2.mostconserved')
exons = pygr.Data.getResource('TEST.Annotation.SQL.dm2.exons')
splices = pygr.Data.getResource('TEST.Annotation.SQL.dm2.splices')
mostconserved = \
pygr.Data.getResource('TEST.Annotation.UCSC.SQL.dm2.mostconserved')
# OPEN DM2_MULTIZ15WAY NLMSA
msa = cnestedlist.NLMSA(os.path.join(msaDir, 'dm2_multiz15way'), 'r',
trypath=[seqDir])
exonAnnotFileName = os.path.join(testInputDir,
'Annotation_ConservedElement_Exons%s_dm2.txt'
% smallSamplePostfix)
intronAnnotFileName = os.path.join(testInputDir,
'Annotation_ConservedElement_Introns%s_dm2.txt'
% smallSamplePostfix)
newexonAnnotFileName = os.path.join(self.path, 'new_Exons_dm2.txt')
newintronAnnotFileName = os.path.join(self.path, 'new_Introns_dm2.txt')
tmpexonAnnotFileName = self.copyFile(exonAnnotFileName)
tmpintronAnnotFileName = self.copyFile(intronAnnotFileName)
if smallSampleKey:
chrList = [smallSampleKey]
else:
chrList = dm2.seqLenDict.keys()
chrList.sort()
outfile = open(newexonAnnotFileName, 'w')
for chrid in chrList:
slice = dm2[chrid]
try:
ex1 = exonmsa[slice]
except KeyError:
continue
else:
exlist1 = [(ix.exon_id, ix) for ix in ex1.keys()]
exlist1.sort()
for ixx, exon in exlist1:
saveList = []
tmp = exon.sequence
tmpexon = exons[exon.exon_id]
tmpslice = tmpexon.sequence # FOR REAL EXON COORDINATE
wlist1 = 'EXON', chrid, tmpexon.exon_id, tmpexon.gene_id, \
tmpslice.start, tmpslice.stop
try:
out1 = conservedmsa[tmp]
except KeyError:
pass
else:
elementlist = [(ix.ucsc_id, ix) for ix in out1.keys()]
elementlist.sort()
for iyy, element in elementlist:
if element.stop - element.start < 100:
continue
score = int(string.split(element.gene_id, '=')[1])
if score < 100:
continue
tmp2 = element.sequence
tmpelement = mostconserved[element.ucsc_id]
# FOR REAL ELEMENT COORDINATE
tmpslice2 = tmpelement.sequence
wlist2 = wlist1 + (tmpelement.ucsc_id,
tmpelement.gene_id,
tmpslice2.start, tmpslice2.stop)
slicestart, sliceend = max(tmp.start, tmp2.start),\
min(tmp.stop, tmp2.stop)
tmp1 = msa.seqDict['dm2.' + chrid][slicestart:
sliceend]
edges = msa[tmp1].edges()
for src, dest, e in edges:
if src.stop - src.start < 100:
continue
palign, pident = e.pAligned(), e.pIdentity()
if palign < 0.8 or pident < 0.8:
continue
palign, pident = '%.2f' % palign, \
'%.2f' % pident
wlist3 = wlist2 + ((~msa.seqDict)[src],
str(src), src.start,
src.stop,
(~msa.seqDict)[dest],
str(dest), dest.start,
dest.stop, palign, pident)
saveList.append('\t'.join(map(str, wlist3))
+ '\n')
saveList.sort()
for saveline in saveList:
outfile.write(saveline)
outfile.close()
md5old = hashlib.md5()
md5old.update(open(tmpexonAnnotFileName, 'r').read())
md5new = hashlib.md5()
md5new.update(open(newexonAnnotFileName, 'r').read())
assert md5old.digest() == md5new.digest()
outfile = open(newintronAnnotFileName, 'w')
for chrid in chrList:
slice = dm2[chrid]
try:
sp1 = splicemsa[slice]
except:
continue
else:
splist1 = [(ix.splice_id, ix) for ix in sp1.keys()]
splist1.sort()
for ixx, splice in splist1:
saveList = []
tmp = splice.sequence
tmpsplice = splices[splice.splice_id]
tmpslice = tmpsplice.sequence # FOR REAL EXON COORDINATE
wlist1 = 'INTRON', chrid, tmpsplice.splice_id, \
tmpsplice.gene_id, tmpslice.start, tmpslice.stop
try:
out1 = conservedmsa[tmp]
except KeyError:
pass
else:
elementlist = [(ix.ucsc_id, ix) for ix in out1.keys()]
elementlist.sort()
for iyy, element in elementlist:
if element.stop - element.start < 100:
continue
score = int(string.split(element.gene_id, '=')[1])
if score < 100:
continue
tmp2 = element.sequence
tmpelement = mostconserved[element.ucsc_id]
# FOR REAL ELEMENT COORDINATE
tmpslice2 = tmpelement.sequence
wlist2 = wlist1 + (tmpelement.ucsc_id,
tmpelement.gene_id,
tmpslice2.start, tmpslice2.stop)
slicestart, sliceend = max(tmp.start, tmp2.start),\
min(tmp.stop, tmp2.stop)
tmp1 = msa.seqDict['dm2.' + chrid][slicestart:
sliceend]
edges = msa[tmp1].edges()
for src, dest, e in edges:
if src.stop - src.start < 100:
continue
palign, pident = e.pAligned(), e.pIdentity()
if palign < 0.8 or pident < 0.8:
continue
palign, pident = '%.2f' % palign, \
'%.2f' % pident
wlist3 = wlist2 + ((~msa.seqDict)[src],
str(src), src.start,
src.stop,
(~msa.seqDict)[dest],
str(dest), dest.start,
dest.stop, palign, pident)
saveList.append('\t'.join(map(str, wlist3))
+ '\n')
saveList.sort()
for saveline in saveList:
outfile.write(saveline)
outfile.close()
md5old = hashlib.md5()
md5old.update(open(tmpintronAnnotFileName, 'r').read())
md5new = hashlib.md5()
md5new.update(open(newintronAnnotFileName, 'r').read())
assert md5old.digest() == md5new.digest()
def test_collectionannot(self):
'Test building an AnnotationDB from file'
from pygr import seqdb, cnestedlist, sqlgraph
dm2 = pygr.Data.getResource('TEST.Seq.Genome.dm2')
# BUILD ANNOTATION DATABASE FOR REFSEQ EXONS
exon_slices = Collection(
filename=os.path.join(self.path, 'refGene_exonAnnot_dm2.cdb'),
intKeys=True, mode='cr', writeback=False)
exon_db = seqdb.AnnotationDB(exon_slices, dm2,
sliceAttrDict=dict(id=0, exon_id=1,
orientation=2,
gene_id=3, start=4,
stop=5))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'refGene_exonAnnot_dm2'), 'w',
pairwiseMode=True, bidirectional=False)
for lines in open(os.path.join(testInputDir,
'refGene_exonAnnot%s_dm2.txt'
% smallSamplePostfix),
'r').xreadlines():
row = [x for x in lines.split('\t')] # CONVERT TO LIST SO MUTABLE
row[1] = int(row[1]) # CONVERT FROM STRING TO INTEGER
exon_slices[row[1]] = row
exon = exon_db[row[1]] # GET THE ANNOTATION OBJECT FOR THIS EXON
msa.addAnnotation(exon) # SAVE IT TO GENOME MAPPING
exon_db.clear_cache() # not really necessary; cache should autoGC
# SHELVE SHOULD BE EXPLICITLY CLOSED IN ORDER TO SAVE CURRENT CONTENTS
exon_slices.close()
msa.build() # FINALIZE GENOME ALIGNMENT INDEXES
exon_db.__doc__ = 'Exon Annotation Database for dm2'
pygr.Data.addResource('TEST.Annotation.dm2.exons', exon_db)
msa.__doc__ = 'NLMSA Exon for dm2'
pygr.Data.addResource('TEST.Annotation.NLMSA.dm2.exons', msa)
exon_schema = pygr.Data.ManyToManyRelation(dm2, exon_db,
bindAttrs=('exon1', ))
exon_schema.__doc__ = 'Exon Schema for dm2'
pygr.Data.addSchema('TEST.Annotation.NLMSA.dm2.exons', exon_schema)
# BUILD ANNOTATION DATABASE FOR REFSEQ SPLICES
splice_slices = Collection(
filename=os.path.join(self.path, 'refGene_spliceAnnot_dm2.cdb'),
intKeys=True, mode='cr', writeback=False)
splice_db = seqdb.AnnotationDB(splice_slices, dm2,
sliceAttrDict=dict(id=0, splice_id=1,
orientation=2,
gene_id=3, start=4,
stop=5))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'refGene_spliceAnnot_dm2'), 'w',
pairwiseMode=True, bidirectional=False)
for lines in open(os.path.join(testInputDir,
'refGene_spliceAnnot%s_dm2.txt'
% smallSamplePostfix),
'r').xreadlines():
row = [x for x in lines.split('\t')] # CONVERT TO LIST SO MUTABLE
row[1] = int(row[1]) # CONVERT FROM STRING TO INTEGER
splice_slices[row[1]] = row
# GET THE ANNOTATION OBJECT FOR THIS EXON
splice = splice_db[row[1]]
msa.addAnnotation(splice) # SAVE IT TO GENOME MAPPING
splice_db.clear_cache() # not really necessary; cache should autoGC
# SHELVE SHOULD BE EXPLICITLY CLOSED IN ORDER TO SAVE CURRENT CONTENTS
splice_slices.close()
msa.build() # FINALIZE GENOME ALIGNMENT INDEXES
splice_db.__doc__ = 'Splice Annotation Database for dm2'
pygr.Data.addResource('TEST.Annotation.dm2.splices', splice_db)
msa.__doc__ = 'NLMSA Splice for dm2'
pygr.Data.addResource('TEST.Annotation.NLMSA.dm2.splices', msa)
splice_schema = pygr.Data.ManyToManyRelation(dm2, splice_db,
bindAttrs=('splice1', ))
splice_schema.__doc__ = 'Splice Schema for dm2'
pygr.Data.addSchema('TEST.Annotation.NLMSA.dm2.splices', splice_schema)
# BUILD ANNOTATION DATABASE FOR MOST CONSERVED ELEMENTS FROM UCSC
ucsc_slices = Collection(
filename=os.path.join(self.path, 'phastConsElements15way_dm2.cdb'),
intKeys=True, mode='cr', writeback=False)
ucsc_db = seqdb.AnnotationDB(ucsc_slices, dm2,
sliceAttrDict=dict(id=0, ucsc_id=1,
orientation=2,
gene_id=3, start=4,
stop=5))
msa = cnestedlist.NLMSA(os.path.join(self.path,
'phastConsElements15way_dm2'),
'w', pairwiseMode=True, bidirectional=False)
for lines in open(os.path.join(testInputDir,
'phastConsElements15way%s_dm2.txt'
% smallSamplePostfix),
'r').xreadlines():
row = [x for x in lines.split('\t')] # CONVERT TO LIST SO MUTABLE
row[1] = int(row[1]) # CONVERT FROM STRING TO INTEGER
ucsc_slices[row[1]] = row
ucsc = ucsc_db[row[1]] # GET THE ANNOTATION OBJECT FOR THIS EXON
msa.addAnnotation(ucsc) # SAVE IT TO GENOME MAPPING
ucsc_db.clear_cache() # not really necessary; cache should autoGC
# SHELVE SHOULD BE EXPLICITLY CLOSED IN ORDER TO SAVE CURRENT CONTENTS
ucsc_slices.close()
msa.build() # FINALIZE GENOME ALIGNMENT INDEXES
ucsc_db.__doc__ = 'Most Conserved Elements for dm2'
pygr.Data.addResource('TEST.Annotation.UCSC.dm2.mostconserved',
ucsc_db)
msa.__doc__ = 'NLMSA for Most Conserved Elements for dm2'
pygr.Data.addResource('TEST.Annotation.UCSC.NLMSA.dm2.mostconserved',
msa)
ucsc_schema = pygr.Data.ManyToManyRelation(dm2, ucsc_db,
bindAttrs=('element1', ))
ucsc_schema.__doc__ = 'Schema for UCSC Most Conserved Elements for dm2'
pygr.Data.addSchema('TEST.Annotation.UCSC.NLMSA.dm2.mostconserved',
ucsc_schema)
pygr.Data.save()
pygr.Data.clear_cache() # force resources to reload when requested
# QUERY TO EXON AND SPLICES ANNOTATION DATABASE
dm2 = pygr.Data.getResource('TEST.Seq.Genome.dm2')
exonmsa = pygr.Data.getResource('TEST.Annotation.NLMSA.dm2.exons')
splicemsa = pygr.Data.getResource('TEST.Annotation.NLMSA.dm2.splices')
conservedmsa = \
pygr.Data.getResource('TEST.Annotation.UCSC.NLMSA.dm2.mostconserved')
exons = pygr.Data.getResource('TEST.Annotation.dm2.exons')
splices = pygr.Data.getResource('TEST.Annotation.dm2.splices')
mostconserved = \
pygr.Data.getResource('TEST.Annotation.UCSC.dm2.mostconserved')
# OPEN DM2_MULTIZ15WAY NLMSA
msa = cnestedlist.NLMSA(os.path.join(msaDir, 'dm2_multiz15way'), 'r',
trypath=[seqDir])
exonAnnotFileName = os.path.join(testInputDir,
'Annotation_ConservedElement_Exons%s_dm2.txt'
% smallSamplePostfix)
intronAnnotFileName = os.path.join(testInputDir,
'Annotation_ConservedElement_Introns%s_dm2.txt'
% smallSamplePostfix)
newexonAnnotFileName = os.path.join(self.path, 'new_Exons_dm2.txt')
newintronAnnotFileName = os.path.join(self.path, 'new_Introns_dm2.txt')
tmpexonAnnotFileName = self.copyFile(exonAnnotFileName)
tmpintronAnnotFileName = self.copyFile(intronAnnotFileName)
if smallSampleKey:
chrList = [smallSampleKey]
else:
chrList = dm2.seqLenDict.keys()
chrList.sort()
outfile = open(newexonAnnotFileName, 'w')
for chrid in chrList:
slice = dm2[chrid]
try:
ex1 = exonmsa[slice]
except KeyError:
continue
else:
exlist1 = [(ix.exon_id, ix) for ix in ex1.keys()]
exlist1.sort()
for ixx, exon in exlist1:
saveList = []
tmp = exon.sequence
tmpexon = exons[exon.exon_id]
tmpslice = tmpexon.sequence # FOR REAL EXON COORDINATE
wlist1 = 'EXON', chrid, tmpexon.exon_id, tmpexon.gene_id, \
tmpslice.start, tmpslice.stop
try:
out1 = conservedmsa[tmp]
except KeyError:
pass
else:
elementlist = [(ix.ucsc_id, ix) for ix in out1.keys()]
elementlist.sort()
for iyy, element in elementlist:
if element.stop - element.start < 100:
continue
score = int(string.split(element.gene_id, '=')[1])
if score < 100:
continue
tmp2 = element.sequence
tmpelement = mostconserved[element.ucsc_id]
# FOR REAL ELEMENT COORDINATE
tmpslice2 = tmpelement.sequence
wlist2 = wlist1 + (tmpelement.ucsc_id,
tmpelement.gene_id,
tmpslice2.start, tmpslice2.stop)
slicestart, sliceend = max(tmp.start, tmp2.start),\
min(tmp.stop, tmp2.stop)
tmp1 = msa.seqDict['dm2.' + chrid][slicestart:
sliceend]
edges = msa[tmp1].edges()
for src, dest, e in edges:
if src.stop - src.start < 100:
continue
palign, pident = e.pAligned(), e.pIdentity()
if palign < 0.8 or pident < 0.8:
continue
palign, pident = '%.2f' % palign, \
'%.2f' % pident
wlist3 = wlist2 + ((~msa.seqDict)[src],
str(src), src.start,
src.stop,
(~msa.seqDict)[dest],
str(dest), dest.start,
dest.stop, palign, pident)
saveList.append('\t'.join(map(str, wlist3))
+ '\n')
saveList.sort()
for saveline in saveList:
outfile.write(saveline)
outfile.close()
md5old = hashlib.md5()
md5old.update(open(tmpexonAnnotFileName, 'r').read())
md5new = hashlib.md5()
md5new.update(open(newexonAnnotFileName, 'r').read())
assert md5old.digest() == md5new.digest()
outfile = open(newintronAnnotFileName, 'w')
for chrid in chrList:
slice = dm2[chrid]
try:
sp1 = splicemsa[slice]
except:
continue
else:
splist1 = [(ix.splice_id, ix) for ix in sp1.keys()]
splist1.sort()
for ixx, splice in splist1:
saveList = []
tmp = splice.sequence
tmpsplice = splices[splice.splice_id]
tmpslice = tmpsplice.sequence # FOR REAL EXON COORDINATE
wlist1 = 'INTRON', chrid, tmpsplice.splice_id, \
tmpsplice.gene_id, tmpslice.start, tmpslice.stop
try:
out1 = conservedmsa[tmp]
except KeyError:
pass
else:
elementlist = [(ix.ucsc_id, ix) for ix in out1.keys()]
elementlist.sort()
for iyy, element in elementlist:
if element.stop - element.start < 100:
continue
score = int(string.split(element.gene_id, '=')[1])
if score < 100:
continue
tmp2 = element.sequence
tmpelement = mostconserved[element.ucsc_id]
# FOR REAL ELEMENT COORDINATE
tmpslice2 = tmpelement.sequence
wlist2 = wlist1 + (tmpelement.ucsc_id,
tmpelement.gene_id,
tmpslice2.start, tmpslice2.stop)
slicestart, sliceend = max(tmp.start, tmp2.start),\
min(tmp.stop, tmp2.stop)
tmp1 = msa.seqDict['dm2.' + chrid][slicestart:
sliceend]
edges = msa[tmp1].edges()
for src, dest, e in edges:
if src.stop - src.start < 100:
continue
palign, pident = e.pAligned(), e.pIdentity()
if palign < 0.8 or pident < 0.8:
continue
palign, pident = '%.2f' % palign, \
'%.2f' % pident
wlist3 = wlist2 + ((~msa.seqDict)[src],
str(src), src.start,
src.stop,
(~msa.seqDict)[dest],
str(dest), dest.start,
dest.stop, palign, pident)
saveList.append('\t'.join(map(str, wlist3))
+ '\n')
saveList.sort()
for saveline in saveList:
outfile.write(saveline)
outfile.close()
md5old = hashlib.md5()
md5old.update(open(tmpintronAnnotFileName, 'r').read())
md5new = hashlib.md5()
md5new.update(open(newintronAnnotFileName, 'r').read())
assert md5old.digest() == md5new.digest()