def test_vanilla(self):
dummy = Genome(name='GRCh37.75_Y-Only', SNPs='dummySRY_AGN')
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('HTGCAATCATATGCTTCTGC', persProt.transcript.cDNA[:20])
def setUp(self):
try :
B.importGenome("Human.GRCh37.75_Y-Only.tar.gz")
except KeyError :
print "--> Seems to already exist in db"
try :
B.importSNPs("Human_agnostic.dummySRY.tar.gz")
except KeyError :
print "--> Seems to already exist in db"
self.ref = Genome(name = 'GRCh37.75_Y-Only')
def test_noModif(self) : from pyGeno.SNPFiltering import SNPFilter class MyFilter(SNPFilter) : def __init__(self) : SNPFilter.__init__(self) def filter(self, chromosome, dummySRY_AGN) : return None dummy = Genome(name = 'GRCh37.75_Y-Only', SNPs = 'dummySRY_AGN', SNPFilter = MyFilter()) persProt = dummy.get(Protein, id = 'ENSP00000438917')[0] refProt = self.ref.get(Protein, id = 'ENSP00000438917')[0] self.assertEqual(persProt.transcript.cDNA[:20], refProt.transcript.cDNA[:20])
def test_SNP(self) :
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter) :
def __init__(self) :
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN) :
from pyGeno.SNPFiltering import SequenceSNP
return SequenceSNP(dummySRY_AGN.alt)
dummy = Genome(name = 'GRCh37.75_Y-Only', SNPs = 'dummySRY_AGN', SNPFilter = MyFilter())
persProt = dummy.get(Protein, id = 'ENSP00000438917')[0]
refProt = self.ref.get(Protein, id = 'ENSP00000438917')[0]
self.assertEqual('M', refProt.sequence[0])
self.assertEqual('L', persProt.sequence[0])
def test_deletion(self) :
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter) :
def __init__(self) :
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN) :
from pyGeno.SNPFiltering import SequenceDel
refAllele = chromosome.refSequence[dummySRY_AGN.start]
return SequenceDel(1)
dummy = Genome(name = 'GRCh37.75_Y-Only', SNPs = 'dummySRY_AGN', SNPFilter = MyFilter())
persProt = dummy.get(Protein, id = 'ENSP00000438917')[0]
refProt = self.ref.get(Protein, id = 'ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('TGCAATCATATGCTTCTGCT', persProt.transcript.cDNA[:20])
def test_indels(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN_indels):
from pyGeno.SNPFiltering import SequenceInsert
ret = ""
for s in dummySRY_AGN_indels:
ret += "X"
return SequenceInsert(ret)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN_indels',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('XXXATGCAATCATATGCTTC', persProt.transcript.cDNA[:20])
def setUp(self):
# try :
# B.importGenome("Human.GRCh37.75_Y-Only.tar.gz")
# except KeyError :
# deleteGenome("human", "GRCh37.75_Y-Only")
# B.importGenome("Human.GRCh37.75_Y-Only.tar.gz")
# print "--> Seems to already exist in db"
# try :
# B.importSNPs("Human_agnostic.dummySRY.tar.gz")
# except KeyError :
# deleteSNPs("dummySRY_AGN")
# B.importSNPs("Human_agnostic.dummySRY.tar.gz")
# print "--> Seems to already exist in db"
# try :
# B.importSNPs("Human_agnostic.dummySRY_indels")
# except KeyError :
# deleteSNPs("dummySRY_AGN_indels")
# B.importSNPs("Human_agnostic.dummySRY_indels")
# print "--> Seems to already exist in db"
self.ref = Genome(name='GRCh37.75_Y-Only')
class pyGenoSNPTests(unittest.TestCase):
def setUp(self):
# try :
# B.importGenome("Human.GRCh37.75_Y-Only.tar.gz")
# except KeyError :
# deleteGenome("human", "GRCh37.75_Y-Only")
# B.importGenome("Human.GRCh37.75_Y-Only.tar.gz")
# print "--> Seems to already exist in db"
# try :
# B.importSNPs("Human_agnostic.dummySRY.tar.gz")
# except KeyError :
# deleteSNPs("dummySRY_AGN")
# B.importSNPs("Human_agnostic.dummySRY.tar.gz")
# print "--> Seems to already exist in db"
# try :
# B.importSNPs("Human_agnostic.dummySRY_indels")
# except KeyError :
# deleteSNPs("dummySRY_AGN_indels")
# B.importSNPs("Human_agnostic.dummySRY_indels")
# print "--> Seems to already exist in db"
self.ref = Genome(name='GRCh37.75_Y-Only')
def tearDown(self):
pass
# @unittest.skip("skipping")
def test_vanilla(self):
dummy = Genome(name='GRCh37.75_Y-Only', SNPs='dummySRY_AGN')
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('HTGCAATCATATGCTTCTGC', persProt.transcript.cDNA[:20])
# @unittest.skip("skipping")
def test_noModif(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
return None
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual(persProt.transcript.cDNA[:20],
refProt.transcript.cDNA[:20])
# @unittest.skip("skipping")
def test_insert(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceInsert
refAllele = chromosome.refSequence[dummySRY_AGN.start]
return SequenceInsert('XXX')
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('XXXATGCAATCATATGCTTC', persProt.transcript.cDNA[:20])
# @unittest.skip("skipping")
def test_SNP(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceSNP
return SequenceSNP(dummySRY_AGN.alt)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('M', refProt.sequence[0])
self.assertEqual('L', persProt.sequence[0])
# @unittest.skip("skipping")
def test_deletion(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceDel
refAllele = chromosome.refSequence[dummySRY_AGN.start]
return SequenceDel(1)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('TGCAATCATATGCTTCTGCT', persProt.transcript.cDNA[:20])
# @unittest.skip("skipping")
def test_indels(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN_indels):
from pyGeno.SNPFiltering import SequenceInsert
ret = ""
for s in dummySRY_AGN_indels:
ret += "X"
return SequenceInsert(ret)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN_indels',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('XXXATGCAATCATATGCTTC', persProt.transcript.cDNA[:20])
# @unittest.skip("skipping")
def test_bags(self):
dummy = Genome(name='GRCh37.75_Y-Only')
self.assertEqual(dummy.wrapped_object, self.ref.wrapped_object)
# @unittest.skip("skipping")
def test_prot_find(self):
prot = self.ref.get(Protein, id='ENSP00000438917')[0]
needle = prot.sequence[:10]
self.assertEqual(0, prot.find(needle))
needle = prot.sequence[-10:]
self.assertEqual(len(prot) - 10, prot.find(needle))
# @unittest.skip("skipping")
def test_trans_find(self):
trans = self.ref.get(Transcript, name="SRY-001")[0]
self.assertEqual(0, trans.find(trans[:5]))
def test_bags(self):
dummy = Genome(name='GRCh37.75_Y-Only')
self.assertEqual(dummy.wrapped_object, self.ref.wrapped_object)
def setUp(self):
self.ref = Genome(name='GRCh37.75_Y-Only')
class pyGenoSNPTests(unittest.TestCase):
def setUp(self):
self.ref = Genome(name='GRCh37.75_Y-Only')
def tearDown(self):
pass
def test_vanilla(self):
dummy = Genome(name='GRCh37.75_Y-Only', SNPs='dummySRY_AGN')
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('HTGCAATCATATGCTTCTGC', persProt.transcript.cDNA[:20])
def test_noModif(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
return None
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual(persProt.transcript.cDNA[:20],
refProt.transcript.cDNA[:20])
def test_insert(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceInsert
refAllele = chromosome.refSequence[dummySRY_AGN.start]
return SequenceInsert('TCA')
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('ATGATGCAATCATATGCTTC', persProt.transcript.cDNA[:20])
def test_SNP(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceSNP
return SequenceSNP(dummySRY_AGN.alt)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('M', refProt.sequence[0])
self.assertEqual('L', persProt.sequence[0])
def test_deletion(self):
from pyGeno.SNPFiltering import SNPFilter
class MyFilter(SNPFilter):
def __init__(self):
SNPFilter.__init__(self)
def filter(self, chromosome, dummySRY_AGN):
from pyGeno.SNPFiltering import SequenceDel
refAllele = chromosome.refSequence[dummySRY_AGN.start]
return SequenceDel(1)
dummy = Genome(name='GRCh37.75_Y-Only',
SNPs='dummySRY_AGN',
SNPFilter=MyFilter())
persProt = dummy.get(Protein, id='ENSP00000438917')[0]
refProt = self.ref.get(Protein, id='ENSP00000438917')[0]
self.assertEqual('ATGCAATCATATGCTTCTGC', refProt.transcript.cDNA[:20])
self.assertEqual('TGCAATCATATGCTTCTGCT', persProt.transcript.cDNA[:20])
def test_bags(self):
dummy = Genome(name='GRCh37.75_Y-Only')
self.assertEqual(dummy.wrapped_object, self.ref.wrapped_object)
def test_prot_find(self):
prot = self.ref.get(Protein, id='ENSP00000438917')[0]
needle = prot.sequence[:10]
self.assertEqual(0, prot.find(needle))
needle = prot.sequence[-10:]
self.assertEqual(len(prot) - 10, prot.find(needle))
def test_trans_find(self):
trans = self.ref.get(Transcript, name="SRY-001")[0]
self.assertEqual(0, trans.find(trans[:5]))
def test_import_remote_genome(self):
self.assertRaises(KeyError, B.importRemoteGenome,
"Human.GRCh37.75_Y-Only.tar.gz")
def test_import_remote_snps(self):
self.assertRaises(KeyError, B.importRemoteSNPs,
"Human_agnostic.dummySRY.tar.gz")
def importGenome(packageFile, batchSize=50, verbose=0):
"""Import a pyGeno genome package. A genome packages is a tar.gz ball that contains at it's root:
* gziped fasta files for all chromosomes, or URLs from where them must be downloaded
* gziped GTF gene_set file from Ensembl, or an URL from where it must be downloaded
* a manifest.ini file such as::
[package_infos]
description = Test package. This package installs only chromosome Y of mus musculus
maintainer = Tariq Daouda
maintainer_contact = tariq.daouda [at] umontreal
version = GRCm38.73
[genome]
species = Mus_musculus
name = GRCm38_test
source = http://useast.ensembl.org/info/data/ftp/index.html
[chromosome_files]
Y = Mus_musculus.GRCm38.73.dna.chromosome.Y.fa.gz / or an url such as ftp://... or http://
[gene_set]
gtf = Mus_musculus.GRCm38.73_Y-only.gtf.gz / or an url such as ftp://... or http://
All files except the manifest can be downloaded from: http://useast.ensembl.org/info/data/ftp/index.html
A rollback is performed if an exception is caught during importation
batchSize sets the number of genes to parse before performing a database save. PCs with little ram like
small values, while those endowed with more memory may perform faster with higher ones.
Verbose must be an int [0, 4] for various levels of verbosity
"""
def reformatItems(items):
s = str(items)
s = s.replace('[', '').replace(']', '').replace("',", ': ').replace(
'), ', '\n').replace("'", '').replace('(', '').replace(')', '')
return s
printf('Importing genome package: %s... (This may take a while)' %
packageFile)
packageDir = _decompressPackage(packageFile)
parser = SafeConfigParser()
parser.read(os.path.normpath(packageDir + '/manifest.ini'))
packageInfos = parser.items('package_infos')
genomeName = parser.get('genome', 'name')
species = parser.get('genome', 'species')
genomeSource = parser.get('genome', 'source')
seqTargetDir = conf.getGenomeSequencePath(species.lower(), genomeName)
if os.path.isdir(seqTargetDir):
raise KeyError(
"The directory %s already exists, Please call deleteGenome() first if you want to reinstall"
% seqTargetDir)
gtfFile = _getFile(parser.get('gene_set', 'gtf'), packageDir)
chromosomesFiles = {}
chromosomeSet = set()
for key, fil in parser.items('chromosome_files'):
chromosomesFiles[key] = _getFile(fil, packageDir)
chromosomeSet.add(key)
try:
genome = Genome(name=genomeName, species=species)
except KeyError:
pass
else:
raise KeyError(
"There seems to be already a genome (%s, %s), please call deleteGenome() first if you want to reinstall it"
% (genomeName, species))
genome = Genome_Raba()
genome.set(name=genomeName,
species=species,
source=genomeSource,
packageInfos=packageInfos)
printf("Importing:\n\t%s\nGenome:\n\t%s\n..." %
(reformatItems(packageInfos).replace('\n', '\n\t'),
reformatItems(parser.items('genome')).replace('\n', '\n\t')))
chros = _importGenomeObjects(gtfFile, chromosomeSet, genome, batchSize,
verbose)
os.makedirs(seqTargetDir)
startChro = 0
pBar = ProgressBar(nbEpochs=len(chros))
for chro in chros:
pBar.update(label="Importing DNA, chro %s" % chro.number)
length = _importSequence(chro, chromosomesFiles[chro.number.lower()],
seqTargetDir)
chro.start = startChro
chro.end = startChro + length
startChro = chro.end
pBar.close()
shutil.rmtree(packageDir)
#~ objgraph.show_most_common_types(limit=20)
return True
def encode(seq) :
code = {
'A' : [0, 0, 0, 1],
'T' : [0, 0, 1, 0],
'C' : [0, 1, 0, 0],
'G' : [1, 0, 0, 0]
}
res = []
for c in seq :
res.extend(code[c])
return res
ref = Genome(name = 'GRCh37.75_Y-Only')
seqs = []
targs = []
for trans in ref.iterGet(Transcript) :
if len(trans.cDNA) >= 150 :
r = random.randint(0, len(trans.cDNA) - 100)
dnaseq = trans.cDNA[r: r + 100]
seqs.append(encode(dnaseq))
targs.append(1)
randomseq = getRandomSeq(100)
seqs.append(encode(randomseq))
targs.append(0)
t = int(len(seqs) * 0.2)
validation = [seqs[0:t], targs[0:t]]
train = [seqs[t:], targs[t:]]
from pyGeno.Genome import *
g = Genome(name = "GRCh37.75")
prot = g.get(Protein, id = 'ENSP00000438917')[0]
#print the protein sequence
print prot.sequence
#print the protein's gene biotype
print prot.gene.biotype
#print protein's transcript sequence
print prot.transcript.sequence
#fancy queries
for exon in g.get(Exon, {"CDS_start >": x1, "CDS_end <=" : x2, "chromosome.number" : "22"}) :
#print the exon's coding sequence
print exon.CDS
#print the exon's transcript sequence
print exon.transcript.sequence
#You can do the same for your subject specific genomes
#by combining a reference genome with polymorphisms
g = Genome(name = "GRCh37.75", SNPs = ["STY21_RNA"], SNPFilter = MyFilter())