def test_fromgff3_region():
tbl_features = etl.fromgff3('fixture/sample.sorted.gff.gz',
region='apidb|MAL5')
eq_(7, tbl_features.nrows())
tbl_features = etl.fromgff3('fixture/sample.sorted.gff.gz',
region='apidb|MAL5:1289593-1289595')
eq_(4, tbl_features.nrows())
def __init__(self, fasta_path, gff3_path, seqid=None):
"""
An annotated reference genome.
Parameters
----------
fasta_path : string
Path to reference genome FASTA file.
gff3_path : string
Path to genome annotations GFF3 file.
"""
# store initialisation parameters
self._fasta_path = fasta_path
self._gff3_path = gff3_path
self._seqid = seqid
# setup access to reference sequence
self._fasta = pyfasta.Fasta(fasta_path)
# setup access to GFF3 as a table
if isinstance(gff3_path, (list, tuple)):
tbl_features = etl.cat(*[etl.fromgff3(p) for p in gff3_path])
else:
tbl_features = etl.fromgff3(gff3_path)
tbl_features = (tbl_features.unpackdict(
'attributes', ['ID', 'Parent']).rename({
'ID': 'feature_id',
'Parent': 'parent_id',
'end': 'stop'
}).select(lambda row: (row.stop - row.start) > 0))
# limit data to a single chromosome
if seqid is not None:
tbl_features = tbl_features.eq('seqid', seqid)
self._tbl_features = tbl_features.cache()
# index features by ID
self._idx_feature_id = self._tbl_features.recordlookupone('feature_id')
# index features by parent ID
self._idx_parent_id = self._tbl_features.recordlookup('parent_id')
# index features by genomic location
self._idx_location = self._tbl_features.facetintervalrecordlookup(
'seqid', 'start', 'stop', include_stop=True)
def get_geneset_features(geneset_fn, chrom, start=None, stop=None):
"""Function to load geneset features for a specific genome region via petl."""
if start and stop:
region = '%s:%s-%s' % (chrom, start, stop)
else:
region = chrom
return etl.fromgff3(geneset_fn, region=region)
def test_fromgff3_trailing_semicolon():
features = etl.fromgff3(sample_gff3_filename)
row = list(features)[2]
eq_('apidb|MAL2', row[0])
eq_('ApiDB', row[1])
eq_('supercontig', row[2])
eq_(1, row[3])
eq_(947102, row[4])
eq_('.', row[5])
eq_('+', row[6])
eq_('.', row[7])
eq_('apidb|MAL2', row[8]['ID'])
eq_('MAL2', row[8]['Name'])
eq_('Plasmodium falciparum', row[8]['organism_name'])
def test_fromgff3_trailing_semicolon():
features = etl.fromgff3(sample_gff3_filename)
row = list(features)[2]
eq_("apidb|MAL2", row[0])
eq_("ApiDB", row[1])
eq_("supercontig", row[2])
eq_(1, row[3])
eq_(947102, row[4])
eq_(".", row[5])
eq_("+", row[6])
eq_(".", row[7])
eq_("apidb|MAL2", row[8]["ID"])
eq_("MAL2", row[8]["Name"])
eq_("Plasmodium falciparum", row[8]["organism_name"])
def test_fromgff3():
features = etl.fromgff3(sample_gff3_filename)
eq_(GFF3_HEADER, features.header())
row = list(features)[1]
eq_('apidb|MAL1', row[0])
eq_('ApiDB', row[1])
eq_('supercontig', row[2])
eq_(1, row[3])
eq_(643292, row[4])
eq_('.', row[5])
eq_('+', row[6])
eq_('.', row[7])
eq_('apidb|MAL1', row[8]['ID'])
eq_('MAL1', row[8]['Name'])
eq_('Plasmodium falciparum', row[8]['organism_name'])
def test_fromgff3():
features = etl.fromgff3(sample_gff3_filename)
eq_(GFF3_HEADER, features.header())
row = list(features)[1]
eq_("apidb|MAL1", row[0])
eq_("ApiDB", row[1])
eq_("supercontig", row[2])
eq_(1, row[3])
eq_(643292, row[4])
eq_(".", row[5])
eq_("+", row[6])
eq_(".", row[7])
eq_("apidb|MAL1", row[8]["ID"])
eq_("MAL1", row[8]["Name"])
eq_("Plasmodium falciparum", row[8]["organism_name"])
import petlx.bio
table1 = etl.fromtabix('fixture/test.bed.gz',
region='Pf3D7_02_v3')
table1
table2 = etl.fromtabix('fixture/test.bed.gz',
region='Pf3D7_02_v3:110000-120000')
table2
# fromgff3()
############
import petl as etl
# activate bio extensions
import petlx.bio
table1 = etl.fromgff3('fixture/sample.gff')
table1.look(truncate=30)
# extract from a specific genome region via tabix
table2 = etl.fromgff3('fixture/sample.sorted.gff.gz',
region='apidb|MAL5:1289593-1289595')
table2.look(truncate=30)
# fromvcf()
###########
import petl as etl
# activate bio extensions
import petlx.bio
table1 = etl.fromvcf('fixture/sample.vcf')
table1.look(truncate=20)
import petl as etl
# activate bio extensions
import petlx.bio
table1 = etl.fromtabix('fixture/test.bed.gz', region='Pf3D7_02_v3')
table1
table2 = etl.fromtabix('fixture/test.bed.gz',
region='Pf3D7_02_v3:110000-120000')
table2
# fromgff3()
############
import petl as etl
# activate bio extensions
import petlx.bio
table1 = etl.fromgff3('fixture/sample.gff')
table1.look(truncate=30)
# extract from a specific genome region via tabix
table2 = etl.fromgff3('fixture/sample.sorted.gff.gz',
region='apidb|MAL5:1289593-1289595')
table2.look(truncate=30)
# fromvcf()
###########
import petl as etl
# activate bio extensions
import petlx.bio
table1 = etl.fromvcf('fixture/sample.vcf')
table1.look(truncate=20)
def test_fromgff3_region():
tbl_features = etl.fromgff3("fixture/sample.sorted.gff.gz", region="apidb|MAL5")
eq_(7, tbl_features.nrows())
tbl_features = etl.fromgff3("fixture/sample.sorted.gff.gz", region="apidb|MAL5:1289593-1289595")
eq_(4, tbl_features.nrows())