def test_init():
scriptPath = os.path.realpath(__file__)
dataPath = os.path.dirname(scriptPath) + "/../data/"
g = get_switches.GetSwitches(dataPath + 'annotation.pklz')
g._genes.flushSwitches()
g.run(dataPath + "switches")
# number of switches is correct
assert len(g._genes.nodes()["ENSG00.5"]["switches"]) == 2
assert len(g._genes.nodes()["ENSG03.3"]["switches"]) == 2
assert len(g._genes.nodes()["ENSG05.2"]["switches"]) == 1
assert len(g._genes.nodes()["ENSG09.6"]["switches"]) == 3
# check the switches are the right ones
assert [ x for x in g._genes.nodes()["ENSG00.5"]["switches"] if x.ctrl == "ENST01.2" and x.case == "ENST02.2" and x.samples == {"A","B","C"} ]
assert [ x for x in g._genes.nodes()["ENSG00.5"]["switches"] if x.ctrl == "ENST02.2" and x.case == "ENST01.2" and x.samples == {"D"} ]
assert [ x for x in g._genes.nodes()["ENSG03.3"]["switches"] if x.ctrl == "ENST06.1" and x.case == "ENST05.1" and x.samples == {"A","B"} ]
assert [ x for x in g._genes.nodes()["ENSG03.3"]["switches"] if x.ctrl == "ENST05.1" and x.case == "ENST06.1" and x.samples == {"C","D"} ]
assert [ x for x in g._genes.nodes()["ENSG05.2"]["switches"] if x.ctrl == "ENST08.1" and x.case == "ENST09.1" and x.samples == {"A","B"} ]
assert [ x for x in g._genes.nodes()["ENSG09.6"]["switches"] if x.ctrl == "ENST15.1" and x.case == "ENST13.5" and x.samples == {"A","B","C","D"} ]
assert [ x for x in g._genes.nodes()["ENSG09.6"]["switches"] if x.ctrl == "ENST16.2" and x.case == "ENST13.5" and x.samples == {"E","F","G"} ]
assert [ x for x in g._genes.nodes()["ENSG09.6"]["switches"] if x.ctrl == "ENST16.2" and x.case == "ENST14.5" and x.samples == {"H","I"} ]
def test_run():
g = get_switches.GetSwitches(dataPath + 'annotation.pklz')
g.run(dataPath + "switches")
assert [x for x in g._genes.switches(g._txs)]
def test_printSwitches():
g = get_switches.GetSwitches(dataPath + 'annotation.pklz')
g.run(dataPath + 'switches')
io.printSwitches(g._genes, g._txs)
switches = [ x for x in io.readTable("switches_spada.tsv") ]
assert len(switches) == 8
os.remove("switches_spada.tsv")
def test_printSwitchesToGff():
g = get_switches.GetSwitches(dataPath + 'annotation.pklz')
g.run(dataPath + 'switches')
io.printSwitchesToGff(g._genes, g._txs)
for line in io.readGTF('switches_spada.gff', tag_sep = '='):
if line['feature'] == 'mRNA':
assert line['ID'] in g._txs.nodes()
assert line['strand'] == g._txs[line['ID']]['strand']
elif line['feature'] == 'exon':
assert [line['start'], line['end']] in g._txs[line['Parent']]['exons']
assert line['strand'] == g._txs[line['Parent']]['strand']
elif line['feature'] == 'CDS':
assert (line['start'], line['end']) == tuple(g._txs[line['Parent']]['CDS'])
assert line['strand'] == g._txs[line['Parent']]['strand']
elif line['feature'] == 'start_codon':
if line['strand'] == '+':
assert line['start'] == g._txs[line['Parent']]['start_codon']
elif line['strand'] == '-':
assert line['end'] == g._txs[line['Parent']]['start_codon']
assert line['strand'] == g._txs[line['Parent']]['strand']
elif line['feature'] in ('five_prime_UTR', 'three_prime_UTR'):
pass
elif line['feature'] == 'translated_nucleotide_match':
parent = line['CDS_matches'].replace('cds_', '')
assert line['strand'] == g._txs[parent]['strand']
p = protein.Protein(parent, g._txs[parent])
regions = p.getFeature(line['Note'], line['Alias'])
gpos = map(lambda x: [ y.genomicPosition for y in x ], regions)
bounds = [ (min(x), max(x)) for x in gpos ]
assert (line['start'], line['end']) in bounds
os.remove('switches_spada.gff')
from spada.methods import get_switches, structural_analysis
from spada.io import io
import os
import pytest
scriptPath = os.path.realpath(__file__)
dataPath = os.path.dirname(scriptPath) + "/../../data/"
g = get_switches.GetSwitches(dataPath + 'annotation.pklz')
g._genes.flushSwitches()
g.run(dataPath + "switches")
def test_featureAnalysis():
s = structural_analysis.StructuralAnalysis((g._genes, g._txs))
s.featureAnalysis()
# pfams
pfam = [x for x in io.readTable("pfam_analysis.tsv")]
assert len(pfam) == 8
assert [
x for x in pfam
if x['Control_transcript'] == "ENST01.2" and x['Case_transcript'] ==
"ENST02.2" and x['What'] == "Nothing" and x['Feature'] == "D1"
]
assert [
x for x in pfam
if x['Control_transcript'] == "ENST01.2" and x['Case_transcript'] ==
"ENST02.2" and x['What'] == "Lost_in_cases" and x['Feature'] == "D1"
]