def setUp(self):
self.motif = motif.Motif("O..x.-+")
def setUp(self):
self.motif = motif.Motif('O..x.-+')
def test_filter(self):
for data in self.data.values():
for f in [
{
"ambiguous": True
},
{
"ambiguous": False
},
{
"p": .1
},
{
"q": .1
},
{
"fold": 1.5
},
{
"fold": 1 / 1.5
},
{
"asym_fold": 1.5
},
{
"asym_fold": 1 / 1.5
},
{
"sequence": "AVDSLVPIGR"
},
{
"sequence": ["AVDSLVPIGR"]
},
{
"protein": "Pkm"
},
{
"protein": ["Pkm"]
},
{
"ion_score": 10
},
{
"isolation": 15
},
{
"fn": lambda x: len(x["Sequence"]) > 5
},
{
"series":
data["Isolation Interference"] < data["Ion Score"]
},
{
"missed_cleavage": 0
},
{
"median_quant": 10000
},
{
"only_validated": False
},
{
"mod": "Y"
},
{
"mod": "Phospho"
},
{
"mod": [(None, "Phospho")]
},
{
"p": .1,
"inverse": True
},
{
"motif": motif.Motif(".......xP......")
},
{
"confidence": "Low"
},
{
"confidence": "Medium"
},
{
"confidence": "High"
},
{
"group_a": "CK-p25 Hip",
"group_b": "CK Hip"
},
]:
data.filter(f)
def setUp(self):
self.foreground = [
i.strip()
for i in FOREGROUND.split('\n')
if i.strip()
]
self.background = [
i.strip()
for i in BACKGROUND.split('\n')
if i.strip()
]
self.output = []
for line in OUTPUT.split('\n'):
line = line.strip()
if not line:
continue
tokens = line.split('|')
m = motif.Motif(tokens[1].strip())
fore_hits = int(tokens[2].split('/')[0])
fore_size = int(tokens[2].split('/')[1])
back_hits = int(tokens[3].split('/')[0])
back_size = int(tokens[3].split('/')[1])
p_val = float(tokens[4])
self.output.append(
(
m,
fore_hits, fore_size,
back_hits, back_size,
p_val,
)
)
self.output = pd.DataFrame(
data=self.output,
columns=[
'Motif',
'Foreground Hits',
'Foreground Size',
'Background Hits',
'Background Size',
'p-value',
],
)
# Re-sort as the p-values on Brian's tables are truncated a bit short.
self.output['sort-p-value'] = pd.Series(
[
motif._motif_sig(
row['Foreground Hits'],
row['Foreground Size'],
row['Background Hits'],
row['Background Size'],
)
for _, row in self.output.iterrows()
],
index=self.output.index,
)
self.output.sort_values(by=['sort-p-value', 'Motif'], inplace=True)
self.output.reset_index(drop=True)
def test_filter(self):
for data in self.data.values():
for f in [
{
'ambiguous': True
},
{
'ambiguous': False
},
{
'p': .1
},
{
'q': .1
},
{
'fold': 1.5
},
{
'fold': 1 / 1.5
},
{
'asym_fold': 1.5
},
{
'asym_fold': 1 / 1.5
},
{
'sequence': 'AVDSLVPIGR'
},
{
'sequence': ['AVDSLVPIGR']
},
{
'protein': 'Pkm'
},
{
'protein': ['Pkm']
},
{
'ion_score': 10
},
{
'isolation': 15
},
{
'fn': lambda x: len(x['Sequence']) > 5
},
{
'series':
data['Isolation Interference'] < data['Ion Score']
},
{
'missed_cleavage': 0
},
{
'median_quant': 10000
},
{
'only_validated': False
},
{
'mod': 'Y'
},
{
'mod': 'Phospho'
},
{
'mod': [(None, 'Phospho')]
},
{
'p': .1,
'inverse': True
},
{
'motif': motif.Motif('.......xP......')
},
{
'confidence': 'Low'
},
{
'confidence': 'Medium'
},
{
'confidence': 'High'
},
{
'group_a': 'CK-p25 Hip',
'group_b': 'CK Hip'
},
]:
data.filter(f)