def test_sampleset_attrs_sort(self):
""" """
ssa = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor(),
attrs=(
{
'fr': 'a9'
},
{
'fr': 'a10'
},
{
'fr': 'a11'
},
{
'fr': 'a12'
},
{
'fr': 'b1'
},
),
)
idx = ssa.argsort_by_sample_id(['A10', 'A11', 'A12', 'B1', 'A9'])
ssa.sort_by_index(idx)
assert ssa.sample_id_to_index[('A', 12)] == 2
assert ssa.sample_index_to_id[0] == ('A', 10)
assert ssa.attrs[-1].attrs['fr'] == 'a9'
def read_peaks(self):
reader = sample.SampleReader(
input_type='peaks',
fname=self.peaks_fname,
)
self.samples = reader.get_sampleset(
sampleset_args={
'sample_id_proc': sampleattrs.plate_sample_id_processor(),
})
self.sample_selected = self.samples.mzs_by_sample[:,
self.samples.attrs.
sample_id_to_index[
self.sample_id]]
idx = self.sample_selected.argsort()
self.samples.sort_all(by=idx)
self.sample_selected = self.samples.mzs_by_sample[:,
self.samples.attrs.
sample_id_to_index[
self.sample_id]]
def test_sec_profile_1(self):
""" """
peakspath = settings.get('peaks_gltpd1_invitro')
secpath = settings.get('sec_gltpd1_invitro')
reader = sample.SampleReader(
input_type='peaks',
fname=peakspath,
)
samples = reader.get_sampleset(
sample_id_proc=sampleattrs.plate_sample_id_processor(), )
secprofile = sampleattrs.SECProfile(
sec_path=secpath,
samples=samples,
)
assert secprofile.numof_samples == samples.numof_samples
assert np.all(secprofile.attrs.sample_index_to_id ==
samples.attrs.sample_index_to_id)
assert id(samples) in secprofile._sample_data
assert id(secprofile) in samples._sample_data
assert secprofile.profile.max() - 143.40397368421048 < 0.0001
def test_sec_profile_2(self):
""" """
peakspath = settings.get('peaks_gltpd1_invivo')
secpath = settings.get('sec_gltpd1_invivo')
reader = sample.SampleReader(
input_type='peaks',
fname=peakspath,
)
samples = reader.get_sampleset(
sample_id_proc=sampleattrs.plate_sample_id_processor(), )
secprofile = sampleattrs.SECProfile(
sec_path=secpath,
samples=samples,
start_volume=1.2,
offsets=(0.015, 0.045),
start_col=9,
start_row='A',
length=samples.numof_samples,
)
assert secprofile.numof_samples == samples.numof_samples
assert np.all(secprofile.attrs.sample_index_to_id ==
samples.attrs.sample_index_to_id)
assert id(samples) in secprofile._sample_data
assert id(secprofile) in samples._sample_data
assert secprofile.profile015.max() - 20.92373913043478 < 0.0001
assert secprofile.profile045.argmax() == 2
assert secprofile.profile015.argmax() == 3
assert secprofile.profiles == {'profile045', 'profile015'}
def test_sampledata(self):
""" """
samples = self.samples
# repeating these as pytest makes a copy of the object
order = ['A11', 'A12', 'B1', 'B2']
samples.sort_by_sample_ids(order)
samples.sort_all(by='mzs', desc=True)
data0 = ['a', 'b', 'c', 'd']
order = ['B2', 'B1', 'A12', 'A11']
sdata = sampleattrs.SampleData(
var0=data0,
sample_ids=order,
samples=samples,
sample_id_proc=sampleattrs.plate_sample_id_processor(),
)
assert sdata.var0[0] == 'd' and sdata.var0[-1] == 'a'
assert samples.mzs_by_sample[9, 1] == 0
assert (
samples.attrs.sample_index_to_id == sdata.attrs.sample_index_to_id)
assert samples.attrs.sample_index_to_id[2] == ('B', 1)
assert samples.rts[0, 2] == 0
assert id(sdata) in samples._sample_data
assert id(samples) in sdata._sample_data
def test_sampleset_from_attrs(self):
""" """
ssa = sampleattrs.SampleSetAttrs(
sample_ids=peaks_sample_id_method,
attrs=(
{
'label': {
'sample_id': 'G2',
}
},
{
'label': {
'sample_id': 'G3',
}
},
{
'label': {
'sample_id': 'G4',
}
},
),
proc=sampleattrs.plate_sample_id_processor())
assert ssa.attrs[0].attrs['label']['sample_id'] == 'G2'
assert ssa.sample_index_to_id[-1].col == 4
assert len(ssa.sample_id_to_index) == 3
assert ('G', 2) in ssa.sample_id_to_index
def test_selection_logical_or(self):
""" """
sel0 = sampleattrs.SampleSelection(
selection=[False, True, True, False, False],
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
sample_id_proc=sampleattrs.plate_sample_id_processor())
sel1 = sampleattrs.SampleSelection(
selection=['A12'],
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
sample_id_proc=sampleattrs.plate_sample_id_processor())
orsel = sel0.logical_or(sel1)
assert np.all(
orsel.selection == np.array([False, True, True, True, False]))
def test_sample_attrs_from_string(self):
""" """
sa = sampleattrs.SampleAttrs(
sample_id=('A', 11),
proc=sampleattrs.plate_sample_id_processor(),
)
assert sa.sample_id == ('A', 11)
def test_plate_sample_id_processor(self):
""" """
sip = sampleattrs.plate_sample_id_processor()
a11_from_string = sip('A11')
a11_from_tuple = sip(('A', 11))
assert a11_from_string == ('A', 11)
assert a11_from_tuple == ('A', 11)
def test_sampleset_attrs_argsort(self):
""" """
ssa = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor())
idx = ssa.argsort_by_sample_id(['A10', 'A11', 'A12', 'B1', 'A9'])
assert np.all(idx == np.array([1, 2, 3, 4, 0]))
def test_sampleset_from_sample_ids_proc(self):
""" """
ssa = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor())
assert ssa.sample_index_to_id[-1].row == 'B'
assert ssa.sample_id_to_index[('A', 12)] == 3
assert len(ssa.sample_index_to_id) == 5
def test_selection_logical_not(self):
""" """
sel = sampleattrs.SampleSelection(
selection=[False, True, True, False, False],
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
sample_id_proc=sampleattrs.plate_sample_id_processor())
nsel = sel.logical_not()
assert np.all(
nsel.selection == np.array([True, False, False, True, True]))
def test_sampleset_attrs_sort_by_id(self):
""" """
ssa = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor(),
)
ssa.sort_by_sample_id(['A10', 'A11', 'A12', 'B1', 'A9'])
assert ssa.sample_id_to_index[('A', 12)] == 2
assert ssa.sample_index_to_id[0] == ('A', 10)
def test_sampleset_attrs_sort_by_other(self):
""" """
ssa0 = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor(),
)
ssa0.sort_by_sample_id(['A10', 'A11', 'A12', 'B1', 'A9'])
ssa1 = sampleattrs.SampleSetAttrs(
sample_ids=['A9', 'A10', 'A11', 'A12', 'B1'],
proc=sampleattrs.plate_sample_id_processor(),
)
ssa1.sort_by(ssa0)
assert np.all(ssa0.sample_index_to_id == ssa1.sample_index_to_id)
assert ssa1.sample_id_to_index[('A', 12)] == 2
assert ssa1.sample_index_to_id[0] == ('A', 10)
assert all(ssa0.sample_id_to_index[s] == ssa1.sample_id_to_index[s]
for s in ssa0.sample_index_to_id)
def test_sampleset_from_peaks(self):
""" """
peaksfile = settings.get('peaks_example')
reader = sample.SampleReader(input_type='peaks', fname=peaksfile)
samples = reader.get_sampleset(
sampleset_args={
'sample_id_proc': sampleattrs.plate_sample_id_processor(),
})
assert abs(samples.mzs_by_sample[7, 3] - 375.0018) < 0.0001
assert samples.attrs.sample_index_to_id[-1] == ('A', 12)
assert samples.attrs.attrs[0].attrs['label']['sample_id'] == ('A', 6)
def test_sample_attrs_from_attrs(self):
""" """
attrs = {
'label': {
'sample_id': ('A', 11),
}
}
sa = sampleattrs.SampleAttrs(
sample_id=peaks_sample_id_method,
attrs=attrs,
proc=sampleattrs.plate_sample_id_processor(),
)
assert sa.sample_id == ('A', 11)
def auto_inject_fixture(self):
""" """
sample_ids = ['A12', 'A11', 'B2', 'B1']
mzs = np.arange(40)
mzs.shape = (10, 4)
rts = np.arange(40)[::-1]
rts.shape = (10, 4)
self.samples = sample.SampleSet(
mzs=mzs,
rts=rts,
ionmode='pos',
sample_ids=sample_ids,
sample_id_proc=sampleattrs.plate_sample_id_processor(),
)
def test_protein_containing_samples(self):
""" """
peakspath = settings.get('peaks_gltpd1_invivo')
secpath = settings.get('sec_gltpd1_invivo')
reader = sample.SampleReader(
input_type='peaks',
fname=peakspath,
)
samples = reader.get_sampleset(
sample_id_proc=sampleattrs.plate_sample_id_processor(), )
secprofile = sampleattrs.SECProfile(
sec_path=secpath,
samples=samples,
start_volume=1.2,
offsets=(0.015, 0.045),
start_col=9,
start_row='A',
length=samples.numof_samples,
)
pcs = secprofile.protein_containing_samples()
assert np.all(
pcs.selection == np.array([False, False, True, True, False]))
pcs = secprofile.protein_containing_samples(manual=['A10', 'A11'])
assert np.all(
pcs.selection == np.array([False, True, True, False, False]))
pcs = secprofile.protein_containing_samples(exclude=['A12'])
assert np.all(
pcs.selection == np.array([False, False, True, False, False]))
def auto_inject_fixture(self):
""" """
sample_ids = ['A10', 'A11', 'A12', 'B1']
intensities = np.vstack([
[.1] * 10,
np.arange(10) * .1,
(np.arange(10) * .1)[::-1],
[.1] * 10,
])
intensities = intensities.transpose()
mzs = np.random.random(10)
self.samples = sample.SampleSet(
mzs = mzs,
intensities = intensities,
ionmode = 'pos',
sample_ids = sample_ids,
sample_id_proc = sampleattrs.plate_sample_id_processor(),
)
self.protein_samples = self.samples.get_selection(['A11', 'A12'])
from lipyd import settings
from lipyd import sample
from lipyd import sampleattrs
peaksfile = settings.get('peaks_example')
peaksfile = 'stard10_pos.csv'
reader = sample.SampleReader(
input_type = 'peaks',
fname = peaksfile
)
samples = reader.get_sampleset(
sampleset_args = {
'sample_id_proc': sampleattrs.plate_sample_id_processor(),
}
)
idx = samples.mzs_by_sample[
:,samples.attrs.sample_id_to_index[('A', 10)]
].argsort()
samples.sort_all(by = idx)
# m/z's for one sample:
samples.mzs_by_sample[:,samples.attrs.sample_id_to_index[('A', 10)]]
# intensities for one sample:
samples.intensities[:,samples.attrs.sample_id_to_index[('A', 10)]]
# RTs for one sample:
samples.rts[:,samples.attrs.sample_id_to_index[('A', 10)]]
