def test_hp_task_creation():
"test fit to hp dataframe"
task = FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "ctgc",
fit = ChiSquareFit(),
)
assert isinstance(task.fit.pop(None), ChiSquareFit)
assert set(task.fit) == {'015', *(f"GF{i}" for i in range(1, 5))}
assert all(isinstance(i, ChiSquareFit) for i in task.fit.values())
assert_equal(task.fit['GF4'].peaks, [153, 205, 407, 496, 715, 845])
assert all(isinstance(i, ChiSquareFit) for i in task.fit.values())
task = FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "ctgc",
fit = PeakGridFit(),
)
assert isinstance(task.fit.pop(None), PeakGridFit)
assert set(task.fit) == {'015', *(f"GF{i}" for i in range(1, 5))}
assert all(isinstance(i, PeakGridFit) for i in task.fit.values())
for i in PeakGridFit(), ChiSquareFit():
task = FitToHairpinTask(
sequence = "doesnotexist.fasta",
oligos = "ctgc",
fit = i
)
assert isinstance(task.fit.pop(None), type(i))
assert not task.fit
def test_rescale():
"test rescale"
rng = Range(1, 1, 1)
obj = rng.rescale("bias", 5)
assert rng is not obj
assert all(abs(5.-i) < 1e-5 for i in obj)
obj = rng.rescale("stretch", .2)
assert rng is not obj
assert all(abs(5.-i) < 1e-5 for i in obj)
rng = Range(None, 1, 1)
obj = rng.rescale("bias", 5)
assert rng is not obj
assert obj[0] is None
assert all(abs(5.-i) < 1e-5 for i in obj[1:])
obj = rng.rescale("stretch", .2)
assert rng is not obj
assert obj[0] is None
assert all(abs(5.-i) < 1e-5 for i in obj[1:])
dist = DistanceConstraint("hp", {"stretch": Range(1, 1, 1), "bias": Range(1, 1, 1)})
obj = dist.rescale(5.)
assert dist is not obj
assert obj[0] == "hp"
assert all(abs(5.-i) < 1e-5 for i in obj[1]['bias'])
assert all(abs(.2-i) < 1e-5 for i in obj[1]['stretch'])
task = FitToHairpinTask()
assert task.rescale(5.) is not task
def readconstraints(idtask: FitToHairpinTask,
idpath: Union[Path, str, None],
useparams: bool = True,
constraints: Dict[str, Range] = None) -> FitToHairpinTask:
"adds constraints to an identification task"
cstrs: Constraints = {}
idtask.constraints = cstrs
if idpath is None or not Path(idpath).exists():
return idtask
deflt = dict(FitToHairpinTask.DEFAULT_CONSTRAINTS)
deflt.update(constraints if constraints else {})
for item in readparams(cast(str, idpath)):
cstrs[item[0]] = DistanceConstraint(item[1], {})
if len(item) == 2 or not useparams:
continue
if item[2] is not None:
cstrs[item[0]].constraints['stretch'] = Range(
item[2], *deflt['stretch'][1:3])
if item[3] is not None:
cstrs[item[0]].constraints['bias'] = Range(item[3],
*deflt['bias'][1:3])
return idtask
def test_beadsplot_info_simple(diskcaching):
"test the view"
# pylint: disable=protected-access
beads, mdl = _Fig.create()
# testing for when there is nothing to plot
for cls in _PeaksPlot, _HairpinPlot:
assert (
dict(cls(beads, mdl.tasks.processors)._reset())['x_range']['factors']
== [('track1', '0')]
)
def _change(tpe, **kwa):
mdl.theme.__dict__.update(**kwa)
cls = _PeaksPlot if tpe else _HairpinPlot
return dict(cls(beads, mdl.tasks.processors)._reset())
mdl.tasks.jobs.launch(list(mdl.tasks.processors.values()))
cache = _change(True)
assert cache['x_range']['factors'] == list(zip(
repeat(''), repeat(''),
[
'0', '1', '2', '3', '4', '7', '8', '12', '13', '14', '17', '18', '23',
'24', '25', '27', '33', '34', '35', '37'
]
))
next(iter(mdl.tasks.tasks.tasks.tasks.values())).add(
FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "4mer",
),
mdl.tasks.tasks.state.processors[FitToHairpinTask]
)
mdl.tasks.jobs.launch(list(mdl.tasks.processors.values()))
cache = _change(False)
assert cache['x_range']['factors'] == [
('GF1', '', '14'), ('GF1', '', '33'), ('GF1', '', '1'), ('GF1', '', '7'),
('GF1', '', '25'), ('GF1', '', '35'), ('GF1', '', '12'), ('GF3', '', '27'),
('GF3', '', '13'), ('GF3', '', '3'), ('GF3', '', '17'), ('GF3', '', '37'),
('GF3', '', '23'), ('GF3', '', '18'), ('GF4', '', '34'), ('GF4', '', '0'),
('GF4', '', '4'), ('GF4', '', '24'), ('GF2', '', '2')
]
mdl.display.hairpins = {'015', 'GF2', 'GF3', 'GF4'}
cache = _change(False)
assert cache['x_range']['factors'] == [
('GF1', '', '14'), ('GF1', '', '33'), ('GF1', '', '1'), ('GF1', '', '7'),
('GF1', '', '25'), ('GF1', '', '35'), ('GF1', '', '12')
]
mdl.theme.sorting = {}
cache = _change(False)
assert cache['x_range']['factors'] == [
('GF1', '', '1'), ('GF1', '', '7'), ('GF1', '', '12'), ('GF1', '', '14'),
('GF1', '', '25'), ('GF1', '', '33'), ('GF1', '', '35')
]
def test_hp_dataframe(record):
"test fit to hp dataframe"
pair = next(iter(create(
TrackReaderTask(path = utpath("big_legacy")),
EventDetectionTask(),
PeakSelectorTask(),
FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "4mer",
fit = ChiSquareFit()
),
DataFrameTask(merge = True, measures = dict(
peaks = dict(missing = True, peakhfsigma = True)
)),
).run()))
assert pair.shape == (102, 29)
assert 'falseneg' in pair.peaks[1].status.unique()
assert pair.index.names == ['hpin', 'track', 'bead']
assert isinstance(pair.peaks.values[0], pd.DataFrame)
assert 'modification' in pair.columns
assert hasattr(pair, 'tasklist')
assert record["withmissing"].approx(
pair.drop(columns = ['peaks', 'cost', 'modification']).iloc[:5],
atol = 5e-4
)
assert record["peakswithmissing"].approx(
pair.peaks[1].iloc[:5], atol = 5e-4
)
pair = next(iter(create(
TrackReaderTask(path = utpath("big_legacy")),
EventDetectionTask(),
PeakSelectorTask(),
FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "4mer",
fit = ChiSquareFit()
),
DataFrameTask(merge = True),
).run()))
assert pair.shape == (102, 26)
assert pair.index.names == ['hpin', 'track', 'bead']
assert 'modification' in pair.columns
assert hasattr(pair, 'tasklist')
def fittohairpintask(seqpath: Union[Path, str],
oligos: Union[Sequence[str], str],
idpath: Union[None, Path, str] = None,
useparams: bool = True,
constraints: Dict[str, Range] = None,
**kwa) -> FitToHairpinTask:
"creates and identification task from paths"
task = FitToHairpinTask.read(seqpath, oligos, **kwa)
if len(task.fit) == 0:
raise IOError("Could not find any sequence in " + str(seqpath))
return readconstraints(task, idpath, useparams, constraints)
def addhp(server, rendered = _EVT, **kwa):
"add the hairpin"
from peakcalling.processor import FitToHairpinTask
kwa.setdefault('sequences', utpath("hairpins.fasta"))
kwa.setdefault('oligos', "kmer")
server.cmd(
lambda: server.ctrl.tasks.addtask(
next(next(server.ctrl.tasks.tasklist(...))),
FitToHairpinTask(**kwa)
),
rendered = rendered
)
def test_beadsplot_info_filter(diskcaching):
"test the view"
# pylint: disable=protected-access
beads, mdl = _Fig.create()
next(iter(mdl.tasks.tasks.tasks.tasks.values())).add(
FitToHairpinTask(
sequence = utpath("hairpins.fasta"),
oligos = "4mer",
),
mdl.tasks.tasks.state.processors[FitToHairpinTask]
)
mdl.tasks.jobs.launch(list(mdl.tasks.processors.values()))
cache = dict(_HairpinPlot(beads, mdl.tasks.processors)._reset())
arr = cache['_expdata']['data']['closest']
arr = np.unique(arr[np.isfinite(arr)])
assert_equal(
arr,
[
38., 46., 151., 157., 222., 258., 274., 294., 347., 357., 379., 393., 503.,
540., 569., 576., 631., 659., 704., 738., 754., 784., 791., 795., 800.
]
)
arr = np.unique(
next(j for i,j in cache.items() if isinstance(i, _Fig._CData))
['data']['bindingposition']
)
assert_equal(
arr,
[
38., 46., 151., 157., 222., 258., 274., 294., 347., 357., 379., 393., 503.,
540., 569., 576., 631., 659., 704., 738., 754., 784., 791., 795., 800.
]
)
mdl.display.ranges[('peaks', 'baseposition')] = Slice(100, 400)
cache = dict(_HairpinPlot(beads, mdl.tasks.processors)._reset())
arr = cache['_expdata']['data']['closest']
arr = np.unique(arr[np.isfinite(arr)])
assert_equal(arr, [151., 157., 222., 258., 274., 294., 347., 357., 379., 393.])
arr = np.unique(
next(j for i,j in cache.items() if isinstance(i, _Fig._CData))
['data']['bindingposition']
)
assert_equal(arr, [151., 157., 222., 258., 274., 294., 347., 357., 379., 393.])