def test_get_third_highest_mz(peak):
assert peak.get_third_highest_mz() == 59
assert isinstance(peak.get_third_highest_mz(), int)
assert Peak(test_float, test_float).get_third_highest_mz() is None
# with pytest.raises(AttributeError):
assert Peak(test_float).get_third_highest_mz() is None
def test_another_peak(im_i, peak):
# A different peak
scan_i = im_i.get_index_at_time(31.44 * 60.0)
ms = im_i.get_ms_at_index(scan_i)
peak2 = Peak(31.44, ms, minutes=True)
assert peak2.rt == 1886.4
assert peak2.UID == "207-68-42-1886.40"
assert peak.UID != peak2.UID
def test_UID(peak):
# Get the peak's unique ID
# Consists of the two most abundant ions and their ratio,
# and the retention time (in the format set by minutes=True or False)
assert isinstance(peak.UID, str)
assert peak.UID == "131-73-42-12.34"
assert isinstance(Peak(test_float).UID, str)
def test_ic_mass():
peak = Peak(12.34, 55)
uid = peak.UID
assert isinstance(peak.ic_mass, Number)
assert peak.ic_mass == 55
peak.ic_mass = 12
assert peak.mass_spectrum is None
assert peak.UID != uid
assert peak.ic_mass == 12
peak.ic_mass = 1234
assert peak.ic_mass == 1234
# Errors
for obj in [*test_sequences, test_string, test_dict]:
with pytest.raises(TypeError):
peak.ic_mass = obj
def test_Peak(im_i, peak):
assert isinstance(peak, Peak)
# Get the scan of a known TIC peak (at RT 31.17 minutes)
# get the index of the scan nearest to 31.17 minutes (converted to seconds)
scan_i = im_i.get_index_at_time(31.17 * 60.0)
# get the MassSpectrum Object
ms = im_i.get_ms_at_index(scan_i)
# create a Peak object
Peak(31.17)
Peak(31.17, ms, outlier=True)
Peak(31.17, ms, minutes=True)
# Errors
for obj in [test_string, *test_lists, test_dict]:
with pytest.raises(TypeError):
Peak(obj, ms, minutes=True) # type: ignore
with pytest.raises(TypeError):
Peak(test_float, obj, minutes=False) # type: ignore
Peak(test_float, test_int)
ICPeak(test_float, test_int)
Peak(test_float, test_float)
ICPeak(test_float, test_float)
def test_area(im_i, peak):
peak = copy.deepcopy(peak)
# determine and set area
area = peak_sum_area(im_i, peak)
assert isinstance(area, float)
peak.area = area
assert peak.area == area
assert isinstance(peak.area, float)
scan_i = im_i.get_index_at_time(31.17 * 60.0)
ms = im_i.get_ms_at_index(scan_i)
for obj in [test_string, test_dict, test_list_strs, test_list_ints]:
with pytest.raises(TypeError):
Peak(test_float, ms).area = obj
with pytest.raises(ValueError):
Peak(test_float, ms).area = -1
def peak_top_ion_areas(
im: IntensityMatrix,
peak: Peak,
n_top_ions: int = 5,
max_bound: int = 0,
) -> Dict[float, float]:
"""
Calculate and return the ion areas of the five most abundant ions in the peak.
:param im: The originating IntensityMatrix object.
:param peak:
:param n_top_ions: Number of top ions to return areas for.
:param max_bound: Optional value to limit size of detected bound.
:return: Dictionary of ``ion : ion_area pairs``.
:authors: Sean O'Callaghan, Dominic Davis-Foster (type assertions)
"""
if not isinstance(im, IntensityMatrix):
raise TypeError("'im' must be an IntensityMatrix object")
if not isinstance(peak, Peak):
raise TypeError("'peak' must be a Peak object")
if not isinstance(n_top_ions, int):
raise TypeError("'n_top_ions' must be an integer")
if not isinstance(max_bound, int):
raise TypeError("'max_bound' must be an integer")
# ms = peak.mass_spectrum
rt = peak.rt
apex = im.get_index_at_time(rt)
ion_areas = {} # Dictionary to store ion:ion_area pairs
top_ions = peak.top_ions(n_top_ions)
# print(top_ions)
for ion in top_ions:
ion_chrom = im.get_ic_at_mass(ion)
# need ia as a list not numpy array so use .tolist()
ia = ion_chrom.intensity_array.tolist()
area, left, right, l_share, r_share = ion_area(ia, apex, max_bound)
# need actual mass for single ion areas
ion_areas[ion] = area
return ion_areas
def test_null_mass(peak):
peak = copy.deepcopy(peak)
uid = peak.UID
peak.null_mass(73)
peak.null_mass(147.0)
index_73 = peak.mass_spectrum.mass_list.index(73)
assert peak.mass_spectrum.mass_spec[index_73] == 0
index_147 = peak.mass_spectrum.mass_list.index(147)
assert peak.mass_spectrum.mass_spec[index_147] == 0
assert peak.UID != uid
# Errors
with pytest.raises(ValueError, match="Mass spectrum is unset."):
Peak(test_float).null_mass(1)
for obj in [test_string, *test_lists, test_dict]:
with pytest.raises(TypeError):
Peak(test_float, peak.mass_spectrum).null_mass(obj) # type: ignore
with pytest.raises(IndexError):
Peak(test_float, peak.mass_spectrum).null_mass(1)
with pytest.raises(IndexError):
Peak(test_float, peak.mass_spectrum).null_mass(10000)
def test_mass_spectrum(peak, im_i):
scan_i = im_i.get_index_at_time(31.17 * 60.0)
ms = im_i.get_ms_at_index(scan_i)
assert isinstance(peak.mass_spectrum, MassSpectrum)
assert peak.mass_spectrum == ms
assert peak.ic_mass is None
peak = Peak(test_float)
assert peak.mass_spectrum is None
peak.mass_spectrum = ms
assert peak.mass_spectrum == ms
assert peak.ic_mass is None
peak = Peak(test_float)
assert peak.mass_spectrum is None
peak.mass_spectrum = ms
assert isinstance(peak.mass_spectrum, MassSpectrum)
assert isinstance(peak.mass_spectrum.mass_spec, list)
for obj in [test_string, *test_numbers, test_dict, *test_lists]:
with pytest.raises(TypeError):
peak.mass_spectrum = obj
def composite_peak(peak_list: List, ignore_outliers: bool = False) -> Peak:
"""
Create a peak that consists of a composite spectrum from all spectra in the list of peaks.
:param peak_list: A list of peak objects
:type peak_list: list
:param ignore_outliers:
:type ignore_outliers: bool, optional
:return: The composite peak
:type: pyms.Peak.Class.Peak
:author: Andrew Isaac
:author: Dominic Davis-Foster (type assertions)
"""
if not is_peak_list(peak_list):
raise TypeError("'peak_list' must be a list of Peak objects")
first = True
count = 0
avg_rt = 0
# new_ms = None
# DK: first mark peaks in the list that are outliers by RT, but only if there are more than 3 peaks in the list
if ignore_outliers:
rts = []
if len(peak_list) > 3:
for peak in peak_list:
rts.append(peak.rt)
is_outlier = median_outliers(rts)
for i, val in enumerate(is_outlier):
if val:
peak_list[i].isoutlier = True
# DK: the average RT and average mass spec for the compound peak is now calculated from peaks that are NOT outliers.
# This should improve the ability to order peaks and figure out badly aligned entries
for peak in peak_list:
if peak is not None and ((ignore_outliers and not peak.is_outlier)
or not ignore_outliers):
ms = peak.mass_spectrum
spec = numpy.array(ms.mass_spec, dtype='d')
if first:
avg_spec = numpy.zeros(len(ms.mass_spec), dtype='d')
mass_list = ms.mass_list
first = False
# scale all intensities to [0,100]
max_spec = max(spec) / 100.0
if max_spec > 0:
spec = spec / max_spec
else:
spec = spec * 0
avg_rt += peak.rt
avg_spec += spec
count += 1
if count > 0:
avg_rt = avg_rt / count
avg_spec = avg_spec / count
new_ms = MassSpectrum(mass_list, avg_spec)
return Peak(avg_rt, new_ms)
else:
return None
def fill_peaks(data, peak_list: List, D: float, minutes: bool = False) -> Peak:
"""
Gets the best matching Retention Time and spectra from 'data' for each peak
in the peak list.
:param data: A data IntensityMatrix that has the same mass range as the
peaks in the peak list
:type data: pyms.IntensityMatrix.IntensityMatrix
:param peak_list: A list of peak objects
:type peak_list: list
:param D: Peak width standard deviation in seconds.
Determines search window width.
:type D: float
:param minutes: Return retention time as minutes
:type minutes: bool, optional
:return: List of Peak Objects
:type: list of :class:`pyms.Peak.Class.Peak`
:author: Andrew Isaac
:author: Dominic Davis-Foster (type assertions)
"""
if not is_peak_list(peak_list):
raise TypeError("'peak_list' must be a list of Peak objects")
if not isinstance(D, float):
raise TypeError("'D' must be a float")
# Test for best match in range where RT weight is greater than _TOL
_TOL = 0.001
cutoff = D * math.sqrt(-2.0 * math.log(_TOL))
# Penalise for neighboring peaks
# reweight so RT weight at nearest peak is _PEN
_PEN = 0.5
datamat = data.intensity_array
mass_list = data.mass_list
datatimes = data.time_list
minrt = min(datatimes)
maxrt = max(datatimes)
rtl = 0
rtr = 0
new_peak_list = []
for ii in range(len(peak_list)):
spec = peak_list[ii].mass_spectrum.mass_spec
spec = numpy.array(spec, dtype='d')
rt = peak_list[ii].rt
sum_spec_squared = numpy.sum(spec**2, axis=0)
# get neighbour RT's
if ii > 0:
rtl = peak_list[ii - 1].rt
if ii < len(peak_list) - 1:
rtr = peak_list[ii + 1].rt
# adjust weighting for neighbours
rtclose = min(abs(rt - rtl), abs(rt - rtr))
Dclose = rtclose / math.sqrt(-2.0 * math.log(_PEN))
if Dclose > 0:
Dclose = min(D, Dclose)
else:
Dclose = D
# Get bounds
rtlow = rt - cutoff
if rtlow < minrt:
rtlow = minrt
lowii = data.get_index_at_time(rtlow)
rtup = rt + cutoff
if rtup > maxrt:
rtup = maxrt
upii = data.get_index_at_time(rtup)
# Get sub matrix of scans in bounds
submat = datamat[lowii:upii + 1]
submat = numpy.array(submat, dtype='d')
subrts = datatimes[lowii:upii + 1]
subrts = numpy.array(subrts, dtype='d')
sum_summat_squared = numpy.sum(submat**2, axis=1)
# transpose spec (as matrix) for dot product
spec = numpy.transpose([spec])
# dot product on rows
toparr = numpy.dot(submat, spec)
botarr = numpy.sqrt(sum_spec_squared * sum_summat_squared)
# convert back to 1-D array
toparr = toparr.ravel()
# scaled dot product of each scan
cosarr = toparr / botarr
# RT weight of each scan
rtimearr = numpy.exp(-((subrts - rt) / float(Dclose))**2 / 2.0)
# weighted scores
scorearr = cosarr * rtimearr
# index of best score
best_ii = scorearr.argmax()
# Add new peak
bestrt = subrts[best_ii]
bestspec = submat[best_ii].tolist()
ms = MassSpectrum(mass_list, bestspec)
new_peak_list.append(Peak(bestrt, ms, minutes))
return new_peak_list
def test_bounds(peak):
peak = copy.copy(peak)
# Setter
peak.bounds = (11, 12, 13)
for obj in [
test_string, *test_numbers, test_dict, ['a', 'b', 'c'], test_tuple
]:
with pytest.raises(TypeError):
peak.bounds = obj
for obj in [*test_lists, (1, 2), [1, 2, 3, 4]]:
with pytest.raises(ValueError,
match="'Peak.bounds' must have exactly 3 elements"):
peak.bounds = obj
# Getter
assert peak.bounds == (11, 12, 13)
assert isinstance(peak.bounds, tuple)
peak2 = Peak(test_float)
peak2.bounds = [11, 12, 13] # type: ignore
assert peak2.bounds == (11, 12, 13)
assert isinstance(peak2.bounds, tuple)
# set_bounds
peak3 = Peak(test_float)
peak3.set_bounds(11, 12, 13)
assert peak3.bounds == (11, 12, 13)
assert isinstance(peak3.bounds, tuple)
for obj in [*test_sequences, test_string, test_dict, test_float]:
print(obj)
with pytest.raises(TypeError):
peak3.set_bounds(obj, 12, 13) # type: ignore
with pytest.raises(TypeError):
peak3.set_bounds(11, obj, 13) # type: ignore
with pytest.raises(TypeError):
peak3.set_bounds(11, 12, obj) # type: ignore
def test_equality(peak):
assert peak == Peak(peak.rt, peak.mass_spectrum)
assert peak != Peak(50, peak.mass_spectrum)
def test_outlier(peak):
assert isinstance(peak.is_outlier, bool)
assert peak.is_outlier is False
assert Peak(12.34, outlier=True).is_outlier is True
def test_get_third_highest_mz(peak):
assert peak.get_third_highest_mz() == 59
assert isinstance(peak.get_third_highest_mz(), int)
with pytest.raises(ValueError, match="Mass spectrum is unset."):
Peak(test_float).get_third_highest_mz()
def test_bounds(peak):
peak = copy.copy(peak)
# Setter
peak.bounds = (11, 12, 13)
for obj in [
test_string, *test_numbers, test_dict, ["a", "b", "c"], test_tuple
]:
with pytest.raises(TypeError):
peak.bounds = obj
for obj in [*test_lists, (1, 2), [1, 2, 3, 4]]:
with pytest.raises(ValueError):
peak.bounds = obj
# Getter
assert peak.bounds == (11, 12, 13)
assert isinstance(peak.bounds, tuple)
peak2 = Peak(test_float)
peak2.bounds = [11, 12, 13]
assert peak2.bounds == [11, 12, 13]
assert isinstance(peak2.bounds, list)
# set_bounds
peak3 = Peak(test_float)
peak3.set_bounds(11, 12, 13)
assert peak3.bounds == (11, 12, 13)
assert isinstance(peak3.bounds, tuple)
for obj in [*test_sequences, test_string, test_dict, test_float]:
with pytest.raises(TypeError):
print(obj)
peak3.set_bounds(obj, 12, 13)
with pytest.raises(TypeError):
peak3.set_bounds(11, obj, 13)
with pytest.raises(TypeError):
peak3.set_bounds(11, 12, obj)