def cal_nnls(LibIntensity, MS2Intensity, penalty):
RowIndex = list(range(len(LibIntensity) + 1))
ColIndex = [0] * (len(LibIntensity) + 1)
LibIntensity.append(penalty)
MS2Intensity.append(0)
MS2Intensity = np.array(MS2Intensity)
LibraryVector = sparse.coo_matrix((LibIntensity, (RowIndex, ColIndex)))
LibraryCoeffs = sparse_nnls.lsqnonneg(LibraryVector, MS2Intensity,
{'show_progress': False})
LibraryCoeffs = LibraryCoeffs['x']
LibraryCoeffs = LibraryCoeffs[0]
return LibraryCoeffs
def RegressSpectraOntoLibrary(DIASpectraIterator, Library, tol,
maxWindowOffset):
RefSpectraLibrary = Library.value
for DIASpectrum in DIASpectraIterator:
precMZ = float(DIASpectrum[1])
precRT = float(DIASpectrum[2]) #MS2 scan retention time, in minutes
index = DIASpectrum[3]
windowWidth = DIASpectrum[4]
DIASpectrum = np.array(DIASpectrum[0])
LibraryCoeffs = []
if len(DIASpectrum.shape) == 2:
if windowWidth > 0:
CandidateRefSpectraLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if abs(float(spectrum['PrecursorMZ']) -
precMZ) < windowWidth / 2
]
MassWindowCandidates = [
key for key, spectrum in RefSpectraLibrary.iteritems()
if abs(float(spectrum['PrecursorMZ']) -
precMZ) < windowWidth / 2
]
else:
CandidateRefSpectraLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if float(spectrum['PrecursorMZ']) > precMZ -
maxWindowOffset / 2
]
MassWindowCandidates = [
key for key, spectrum in RefSpectraLibrary.iteritems()
if float(spectrum['PrecursorMZ']) > precMZ -
maxWindowOffset / 2
]
#MERGING OF POINTS IN ACQUIRED SPECTRUM WITH NEARBY M/Z COORDINATES
MergedDIASpecCoordIndices = np.searchsorted(
DIASpectrum[:, 0] + tol * DIASpectrum[:, 0], DIASpectrum[:, 0])
MergedDIASpecCoords = DIASpectrum[
np.unique(MergedDIASpecCoordIndices), 0]
MergedDIASpecIntensities = [
np.mean(
DIASpectrum[np.where(MergedDIASpecCoordIndices == i)[0],
1])
for i in np.unique(MergedDIASpecCoordIndices)
]
DIASpectrum = np.array(
(MergedDIASpecCoords, MergedDIASpecIntensities)).transpose()
#FILTER LIBRARY SPECTRA BY THE CONDITION THAT SOME NUMBER OF THEIR 10 MOST INTENSE PEAKS BELONG TO THE DIA SPECTRUM
CentroidBreaks = np.concatenate(
(DIASpectrum[:, 0] - tol * DIASpectrum[:, 0],
DIASpectrum[:, 0] + tol * DIASpectrum[:, 0]))
CentroidBreaks = np.sort(CentroidBreaks)
LocateReferenceCoordsInDIA = [
np.searchsorted(CentroidBreaks, M[:, 0])
for M in CandidateRefSpectraLibrary
]
TopTenPeaksCoordsInDIA = [
np.searchsorted(
CentroidBreaks,
M[np.argsort(-M[:, 1])[0:min(10, M.shape[0])], 0])
for M in CandidateRefSpectraLibrary
]
ReferencePeaksInDIA = [
i for i in range(len(MassWindowCandidates))
if len([a
for a in TopTenPeaksCoordsInDIA[i] if a % 2 == 1]) > 5
] #min(3,CandidateRefSpectraLibrary[i].shape[0])]
ProportionOfReferencePeaksInDIA = [
len([a for a in TopTenPeaksCoordsInDIA[i] if a % 2 == 1]) /
CandidateRefSpectraLibrary[i].shape[0]
for i in range(len(MassWindowCandidates))
]
RefPeptideCandidatesLocations = [
LocateReferenceCoordsInDIA[i] for i in ReferencePeaksInDIA
]
RefPeptideCandidateList = [
CandidateRefSpectraLibrary[i] for i in ReferencePeaksInDIA
]
RefPeptideCandidates = [
MassWindowCandidates[i] for i in ReferencePeaksInDIA
]
NormalizedRefPeptideCandidateList = [
M[:, 1] / sum(M[:, 1]) for M in RefPeptideCandidateList
]
RefSpectraLibrarySparseRowIndices = (np.array([
i for v in RefPeptideCandidatesLocations
for i in v if i % 2 == 1
]) + 1) / 2
RefSpectraLibrarySparseRowIndices = RefSpectraLibrarySparseRowIndices - 1 #Respect the 0-indexing
RefSpectraLibrarySparseColumnIndices = np.array([
i for j in range(len(RefPeptideCandidates))
for i in [j] * len([
k for k in RefPeptideCandidatesLocations[j] if k % 2 == 1
])
])
RefSpectraLibrarySparseMatrixEntries = np.array([
NormalizedRefPeptideCandidateList[k][i]
for k in range(len(NormalizedRefPeptideCandidateList))
for i in range(len(NormalizedRefPeptideCandidateList[k]))
if RefPeptideCandidatesLocations[k][i] % 2 == 1
])
if (len(RefSpectraLibrarySparseRowIndices) > 0
and len(RefSpectraLibrarySparseColumnIndices) > 0
and len(RefSpectraLibrarySparseMatrixEntries) > 0):
UniqueRowIndices = [
i for i in set(RefSpectraLibrarySparseRowIndices)
]
UniqueRowIndices.sort()
DIASpectrumIntensities = DIASpectrum[
UniqueRowIndices,
1] #Project the spectrum to those m/z bins at which at least one column of the coefficient matrix has a nonzero entry
DIASpectrumIntensities = np.append(DIASpectrumIntensities, [
0
]) #Add a zero to the end of the DIA data vector to penalize
#peaks of library spectra not present in the DIA spectrum
#AUGMENT THE LIBRARY MATRIX WITH TOTAL ION INTENSITIES OF PEAKS OF LIBRARY SPECTRA THAT DON'T CORRESPOND TO PEAKS IN DIA SPECTRUM
ReferencePeaksNotInDIA = np.array([
k for v in RefPeptideCandidatesLocations
for k in range(len(v)) if v[k] % 2 == 0
])
SparseColumnIndicesForPeaksNotInDIA = np.arange(
len(RefPeptideCandidates))
NumRowsOfLibraryMatrix = max(UniqueRowIndices)
SparseRowIndicesForPeaksNotInDIA = [
NumRowsOfLibraryMatrix + 1
] * len(SparseColumnIndicesForPeaksNotInDIA)
#Duplicate (i,j) entries are summed together, yielding total ion intensities
SparseMatrixEntriesForPeaksNotInDIA = np.array([
np.sum([
NormalizedRefPeptideCandidateList[j][k] for k in range(
len(NormalizedRefPeptideCandidateList[j]))
if RefPeptideCandidatesLocations[j][k] % 2 == 0
]) for j in range(len(NormalizedRefPeptideCandidateList))
])
SparseRowIndices = np.append(RefSpectraLibrarySparseRowIndices,
SparseRowIndicesForPeaksNotInDIA)
SparseColumnIndices = np.append(
RefSpectraLibrarySparseColumnIndices,
SparseColumnIndicesForPeaksNotInDIA)
SparseMatrixEntries = np.append(
RefSpectraLibrarySparseMatrixEntries,
SparseMatrixEntriesForPeaksNotInDIA)
SparseRowIndices = stats.rankdata(
SparseRowIndices, method='dense'
).astype(
int
) - 1 #Renumber the row indices according to the projected spectrum,
#respecting the 0-indexing
LibrarySparseMatrix = sparse.coo_matrix(
(SparseMatrixEntries, (SparseRowIndices,
SparseColumnIndices)))
LibraryCoeffs = sparse_nnls.lsqnonneg(LibrarySparseMatrix,
DIASpectrumIntensities,
{'show_progress': False})
LibraryCoeffs = LibraryCoeffs['x']
NonzeroCoeffs = [c for c in LibraryCoeffs if c != 0]
NonzeroCoeffsAboveThreshold = NonzeroCoeffs
Output = [[0, index, 0, 0, 0, 0]]
if len(NonzeroCoeffs) > 0:
RefSpectraIDs = [
RefPeptideCandidates[j]
for j in range(len(RefPeptideCandidates))
if LibraryCoeffs[j] != 0
]
Output = [[
NonzeroCoeffsAboveThreshold[i], index, RefSpectraIDs[i][0],
RefSpectraIDs[i][1], precMZ, precRT
] for i in range(len(NonzeroCoeffsAboveThreshold))]
yield Output
def RegressSpectraOntoLibraryWithDecoys(DIASpectraIterator, Library, tol,
maxWindowOffset):
RefSpectraLibrary = Library.value
for DIASpectrum in DIASpectraIterator:
precMZ = float(DIASpectrum[1])
precRT = float(DIASpectrum[2]) #MS2 scan retention time, in minutes
index = DIASpectrum[3]
windowWidth = DIASpectrum[4]
DIASpectrum = np.array(DIASpectrum[0])
LibraryCoeffs = []
if len(DIASpectrum.shape) == 2:
if windowWidth > 0:
CandidateRefSpectraLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if abs(float(spectrum['PrecursorMZ']) -
precMZ) < windowWidth / 2
]
MassWindowCandidates = [
key for key, spectrum in RefSpectraLibrary.iteritems()
if abs(float(spectrum['PrecursorMZ']) -
precMZ) < windowWidth / 2
]
CandidateDecoyLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if windowWidth /
2 <= abs(float(spectrum['PrecursorMZ']) -
precMZ) <= windowWidth
]
MassWindowDecoyCandidates = [
("DECOY_" + key[0], key[1])
for key, spectrum in RefSpectraLibrary.iteritems()
if windowWidth /
2 <= abs(float(spectrum['PrecursorMZ']) -
precMZ) <= windowWidth
]
else:
CandidateRefSpectraLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if float(spectrum['PrecursorMZ']) > precMZ -
maxWindowOffset / 2
]
MassWindowCandidates = [
key for key, spectrum in RefSpectraLibrary.iteritems()
if float(spectrum['PrecursorMZ']) > precMZ -
maxWindowOffset / 2
]
CandidateDecoyLibrary = [
spectrum['Spectrum']
for key, spectrum in RefSpectraLibrary.iteritems()
if precMZ - maxWindowOffset <= float(
spectrum['PrecursorMZ']) <= precMZ -
maxWindowOffset / 2
]
MassWindowDecoyCandidates = [
("DECOY_" + key[0], key[1])
for key, spectrum in RefSpectraLibrary.iteritems()
if precMZ - maxWindowOffset <= float(
spectrum['PrecursorMZ']) <= precMZ -
maxWindowOffset / 2
]
#FILTER LIBRARY SPECTRA BY THE CONDITION THAT SOME NUMBER OF THEIR 10 MOST INTENSE PEAKS BELONG TO THE DIA SPECTRUM
CentroidBreaks = np.concatenate(
(DIASpectrum[:, 0] - tol * DIASpectrum[:, 0],
DIASpectrum[:, 0] + tol * DIASpectrum[:, 0]))
CentroidBreaks.sort()
LocateReferenceCoordsInDIA = [
np.searchsorted(CentroidBreaks, M[:, 0])
for M in CandidateRefSpectraLibrary
]
#Hard cutoff - at least 5 of the 10 most intense peaks (or all peaks if there are fewer than 3) of reference spectrum must appear in acquired spectrum
TopTenPeaksCoordsInDIA = [
np.searchsorted(
CentroidBreaks,
M[np.argsort(-M[:, 1])[0:min(10, M.shape[0])], 0])
for M in CandidateRefSpectraLibrary
]
ReferencePeaksInDIA = [
i for i in range(len(MassWindowCandidates))
if len([a
for a in TopTenPeaksCoordsInDIA[i] if a % 2 == 1]) > 5
] #min(3,CandidateRefSpectraLibrary[i].shape[0])]
#SHIFT ALL FRAGMENT ION PEAKS OF ALL DECOY SPECTRA BY 20 M/Z TO ENSURE DISSIMILARITY FROM REAL SPECTRA
LocateDecoyCoordsInDIA = [
np.searchsorted(CentroidBreaks, M[:, 0] + 20)
for M in CandidateDecoyLibrary
]
TopTenPeaksCoordsInDIA = [
np.searchsorted(
CentroidBreaks,
M[np.argsort(-M[:, 1])[0:min(10, M.shape[0])], 0] + 20)
for M in CandidateDecoyLibrary
]
DecoyPeaksInDIA = [
i for i in range(len(MassWindowDecoyCandidates))
if len([a
for a in TopTenPeaksCoordsInDIA[i] if a % 2 == 1]) > 5
] #min(3,CandidateRefSpectraLibrary[i].shape[0])]
RefPeptideCandidatesLocations = [
LocateReferenceCoordsInDIA[i] for i in ReferencePeaksInDIA
]
RefPeptideCandidateList = [
CandidateRefSpectraLibrary[i] for i in ReferencePeaksInDIA
]
RefPeptideCandidates = [
MassWindowCandidates[i] for i in ReferencePeaksInDIA
]
NormalizedRefPeptideCandidateList = [
M[:, 1] / sum(M[:, 1]) for M in RefPeptideCandidateList
]
DecoyCandidatesLocations = [
LocateDecoyCoordsInDIA[i] for i in DecoyPeaksInDIA
]
DecoyCandidateList = [
CandidateDecoyLibrary[i] for i in DecoyPeaksInDIA
]
DecoyCandidates = [
MassWindowDecoyCandidates[i] for i in DecoyPeaksInDIA
]
NormalizedDecoyCandidateList = [
M[:, 1] / sum(M[:, 1]) for M in DecoyCandidateList
]
RefSpectraLibrarySparseRowIndices = (np.array([
i for v in RefPeptideCandidatesLocations
for i in v if i % 2 == 1
]) + 1) / 2
RefSpectraLibrarySparseRowIndices = RefSpectraLibrarySparseRowIndices - 1 #Respect the 0-indexing
RefSpectraLibrarySparseColumnIndices = np.array([
i for j in range(len(RefPeptideCandidates))
for i in [j] * len([
k for k in RefPeptideCandidatesLocations[j] if k % 2 == 1
])
])
RefSpectraLibrarySparseMatrixEntries = np.array([
NormalizedRefPeptideCandidateList[k][i]
for k in range(len(NormalizedRefPeptideCandidateList))
for i in range(len(NormalizedRefPeptideCandidateList[k]))
if RefPeptideCandidatesLocations[k][i] % 2 == 1
])
if (len(RefSpectraLibrarySparseRowIndices) > 0
and len(RefSpectraLibrarySparseColumnIndices) > 0
and len(RefSpectraLibrarySparseMatrixEntries) > 0):
DecoyLibrarySparseRowIndices = (np.array([
i for v in DecoyCandidatesLocations
for i in v if i % 2 == 1
]) + 1) / 2
DecoyLibrarySparseRowIndices = DecoyLibrarySparseRowIndices - 1 #Respect the 0-indexing
DecoyLibrarySparseColumnIndices = max(
RefSpectraLibrarySparseColumnIndices
) + 1 + np.array([
i for j in range(len(DecoyCandidates)) for i in [j] *
len([k for k in DecoyCandidatesLocations[j] if k % 2 == 1])
])
DecoyLibrarySparseMatrixEntries = np.array([
NormalizedDecoyCandidateList[k][i]
for k in range(len(NormalizedDecoyCandidateList))
for i in range(len(DecoyCandidatesLocations[k]))
if DecoyCandidatesLocations[k][i] % 2 == 1
])
UniqueRowIndices = np.unique(
np.concatenate((RefSpectraLibrarySparseRowIndices,
DecoyLibrarySparseRowIndices)))
UniqueRowIndices = np.array(np.sort(UniqueRowIndices),
dtype=int)
DIASpectrumIntensities = DIASpectrum[
UniqueRowIndices,
1] #Project the spectrum to those m/z bins at which at least one column of the coefficient matrix has a nonzero entry
DIASpectrumIntensities = np.append(DIASpectrumIntensities, [
0
]) #Add a zero to the end of the DIA data vector to penalize
#peaks of library spectra not present in the DIA spectrum
#AUGMENT THE LIBRARY MATRIX WITH TOTAL ION INTENSITIES OF PEAKS OF LIBRARY SPECTRA THAT DON'T CORRESPOND TO PEAKS IN DIA SPECTRUM
ReferencePeaksNotInDIA = np.array([
k for v in RefPeptideCandidatesLocations
for k in range(len(v)) if v[k] % 2 == 0
])
SparseColumnIndicesForPeaksNotInDIA = np.arange(
len(RefPeptideCandidates))
NumRowsOfLibraryMatrix = max(UniqueRowIndices)
SparseRowIndicesForPeaksNotInDIA = [
NumRowsOfLibraryMatrix + 1
] * len(SparseColumnIndicesForPeaksNotInDIA)
#Duplicate (i,j) entries are summed together, yielding total ion intensities
SparseMatrixEntriesForPeaksNotInDIA = np.array([
np.sum([
NormalizedRefPeptideCandidateList[j][k] for k in range(
len(NormalizedRefPeptideCandidateList[j]))
if RefPeptideCandidatesLocations[j][k] % 2 == 0
]) for j in range(len(NormalizedRefPeptideCandidateList))
])
RefSpectraLibrarySparseRowIndices = np.append(
RefSpectraLibrarySparseRowIndices,
SparseRowIndicesForPeaksNotInDIA)
RefSpectraLibrarySparseColumnIndices = np.append(
RefSpectraLibrarySparseColumnIndices,
SparseColumnIndicesForPeaksNotInDIA)
RefSpectraLibrarySparseMatrixEntries = np.append(
RefSpectraLibrarySparseMatrixEntries,
SparseMatrixEntriesForPeaksNotInDIA)
DecoyPeaksNotInDIA = np.array([
k for v in DecoyCandidatesLocations for k in range(len(v))
if v[k] % 2 == 0
])
SparseColumnIndicesForDecoyPeaksNotInDIA = np.arange(
len(DecoyCandidates))
NumRowsOfLibraryMatrix = max(UniqueRowIndices)
SparseRowIndicesForDecoyPeaksNotInDIA = [
NumRowsOfLibraryMatrix + 1
] * len(SparseColumnIndicesForDecoyPeaksNotInDIA)
#Duplicate (i,j) entries are summed together, yielding total ion intensities
SparseMatrixEntriesForDecoyPeaksNotInDIA = np.array([
np.sum([
NormalizedDecoyCandidateList[j][k]
for k in range(len(NormalizedDecoyCandidateList[j]))
if DecoyCandidatesLocations[j][k] % 2 == 0
]) for j in range(len(NormalizedDecoyCandidateList))
])
DecoyLibrarySparseRowIndices = np.append(
DecoyLibrarySparseRowIndices,
SparseRowIndicesForDecoyPeaksNotInDIA)
DecoyLibrarySparseColumnIndices = np.append(
DecoyLibrarySparseColumnIndices,
max(RefSpectraLibrarySparseColumnIndices) +
SparseColumnIndicesForDecoyPeaksNotInDIA + 1)
DecoyLibrarySparseMatrixEntries = np.append(
DecoyLibrarySparseMatrixEntries,
SparseMatrixEntriesForDecoyPeaksNotInDIA)
SparseRowIndices = np.concatenate(
(RefSpectraLibrarySparseRowIndices,
DecoyLibrarySparseRowIndices))
SparseColumnIndices = np.concatenate(
(RefSpectraLibrarySparseColumnIndices,
DecoyLibrarySparseColumnIndices))
SparseMatrixEntries = np.concatenate(
(RefSpectraLibrarySparseMatrixEntries,
DecoyLibrarySparseMatrixEntries))
SparseRowIndices = stats.rankdata(
SparseRowIndices, method='dense'
).astype(
int
) - 1 #Renumber the row indices according to the projected spectrum,
#respecting the 0-indexing
LibrarySparseMatrix = sparse.coo_matrix(
(SparseMatrixEntries, (SparseRowIndices,
SparseColumnIndices)))
LibraryCoeffs = sparse_nnls.lsqnonneg(LibrarySparseMatrix,
DIASpectrumIntensities,
{'show_progress': False})
LibraryCoeffs = LibraryCoeffs['x']
NonzeroCoeffs = [c for c in LibraryCoeffs if c != 0]
NonzeroCoeffsAboveThreshold = NonzeroCoeffs
Output = [[0, index, 0, 0, 0, 0]]
if len(NonzeroCoeffs) > 0:
RefSpectraIDs = [
RefPeptideCandidates[j]
for j in range(len(RefPeptideCandidates))
if LibraryCoeffs[j] != 0
]
DecoyIDs = [
DecoyCandidates[j] for j in range(len(DecoyCandidates))
if LibraryCoeffs[max(RefSpectraLibrarySparseColumnIndices) +
1 + j] != 0
]
RefSpectraIDs = RefSpectraIDs + DecoyIDs
Output = [[
NonzeroCoeffsAboveThreshold[i], index, RefSpectraIDs[i][0],
RefSpectraIDs[i][1], precMZ, precRT
] for i in range(len(NonzeroCoeffsAboveThreshold))]
yield Output
