def deconvolute(peaklist, massType=0):
"""Recalculate peaklist to singly charged.
peaklist (mspy.peaklist) - peak list to deconvolute
massType (0 or 1) - mass type used for m/z re-calculation, 0 = monoisotopic, 1 = average
"""
# recalculate peaks
buff = []
for peak in copy.deepcopy(peaklist):
CHECK_FORCE_QUIT()
# uncharged peak
if not peak.charge:
continue
# charge is correct
elif abs(peak.charge) == 1:
buff.append(peak)
# recalculate peak
else:
# set fwhm
if peak.fwhm:
newFwhm = abs(peak.fwhm*peak.charge)
peak.setfwhm(newFwhm)
# set m/z and charge
if peak.charge < 0:
newMz = mod_basics.mz(mass=peak.mz, charge=-1, currentCharge=peak.charge, massType=massType)
peak.setmz(newMz)
peak.setcharge(-1)
else:
newMz = mod_basics.mz(mass=peak.mz, charge=1, currentCharge=peak.charge, massType=massType)
peak.setmz(newMz)
peak.setcharge(1)
# store peak
buff.append(peak)
# remove baseline
if buff:
for peak in buff:
peak.setsn(None)
peak.setai(peak.intensity)
peak.setbase(0.)
# update peaklist
peaklist = obj_peaklist.peaklist(buff)
return peaklist
def deconvolute(peaklist, massType=0):
"""Recalculate peaklist to singly charged.
peaklist (mspy.peaklist) - peak list to deconvolute
massType (0 or 1) - mass type used for m/z re-calculation, 0 = monoisotopic, 1 = average
"""
# recalculate peaks
buff = []
for peak in copy.deepcopy(peaklist):
CHECK_FORCE_QUIT()
# uncharged peak
if not peak.charge:
continue
# charge is correct
elif abs(peak.charge) == 1:
buff.append(peak)
# recalculate peak
else:
# set fwhm
if peak.fwhm:
newFwhm = abs(peak.fwhm*peak.charge)
peak.setfwhm(newFwhm)
# set m/z and charge
if peak.charge < 0:
newMz = mod_basics.mz(mass=peak.mz, charge=-1, currentCharge=peak.charge, massType=massType)
peak.setmz(newMz)
peak.setcharge(-1)
else:
newMz = mod_basics.mz(mass=peak.mz, charge=1, currentCharge=peak.charge, massType=massType)
peak.setmz(newMz)
peak.setcharge(1)
# store peak
buff.append(peak)
# remove baseline
if buff:
for peak in buff:
peak.setsn(None)
peak.setai(peak.intensity)
peak.setbase(0.)
# update peaklist
peaklist = obj_peaklist.peaklist(buff)
return peaklist
def mz(self, charge, agentFormula='H', agentCharge=1):
"""Get ion m/z"""
return mod_basics.mz(mass=self.mass(),
charge=charge,
agentFormula=agentFormula,
agentCharge=agentCharge)
def averagine(mz, charge=0, composition=AVERAGE_AMINO):
"""Calculate average formula for given mass and building block composition.
mz (float) - peak m/z
charge (int) - peak charge
composition (dict) - building block composition
"""
# get average mass of block
blockMass = 0.
for element in composition:
blockMass += blocks.elements[element].mass[1] * composition[element]
# get block count
neutralMass = mod_basics.mz(mz, charge=0, currentCharge=charge, massType=1)
count = max(1, neutralMass / blockMass)
# make formula
formula = ''
for element in composition:
formula += '%s%d' % (element, int(composition[element]*count))
formula = obj_compound.compound(formula)
# add some hydrogens to reach the mass
hydrogens = int(round((neutralMass - formula.mass(1)) / blocks.elements['H'].mass[1]))
hydrogens = max(hydrogens, -1*formula.count('H'))
formula += 'H%d' % hydrogens
return formula
def averagine(mz, charge=0, composition=AVERAGE_AMINO):
"""Calculate average formula for given mass and building block composition.
mz (float) - peak m/z
charge (int) - peak charge
composition (dict) - building block composition
"""
# get average mass of block
blockMass = 0.
for element in composition:
blockMass += blocks.elements[element].mass[1] * composition[element]
# get block count
neutralMass = mod_basics.mz(mz, charge=0, currentCharge=charge, massType=1)
count = max(1, neutralMass / blockMass)
# make formula
formula = ''
for element in composition:
formula += '%s%d' % (element, int(composition[element]*count))
formula = obj_compound.compound(formula)
# add some hydrogens to reach the mass
hydrogens = int(round((neutralMass - formula.mass(1)) / blocks.elements['H'].mass[1]))
hydrogens = max(hydrogens, -1*formula.count('H'))
formula += 'H%d' % hydrogens
return formula
def mz(self, charge, agentFormula='H', agentCharge=1):
"""Get ion m/z."""
return mod_basics.mz(self.mass(),
charge = charge,
agentFormula = agentFormula,
agentCharge = agentCharge
)
def mass(self):
"""Get neutral peak mass."""
# check charge
if self.charge == None:
return None
# check mass buffer
if self._mass != None:
return self._mass
# calculate neutral mass
self._mass = mod_basics.mz(self.mz, 0, self.charge, agentFormula='H', agentCharge=1)
return self._mass
def mass(self):
"""Get neutral peak mass."""
# check charge
if self.charge == None:
return None
# check mass buffer
if self._mass != None:
return self._mass
# calculate neutral mass
self._mass = mod_basics.mz(self.mz,
0,
self.charge,
agentFormula='H',
agentCharge=1)
return self._mass
def formulator(mz,
charge=0,
tolerance=1.,
units='ppm',
composition={},
agentFormula='H',
agentCharge=1,
limit=1000):
"""Generate formulae for given mass, tolerance and composition limits.
mz (float) - searched m/z value
charge (int) - current charge
tolerance (float) - mass tolerance
units (ppm or Da) - mass tolerance units
composition (dict of 'element':[min count, max count]) - composition limits
agentFormula (str) - charging agent formula
agentCharge (int) - charging agent unit charge
limit (int) - maximum formulae allowed to be calculated
"""
# get neutral mass
if charge != 0 and agentFormula:
mass = mod_basics.mz(mz,
0,
currentCharge=charge,
agentFormula=agentFormula,
agentCharge=agentCharge)
else:
mass = mz
# check neutral mass
if mass <= 0:
return []
# get mass limits
if units == 'ppm':
loMass = mass - (mass / 1e6) * tolerance
hiMass = mass + (mass / 1e6) * tolerance
elif charge != 0:
loMass = mass - abs(charge) * tolerance
hiMass = mass + abs(charge) * tolerance
else:
loMass = mass - tolerance
hiMass = mass + tolerance
# sort elements by masses to speed up processing
buff = []
for el in composition:
elMass = obj_compound.compound(el).mass(0)
buff.append([elMass, el])
buff.sort(reverse=True)
# compile elements and counts
elementMasses = []
elements = []
minComposition = []
maxComposition = []
for el in buff:
elementMasses.append(el[0])
elements.append(el[1])
minComposition.append(composition[el[1]][0])
maxComposition.append(composition[el[1]][1])
# check max composition
for i in range(len(maxComposition)):
maxComposition[i] = min(maxComposition[i],
int(hiMass / elementMasses[i]))
# generate compositions
formulae = []
comps = _compositions(minComposition, maxComposition, elementMasses,
loMass, hiMass, limit)
for comp in comps:
CHECK_FORCE_QUIT()
formula = ''
for i in range(len(comp)):
formula += '%s%d' % (elements[i], comp[i])
formulae.append(formula)
return formulae
def deisotope(peaklist, maxCharge=1, mzTolerance=0.15, intTolerance=0.5, isotopeShift=0.0):
"""Isotopes determination and calculation of peaks charge.
peaklist (mspy.peaklist) - peaklist to process
maxCharge (float) - max charge to be searched
mzTolerance (float) - absolute m/z tolerance for isotopes distance
intTolerance (float) - relative intensity tolerance for isotopes and model (in %/100)
isotopeShift (float) - isotope distance correction (neutral mass) (for HDX etc.)
"""
# check peaklist
if not isinstance(peaklist, obj_peaklist.peaklist):
raise TypeError, "Peak list must be mspy.peaklist object!"
# clear previous results
for peak in peaklist:
peak.setcharge(None)
peak.setisotope(None)
# get charges
if maxCharge < 0:
charges = [-x for x in range(1, abs(maxCharge)+1)]
else:
charges = [x for x in range(1, maxCharge+1)]
charges.reverse()
# walk in a peaklist
maxIndex = len(peaklist)
for x, parent in enumerate(peaklist):
CHECK_FORCE_QUIT()
# skip assigned peaks
if parent.isotope != None:
continue
# try all charge states
for z in charges:
cluster = [parent]
# search for next isotope within m/z tolerance
difference = (ISOTOPE_DISTANCE + isotopeShift)/abs(z)
y = 1
while x+y < maxIndex:
mzError = (peaklist[x+y].mz - cluster[-1].mz - difference)
if abs(mzError) <= mzTolerance:
cluster.append(peaklist[x+y])
elif mzError > mzTolerance:
break
y += 1
# no isotope found
if len(cluster) == 1:
continue
# get theoretical isotopic pattern
mass = min(15000, int( mod_basics.mz( parent.mz, 0, z))) / 200
pattern = patternLookupTable[mass]
# check minimal number of isotopes in the cluster
limit = 0
for p in pattern:
if p >= 0.33:
limit += 1
if len(cluster) < limit and abs(z) > 1:
continue
# check peak intensities in cluster
valid = True
isotope = 1
limit = min(len(pattern), len(cluster))
while (isotope < limit):
# calc theoretical intensity from previous peak and current error
intTheoretical = (cluster[isotope-1].intensity / pattern[isotope-1]) * pattern[isotope]
intError = cluster[isotope].intensity - intTheoretical
# intensity in tolerance
if abs(intError) <= (intTheoretical * intTolerance):
cluster[isotope].setisotope(isotope)
cluster[isotope].setcharge(z)
# intensity is higher (overlap)
elif intError > 0:
pass
# intensity is lower and first isotope is checked (nonsense)
elif (intError < 0 and isotope == 1):
valid = False
break
# try next peak
isotope += 1
# cluster is OK, set parent peak and skip other charges
if valid:
parent.setisotope(0)
parent.setcharge(z)
break
def formulator(mz, charge=0, tolerance=1., units='ppm', composition={}, agentFormula='H', agentCharge=1, limit=1000):
"""Generate formulae for given mass, tolerance and composition limits.
mz (float) - searched m/z value
charge (int) - current charge
tolerance (float) - mass tolerance
units (ppm or Da) - mass tolerance units
composition (dict of 'element':[min count, max count]) - composition limits
agentFormula (str) - charging agent formula
agentCharge (int) - charging agent unit charge
limit (int) - maximum formulae allowed to be calculated
"""
# get neutral mass
if charge != 0 and agentFormula:
mass = mod_basics.mz(mz, 0, currentCharge=charge, agentFormula=agentFormula, agentCharge=agentCharge)
else:
mass = mz
# check neutral mass
if mass <= 0:
return []
# get mass limits
if units == 'ppm':
loMass = mass - (mass/1e6) * tolerance
hiMass = mass + (mass/1e6) * tolerance
elif charge != 0:
loMass = mass - abs(charge)*tolerance
hiMass = mass + abs(charge)*tolerance
else:
loMass = mass - tolerance
hiMass = mass + tolerance
# sort elements by masses to speed up processing
buff = []
for el in composition:
elMass = obj_compound.compound(el).mass(0)
buff.append([elMass, el])
buff.sort(reverse=True)
# compile elements and counts
elementMasses = []
elements = []
minComposition = []
maxComposition = []
for el in buff:
elementMasses.append(el[0])
elements.append(el[1])
minComposition.append(composition[el[1]][0])
maxComposition.append(composition[el[1]][1])
# check max composition
for i in range(len(maxComposition)):
maxComposition[i] = min(maxComposition[i], int(hiMass/elementMasses[i]))
# generate compositions
formulae = []
comps = _compositions(minComposition, maxComposition, elementMasses, loMass, hiMass, limit)
for comp in comps:
CHECK_FORCE_QUIT()
formula = ''
for i in range(len(comp)):
formula += '%s%d' % (elements[i], comp[i])
formulae.append(formula)
return formulae
def deisotope(peaklist, maxCharge=1, mzTolerance=0.15, intTolerance=0.5, isotopeShift=0.0):
"""Isotopes determination and calculation of peaks charge.
peaklist (mspy.peaklist) - peaklist to process
maxCharge (float) - max charge to be searched
mzTolerance (float) - absolute m/z tolerance for isotopes distance
intTolerance (float) - relative intensity tolerance for isotopes and model (in %/100)
isotopeShift (float) - isotope distance correction (neutral mass) (for HDX etc.)
"""
# check peaklist
if not isinstance(peaklist, obj_peaklist.peaklist):
raise TypeError, "Peak list must be mspy.peaklist object!"
# clear previous results
for peak in peaklist:
peak.setcharge(None)
peak.setisotope(None)
# get charges
if maxCharge < 0:
charges = [-x for x in range(1, abs(maxCharge)+1)]
else:
charges = [x for x in range(1, maxCharge+1)]
charges.reverse()
# walk in a peaklist
maxIndex = len(peaklist)
for x, parent in enumerate(peaklist):
CHECK_FORCE_QUIT()
# skip assigned peaks
if parent.isotope != None:
continue
# try all charge states
for z in charges:
cluster = [parent]
# search for next isotope within m/z tolerance
difference = (ISOTOPE_DISTANCE + isotopeShift)/abs(z)
y = 1
while x+y < maxIndex:
mzError = (peaklist[x+y].mz - cluster[-1].mz - difference)
if abs(mzError) <= mzTolerance:
cluster.append(peaklist[x+y])
elif mzError > mzTolerance:
break
y += 1
# no isotope found
if len(cluster) == 1:
continue
# get theoretical isotopic pattern
mass = min(15000, int( mod_basics.mz( parent.mz, 0, z))) / 200
pattern = patternLookupTable[mass]
# check minimal number of isotopes in the cluster
limit = 0
for p in pattern:
if p >= 0.33:
limit += 1
if len(cluster) < limit and abs(z) > 1:
continue
# check peak intensities in cluster
valid = True
isotope = 1
limit = min(len(pattern), len(cluster))
while (isotope < limit):
# calc theoretical intensity from previous peak and current error
intTheoretical = (cluster[isotope-1].intensity / pattern[isotope-1]) * pattern[isotope]
intError = cluster[isotope].intensity - intTheoretical
# intensity in tolerance
if abs(intError) <= (intTheoretical * intTolerance):
cluster[isotope].setisotope(isotope)
cluster[isotope].setcharge(z)
# intensity is higher (overlap)
elif intError > 0:
pass
# intensity is lower and first isotope is checked (nonsense)
elif (intError < 0 and isotope == 1):
valid = False
break
# try next peak
isotope += 1
# cluster is OK, set parent peak and skip other charges
if valid:
parent.setisotope(0)
parent.setcharge(z)
break
