def read_xcms_peaks(input_file):
fp = open(input_file, 'r')
lines = fp.readlines()
peak_list = []
for line in lines[2:]:
parts = line.split('\t')
xcms_id = parts[0].strip('"')
rt = parts[4]
mass = parts[1]
if parts[-3] != '' and parts[-2] == '':
tag = parts[-3]
elif parts[-3] == '' and parts[-2] != '':
tag = parts[-2]
elif parts[-3] != '' and parts[-2] != '':
tag = parts[-3]+' ' + parts[-2]
else:
tag = ''
tag = tag.strip('"')
compound_group = parts[-1]
name = 'unknown'
peak = Peak(float(mass), float(rt), compound_group = compound_group, \
tag=tag, name=name)
peak.set_xcms_id(int(xcms_id))
peak_list.append(peak)
return peak_list
def read_library_peaks(input_file):
fp = open(input_file, 'r')
lines = fp.readlines()
peak_list = []
for i, line in enumerate(lines):
parts = [x.strip('$').strip() for x in line.split('$')]
try:
rt = float(parts[1])
mass = float(parts[2])
except:
try:
parts = [x.strip(',').strip() for x in line.split(',')]
rt = float(parts[2])
mass = float(parts[1])
except:
print 'Warning: Error reading line %s from reference file' %i
print '====================================================='
print 'Line contents: %s' %line.strip()
print
continue
name = parts[0]
#print name, rt, mass
tag = ''
peak = Peak(float(mass), float(rt), name=name)
peak.add_tag(tag)
peak_list.append(peak)
return peak_list
def add_isotope(peak, isotope):
mass = peak.get_mass()
rt = peak.get_rt()
tag = "M+"+str(isotope)
name = peak.get_name()
id_num = peak.get_id_num()
new_mass = mass + isotope*1.0086710869
new_peak = Peak(new_mass, rt, '0', tag, name=name+' '+tag)
new_peak.set_parent(id_num)
return new_peak
def get_decoy_peaks(peak, mode):
"""Based on the idea of Palmer, Alexandrov et al
Use other elements from the periodic table to create
impossible adducts
"""
mass = peak.get_mass()
rt = peak.get_rt()
name = peak.get_name()
decoy_dict = {'He':4.002602, 'Be':9.0121831, 'F':18.998403,
'Al':26.9815385, 'Sc':44.955908, 'Fe':55.845,
'Ge':72.630, 'Sr':87.62}
HYDROGEN_MASS = 1.0078250
id_num = peak.get_id_num()
peaks = []
if mode == 'pos':
for key,value in decoy_dict.iteritems():
new_mass = mass + value
new_peak = Peak(new_mass, rt, '0', tag='+'+key, name=name+'+'+key)
new_peak.set_parent(id_num)
peaks.append(new_peak)
if mode == 'neg':
for key,value in decoy_dict.iteritems():
new_mass = mass - HYDROGEN_MASS + value
new_peak = Peak(new_mass, rt, '0', tag='-H+'+key, name=name+'-H+'+key)
new_peak.set_parent(id_num)
peaks.append(new_peak)
return peaks
def read_peaks(infile):
fp = open(infile, 'r').readlines()
peaks = []
index = 0
fnames = []
ints = []
for i, l in enumerate(fp):
l = l.strip().split(',')
if i == 0:
metNames = [str(x) for x in l[1:]]
if i == 1:
mzs = [float(x) for x in l[1:]]
if i == 2:
rts = [float(x) for x in l[1:]]
if i > 4:
fnames.append(str(l[0]))
ints.append([float(x) for x in l[1:]])
# transpose ints
ints = map(list, zip(*ints))
for i in range(len(mzs)):
peak = Peak(i, mzs[i], rts[i], fnames, ints[i], metNames[i])
peaks.append(peak)
return peaks
def get_adduct_peaks(peak, mode):
"""
Adducts are from CAMERA paper supplemental material
"""
if mode not in ['pos','neg']:
print "Error: mode must be 'pos' or 'neg'"
mass = peak.get_mass()
rt = peak.get_rt()
name = peak.get_name()
positive_dict = {'M+H':1.0078250, 'M+Na':22.989769, 'M+K':39.0983,
'M+NH4':18.03773, 'M+2H(2+)':2.01565,
'M+Na+HCOOH':69.013079, 'M+H+K(2+)':40.106125,
'2M+Na':22.989769, 'M+K+HCOOH':85.12161,
'2M+K':39.0983}
negative_dict = {"M-H":-1.0078250,"M-H+NaCOOH":66.997429,
"M-2H+Na":20.974119,"2M-2H+Na":20.974119,
"M-H+HCOOH":45.015485, "2M-H":-1.0078250,
"2M-2H+K":37.08265, "M-2H+K":37.08265}
peaks = []
if mode == 'pos':
for key,value in positive_dict.iteritems():
if '2M' in key:
new_mass = 2*mass + value
else:
new_mass = mass + value
if '(2+)' in key:
new_mass = new_mass/2
new_peak = Peak(new_mass, rt, '0', tag=key, name=name+' '+key)
peaks.append(new_peak)
if mode == 'neg':
for key,value in negative_dict.iteritems():
if '2M' in key:
new_mass = 2*mass + value
else:
new_mass = mass + value
if '(2+)' in key:
new_mass = new_mass/2
new_peak = Peak(new_mass, rt, '0', tag=key, name=name+' '+key)
peaks.append(new_peak)
return peaks
def get_adduct_peak(peak, adduct, mode):
"""
Adducts are from CAMERA paper supplemental material
"""
if mode not in ['pos','neg']:
print "Error: mode must be 'pos' or 'neg'"
mass = peak.get_mass()
rt = peak.get_rt()
positive_dict = {'M+H':1.0078250, 'M+Na':22.989769, 'M+K':39.0983,
'M+NH4':18.03773, 'M+2H(2+)':2.01565,
'M+Na+HCOOH':69.013079, 'M+H+K(2+)':40.106125,
'2M+Na':22.989769, 'M+K+HCOOH':85.12161,
'2M+K':39.0983}
negative_dict = {"M-H":-1.0078250,"M-H+NaCOOH":66.997429,
"M-2H+Na":20.974119,"2M-2H+Na":20.974119,
"M-H+HCOOH":45.015485, "2M-H":-1.0078250,
"2M-2H+K":37.08265, "M-2H+K":37.08265}
if adduct not in [positive_dict.keys(),negative_dict.keys()]:
print "Error, adduct not found"
if mode == 'pos':
if '2M' in adduct:
new_mass = 2*mass + positive_dict[adduct]
else:
new_mass = mass + positive_dict[adduct]
if '(2+)' in adduct:
new_mass = new_mass/2
if mode == 'neg':
if '2M' in adduct:
new_mass = 2*mass + negative_dict[adduct]
else:
new_mass = mass + negative_dict[adduct]
new_peak = Peak(new_mass, rt, '0', adduct)
return new_peak
def read_peaks(infile):
fp = open(infile, 'r')
peaks = []
for line in fp.readlines()[1:]:
parts = line.split('\t')
for part in parts:
index = int(parts[0].strip('"'))
mz = float(parts[1])
rt = float(parts[4])
areas = []
for i in range(11, 16):
areas.append(float(parts[i]))
peak = Peak(index, mz, rt, areas)
peaks.append(peak)
return peaks