def Peak_detector(pp_im):
"""
Peak detection and filtering and selection
:param pp_im:
:return:
"""
peakz = []
UID_list = []
counter = 1
for im in list(pp_im):
poss_peaks = BillerBiemann(im, points=9, scans=2) #increase scan #
pi = rel_threshold(poss_peaks, percent=2)
nin = num_ions_threshold(pi, n=5, cutoff=10000)
for peak in nin:
area = peak_sum_area(im, peak)
peak.set_area(area)
peakz.append(nin)
print("...", counter)
counter += 1
for pkz in peakz:pi
print("Peaks detected: ", len(pkz))
uid = pkz.get_UID()
UID_list.append(uid)
def call_peaks(im, tic, smooth, args):
print "calling peaks"
if smooth:
print "Smoothing IM first..."
im.crop_mass(args.lowmass, args.highmass)
print "cropped masses..."
# get the size of the intensity matrix
n_scan, n_mz = im.get_size()
print "# masses in intensity matrix: ", n_mz
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
#print "got ic for mass ", ii
# ic1 = savitzky_golay(ic)
ic_smooth = savitzky_golay(ic, window=args.window,
degree=4) #JT: changed to 4 from 2
#print "savitky golay ran "
ic_base = tophat(ic_smooth, struct="1.5m")
#print "tophat ran "
im.set_ic_at_index(ii, ic_base)
#print "smoothed mass ", ii
print "smoothed IM..."
# noise level calc
tic1 = savitzky_golay(tic)
tic2 = tophat(tic1, struct="1.5m") #JT: How does struct size work?
noise_level = window_analyzer(tic2)
print "Noise level in TIC: ", noise_level
# get the list of Peak objects using BB peak detection / deconv
pl = BillerBiemann(im, args.window, args.scans)
print "Initial number of Peaks found:", len(pl)
# filter down the peaks.
# - First: remove any masses from each peak that have intensity less than r percent of the max intensity in that peak
# - Second: remove any peak where there are less than n ions with intensity above the cutoff
pl2 = rel_threshold(pl, percent=args.minintensity)
pl3 = num_ions_threshold(
pl2, n=args.minions, cutoff=100000
) #100000 for pegBT #200 for peg3 #minions maybe 3 instead of 4?
#JT: Was getting very different noise cutoff values so just made it 10^5
# Which was decided on by looking at chromatograms to find baseline noise lvl
print "Peaks remaining after filtering:", len(pl3)
for peak in pl3:
#peak.null_mass(73)
#peak.null_mass(207) # column bleed
#peak.null_mass(84) # solvent tailing
area = peak_sum_area(im, peak) # get the TIC area for this peak
peak.set_area(area)
area_dict = peak_top_ion_areas(
im, peak, args.topions) # get top n ion areas for this peak
peak.set_ion_areas(area_dict)
return pl3
def call_peaks(im, tic, smooth, args):
print "calling peaks"
if smooth:
print "Smoothing IM first..."
im.crop_mass(args.lowmass, args.highmass)
print "cropped masses..."
# get the size of the intensity matrix
n_scan, n_mz = im.get_size()
print "# masses in intensity matrix: ", n_mz
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
#print "got ic for mass ", ii
# ic1 = savitzky_golay(ic)
ic_smooth = savitzky_golay(ic, window=args.window, degree=2)
#print "savitky golay ran "
ic_base = tophat(ic_smooth, struct="1.5m")
#print "tophat ran "
im.set_ic_at_index(ii, ic_base)
#print "smoothed mass ", ii
print "smoothed IM..."
# noise level calc
tic1 = savitzky_golay(tic)
tic2 = tophat(tic1, struct="1.5m")
noise_level = window_analyzer(tic2)
print "Noise level in TIC: ", noise_level
# get the list of Peak objects using BB peak detection / deconv
pl = BillerBiemann(im, args.window, args.scans)
print "Initial number of Peaks found:", len(pl)
# filter down the peaks.
# - First: remove any masses from each peak that have intensity less than r percent of the max intensity in that peak
# - Second: remove any peak where there are less than n ions with intensity above the cutoff
pl2 = rel_threshold(pl, percent=args.minintensity)
pl3 = num_ions_threshold(pl2, n=args.minions, cutoff=noise_level * args.noisemult)
print "Peaks remaining after filtering:", len(pl3)
for peak in pl3:
# peak.null_mass(73)
peak.null_mass(207) # column bleed
peak.null_mass(84) # solvent tailing
area = peak_sum_area(im, peak) # get the TIC area for this peak
peak.set_area(area)
area_dict = peak_top_ion_areas(im, peak, args.topions) # get top n ion areas for this peak
peak.set_ion_areas(area_dict)
return pl3
def Peak_detector(pp_im):
# Peak detection and filtering and selection
peakz = []
counter = 1
for im in list(pp_im):
poss_peaks = BillerBiemann(im, points=9, scans=2)
pi = rel_threshold(poss_peaks, percent=2)
nin = num_ions_threshold(pi, n=5, cutoff=10000)
for peak in nin:
area = peak_sum_area(im, peak)
peak.set_area(area)
peakz.append(nin)
print("...", counter)
counter += 1
for pkz in peakz:
print("Peaks detected: ", len(pkz))
return (peakz)
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic)
ic_smooth = savitzky_golay(ic1)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
# do peak detection on pre-trimmed data
# get the list of Peak objects
pl = BillerBiemann(im, points, scans)
# trim by relative intensity
apl = rel_threshold(pl, r)
# trim by threshold
peak_list = num_ions_threshold(apl, n, t)
print "Number of Peaks found:", len(peak_list)
# ignore TMS ions and set mass range
for peak in peak_list:
peak.crop_mass(50,540)
peak.null_mass(73)
peak.null_mass(147)
# find area
area = peak_sum_area(im, peak)
peak.set_area(area)
# first by removing all intensities in a peak less than a given relative
# threshold,
# then by removing all peaks that have less than a given number of ions above
# a given value
# Parameters
# percentage ratio of ion intensity to max ion intensity
r = 1
# minimum number of ions, n
n = 3
# greater than or equal to threshold, t
t = 10000
# trim by relative intensity
pl = rel_threshold(peak_list, r)
# trim by threshold
real_peak_list = num_ions_threshold(pl, n, t)
print "Number of filtered peaks in real data: ", len(real_peak_list)
# Set the peak areas
for peak in real_peak_list:
area = peak_sum_area(real_im, peak)
peak.set_area(area)
# real_peak_list is PyMS' best guess at the true peak list
################## Run Simulator ######################
# Simulator takes a peak list, time_list and mass_list
# and returns an IntensityMatrix object.
def Peak_detector(pp_im, noise, name):
# Peak detection and filtering and selection
peakz = []
counter = 1
savePath = '/home/juicebox/utils/easyGC/MS_peak_data'
for im, n, na in itertools.izip(list(pp_im), noise, name):
ms_data = []
#print(na)
poss_peaks = BillerBiemann(im, points=140, scans=20) #increase scan #
pi = rel_threshold(poss_peaks, percent=2)
nin = num_ions_threshold(pi, n=3, cutoff=n)
completeName = os.path.join(savePath, na + "2y.csv")
with open(completeName, 'w') as f:
w = csv.writer(f)
head = [
'RTs', 35.0, 36.0, 37.0, 38.0, 39.0, 40.0, 41.0, 42.0, 43.0,
44.0, 45.0, 46.0, 47.0, 48.0, 49.0, 50.0, 51.0, 52.0, 53.0,
54.0, 55.0, 56.0, 57.0, 58.0, 59.0, 60.0, 61.0, 62.0, 63.0,
64.0, 65.0, 66.0, 67.0, 68.0, 69.0, 70.0, 71.0, 72.0, 73.0,
74.0, 75.0, 76.0, 77.0, 78.0, 79.0, 80.0, 81.0, 82.0, 83.0,
84.0, 85.0, 86.0, 87.0, 88.0, 89.0, 90.0, 91.0, 92.0, 93.0,
94.0, 95.0, 96.0, 97.0, 98.0, 99.0, 100.0, 101.0, 102.0, 103.0,
104.0, 105.0, 106.0, 107.0, 108.0, 109.0, 110.0, 111.0, 112.0,
113.0, 114.0, 115.0, 116.0, 117.0, 118.0, 119.0, 120.0, 121.0,
122.0, 123.0, 124.0, 125.0, 126.0, 127.0, 128.0, 129.0, 130.0,
131.0, 132.0, 133.0, 134.0, 135.0, 136.0, 137.0, 138.0, 139.0,
140.0, 141.0, 142.0, 143.0, 144.0, 145.0, 146.0, 147.0, 148.0,
149.0, 150.0, 151.0, 152.0, 153.0, 154.0, 155.0, 156.0, 157.0,
158.0, 159.0, 160.0, 161.0, 162.0, 163.0, 164.0, 165.0, 166.0,
167.0, 168.0, 169.0, 170.0, 171.0, 172.0, 173.0, 174.0, 175.0,
176.0, 177.0, 178.0, 179.0, 180.0, 181.0, 182.0, 183.0, 184.0,
185.0, 186.0, 187.0, 188.0, 189.0, 190.0, 191.0, 192.0, 193.0,
194.0, 195.0, 196.0, 197.0, 198.0, 199.0, 200.0, 201.0, 202.0,
203.0, 204.0, 205.0, 206.0, 207.0, 208.0, 209.0, 210.0, 211.0,
212.0, 213.0, 214.0, 215.0, 216.0, 217.0, 218.0, 219.0, 220.0
]
w.writerow(head)
for peak in nin:
area = peak_sum_area(im, peak)
print('area=', area)
peak.set_area(area)
ms = peak.get_mass_spectrum()
#print("Peaks rt: ", peak.get_rt())
#print("Peaks ms_list: ", ms.mass_list)
print("Peaks ms_spec: ", list(ms.mass_spec))
p_rt = peak.get_rt()
its = []
items = list(ms.mass_spec)
for i in items:
x = float(i)
its.append(x)
ms_d = ([p_rt] + its)
print(ms_d)
# c = str(ms_d).split(',')
#f.write(str(ms_d))
w.writerow(ms_d)
f.close()
#
#
# #print(peak.get_rt(), items)
# # ms_d = ([peak.get_rt()] + its)
# # print(ms_d)
# # w = csv.writer(f)
# # w.writerow(x for x in list(ms_d))
#
# # w = csv.writer(f, delimiter=',')
# # w.writerows(list[p_rt + items])
# # ms_data.append((peak.get_rt(), list(ms.mass_spec)))
# # completeName = os.path.join(savePath, na+"2b.csv")
# # f = open(completeName, "w+")
# # for i in ms_data:
# # f.write("%s" % str(i))
# # f.close()
# # with open(completeName, 'w') as f:
# # f.write(str([peak.get_rt()] + items) + '\n')
# # f.write(str([peak.get_rt()] + items) + '\n')
# # f.write(str(peak.get_rt()) + str(items).replace('[', '').replace(']', '') + '\n')
# # x = str(peak.get_rt()) + str(items).replace('[', '').replace(']', '')
# # y = x.split(',')
# # print (str(y))
# # f.write(str(y) + '\n')
peakz.append(nin)
#print("...", counter)
counter += 1
#for pkz in peakz:
# print("Peaks detected: ", len(pkz))
#print("Peaks rt: ", pkz.get_rt())
#print("Peaks ms: ", pkz.get_mass_spectrum())
return peakz
# first by removing all intensities in a peak less than a given relative
# threshold,
# then by removing all peaks that have less than a given number of ions above
# a given value
# Parameters
# percentage ratio of ion intensity to max ion intensity
r = 1
# minimum number of ions, n
n = 3
# greater than or equal to threshold, t
t = 10000
# trim by relative intensity
pl = rel_threshold(peak_list, r)
# trim by threshold
real_peak_list = num_ions_threshold(pl, n, t)
print "Number of filtered peaks in real data: ", len(real_peak_list)
# Set the peak areas
for peak in real_peak_list:
area = peak_sum_area(real_im, peak)
peak.set_area(area)
# real_peak_list is PyMS' best guess at the true peak list
################## Run Simulator ######################
# Simulator takes a peak list, time_list and mass_list
def Peak_detector(pp_im, noise, name, points, scans, percent, ni, name_tag, sdir):
"""
Intake cleansed intensity matrices and CMD args
Produces list of peaks and corresponding mass spectrum of each sample
@param pp_im: Cleansed intensity matrices from the Preprocess_IntensityMatrices method
@param noise: Noise level approximation produced by the matrix_from_cdf method
@param name: Sample name use from creating mass spectrum .csv files
@param points: Size of window use for peak detection in BillerBiemann method
@param scans: Number of adjacent windows to compare for peak detection in BillerBiemann method
@param percent: Percentile threshold a peak must exceed to be considered an informative peak
@param ni: Number of ions required per peak to be considered an informative peak
@param name_tag: String consisting of CMD args for identification, ie. 'p140s25%3n3'
@param sdir: Directory to save the mass spectrum .csv files
@return: List of peaks per sample
@return: csv files containing mass spectrum corresponding to each peak
"""
peakz = []
savePath = sdir
ms_data_files = []
print("len pp_im", len(list(pp_im)))
print("len noise", len(noise))
print("len name", len(name), name)
for im, n, na in itertools.izip(list(pp_im), noise, name):
poss_peaks = BillerBiemann(im, points=points, scans=scans)
pi = rel_threshold(poss_peaks, percent=percent)
nin = num_ions_threshold(pi, n=ni, cutoff=n)
completeName = os.path.join(savePath, na + name_tag + "ms_data.csv")
with open(completeName, 'w') as f:
w = csv.writer(f)
head = ['Area', 'RTs'] + [float(i) for i in range(35,221)]
w.writerow(head)
for peak in nin:
area = peak_sum_area(im, peak)
peak.set_area(area)
ms = peak.get_mass_spectrum()
p_rt = peak.get_rt()
its = []
ms_items = list(ms.mass_spec)
for spec in ms_items:
f_spec = float(spec)
its.append(f_spec)
ms_d = ([area] + [p_rt] + its)
w.writerow(ms_d)
f.close()
peakz.append(nin)
ms_data_files.append(completeName)
print('ms_data_files:', ms_data_files)
return [peakz, ms_data_files]
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic)
ic_smooth = savitzky_golay(ic1)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
# do peak detection on pre-trimmed data
# get the list of Peak objects
pl = BillerBiemann(im, points, scans)
# trim by relative intensity
apl = rel_threshold(pl, r)
# trim by threshold
peak_list = num_ions_threshold(apl, n, t)
print "\t -> Number of Peaks found:", len(peak_list)
print "\t -> Executing peak post-procesing and quantification..."
# ignore TMS ions and use same mass range for all experiments
for peak in peak_list:
peak.crop_mass(50, 540)
peak.null_mass(73)
peak.null_mass(147)
# find peak areas
area = peak_sum_area(im, peak)
# first by removing all intensities in a peak less than a given relative
# threshold,
# then by removing all peaks that have less than a given number of ions above
# a given value
# Parameters
# percentage ratio of ion intensity to max ion intensity
r = 1
# minimum number of ions, n
n = 3
# greater than or equal to threshold, t
t = 10000
# trim by relative intensity
pl = rel_threshold(peak_list, r)
# trim by threshold
real_peak_list = num_ions_threshold(pl, n, t)
print "Number of filtered peaks in real data: ", len(real_peak_list)
# Set the peak areas
for peak in real_peak_list:
area = peak_sum_area(real_im, peak)
peak.set_area(area)
# real_peak_list is PyMS' best guess at the true peak list
################## Run Simulator ######################
# Simulator takes a peak list, time_list and mass_list
# and returns an IntensityMatrix object.
# first by removing all intensities in a peak less than a given relative
# threshold,
# then by removing all peaks that have less than a given number of ions above
# a given value
# Parameters
# percentage ratio of ion intensity to max ion intensity
r = 1
# minimum number of ions, n
n = 3
# greater than or equal to threshold, t
t = 10000
# trim by relative intensity
pl = rel_threshold(peak_list, r)
# trim by threshold
real_peak_list = num_ions_threshold(pl, n, t)
print "Number of filtered peaks in real data: ", len(real_peak_list)
# Set the peak areas
for peak in real_peak_list:
area = peak_sum_area(real_im, peak)
peak.set_area(area)
# real_peak_list is PyMS' best guess at the true peak list
################## Run Simulator ######################
# Simulator takes a peak list, time_list and mass_list
def Peak_detector(pp_im, noise, name, points, scans, percent, ni, name_tag,
sdir):
# Peak detection and filtering and selection
peakz = []
# counter = 1
savePath = sdir
ms_data_files = []
print("len pp_im", len(list(pp_im)))
print("len noise", len(noise))
print("len name", len(name), name)
for im, n, na in itertools.izip(list(pp_im), noise, name):
ms_data = []
# print(na)
poss_peaks = BillerBiemann(im, points=points,
scans=scans) # increase scan #
pi = rel_threshold(poss_peaks, percent=percent)
nin = num_ions_threshold(pi, n=ni, cutoff=n)
completeName = os.path.join(savePath, na + name_tag + "ms_data.csv")
with open(completeName, 'w') as f:
w = csv.writer(f)
# head = [35.0, 36.0, 37.0, 38.0, 39.0, 40.0, 41.0, 42.0, 43.0, 44.0, 45.0, 46.0, 47.0, 48.0, 49.0, 50.0, 51.0, 52.0, 53.0, 54.0, 55.0, 56.0, 57.0, 58.0, 59.0, 60.0, 61.0, 62.0, 63.0, 64.0, 65.0, 66.0, 67.0, 68.0, 69.0, 70.0, 71.0, 72.0, 73.0, 74.0, 75.0, 76.0, 77.0, 78.0, 79.0, 80.0, 81.0, 82.0, 83.0, 84.0, 85.0, 86.0, 87.0, 88.0, 89.0, 90.0, 91.0, 92.0, 93.0, 94.0, 95.0, 96.0, 97.0, 98.0, 99.0, 100.0, 101.0, 102.0, 103.0, 104.0, 105.0, 106.0, 107.0, 108.0, 109.0, 110.0, 111.0, 112.0, 113.0, 114.0, 115.0, 116.0, 117.0, 118.0, 119.0, 120.0, 121.0, 122.0, 123.0, 124.0, 125.0, 126.0, 127.0, 128.0, 129.0, 130.0, 131.0, 132.0, 133.0, 134.0, 135.0, 136.0, 137.0, 138.0, 139.0, 140.0, 141.0, 142.0, 143.0, 144.0, 145.0, 146.0, 147.0, 148.0, 149.0, 150.0, 151.0, 152.0, 153.0, 154.0, 155.0, 156.0, 157.0, 158.0, 159.0, 160.0, 161.0, 162.0, 163.0, 164.0, 165.0, 166.0, 167.0, 168.0, 169.0, 170.0, 171.0, 172.0, 173.0, 174.0, 175.0, 176.0, 177.0, 178.0, 179.0, 180.0, 181.0, 182.0, 183.0, 184.0, 185.0, 186.0, 187.0, 188.0, 189.0, 190.0, 191.0, 192.0, 193.0, 194.0, 195.0, 196.0, 197.0, 198.0, 199.0, 200.0, 201.0, 202.0, 203.0, 204.0, 205.0, 206.0, 207.0, 208.0, 209.0, 210.0, 211.0, 212.0, 213.0, 214.0, 215.0, 216.0, 217.0, 218.0, 219.0, 220.0]
head = [
'Area', 'RTs', 35.0, 36.0, 37.0, 38.0, 39.0, 40.0, 41.0, 42.0,
43.0, 44.0, 45.0, 46.0, 47.0, 48.0, 49.0, 50.0, 51.0, 52.0,
53.0, 54.0, 55.0, 56.0, 57.0, 58.0, 59.0, 60.0, 61.0, 62.0,
63.0, 64.0, 65.0, 66.0, 67.0, 68.0, 69.0, 70.0, 71.0, 72.0,
73.0, 74.0, 75.0, 76.0, 77.0, 78.0, 79.0, 80.0, 81.0, 82.0,
83.0, 84.0, 85.0, 86.0, 87.0, 88.0, 89.0, 90.0, 91.0, 92.0,
93.0, 94.0, 95.0, 96.0, 97.0, 98.0, 99.0, 100.0, 101.0, 102.0,
103.0, 104.0, 105.0, 106.0, 107.0, 108.0, 109.0, 110.0, 111.0,
112.0, 113.0, 114.0, 115.0, 116.0, 117.0, 118.0, 119.0, 120.0,
121.0, 122.0, 123.0, 124.0, 125.0, 126.0, 127.0, 128.0, 129.0,
130.0, 131.0, 132.0, 133.0, 134.0, 135.0, 136.0, 137.0, 138.0,
139.0, 140.0, 141.0, 142.0, 143.0, 144.0, 145.0, 146.0, 147.0,
148.0, 149.0, 150.0, 151.0, 152.0, 153.0, 154.0, 155.0, 156.0,
157.0, 158.0, 159.0, 160.0, 161.0, 162.0, 163.0, 164.0, 165.0,
166.0, 167.0, 168.0, 169.0, 170.0, 171.0, 172.0, 173.0, 174.0,
175.0, 176.0, 177.0, 178.0, 179.0, 180.0, 181.0, 182.0, 183.0,
184.0, 185.0, 186.0, 187.0, 188.0, 189.0, 190.0, 191.0, 192.0,
193.0, 194.0, 195.0, 196.0, 197.0, 198.0, 199.0, 200.0, 201.0,
202.0, 203.0, 204.0, 205.0, 206.0, 207.0, 208.0, 209.0, 210.0,
211.0, 212.0, 213.0, 214.0, 215.0, 216.0, 217.0, 218.0, 219.0,
220.0
]
w.writerow(head)
for peak in nin:
area = peak_sum_area(im, peak)
# print('area:', area)
peak.set_area(area)
ms = peak.get_mass_spectrum()
# print("Peaks rt: ", peak.get_rt())
# print("Peaks ms_list: ", ms.mass_list)
# print("Peaks ms_spec: ", list(ms.mass_spec))
p_rt = peak.get_rt()
its = []
items = list(ms.mass_spec)
for i in items:
x = float(i)
its.append(x)
ms_d = ([area] + [p_rt] + its)
# ms_d = its
# print('ms_d', ms_d)
w.writerow(ms_d)
f.close()
peakz.append(nin)
# #print("...", counter)
# counter += 1
ms_data_files.append(completeName)
print('ms_data_files:', ms_data_files)
return [peakz, ms_data_files]