def test_BillerBiemann(self, im_i):
im_i = copy.deepcopy(im_i)
# Intensity matrix size (scans, masses)
n_scan, n_mz = im_i.size
# noise filter and baseline correct
for ii in range(n_mz):
ic = im_i.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
im_i.set_ic_at_index(ii, ic_bc)
# Use Biller and Biemann technique to find apexing ions at a scan
# default is maxima over three scans and not to combine with any neighbouring
# scan.
peak_list = BillerBiemann(im_i)
assert isinstance(peak_list, list)
assert len(peak_list) == 2101
for peak in peak_list:
assert isinstance(peak, Peak)
# Find apex oven 9 points and combine with neighbouring peak if two scans apex
# next to each other.
peak_list2 = BillerBiemann(im_i, points=9, scans=2)
assert len(peak_list2) == 805
assert len(peak_list2) <= len(peak_list)
def test_smooth_im(data):
# Build intensity matrix with defaults, float masses with interval
# (bin size) of one from min mass
im = build_intensity_matrix_i(data)
im.min_mass
n_scan, n_mz = im.size
# process data
for ii in range(n_mz):
# print("Working on IC#", ii + 1)
ic = im.get_ic_at_index(ii)
assert isinstance(ic, IonChromatogram)
# if ((ii+off) in [319, 205, 160, 217]):
# ic.write("output/ic-raw-%d.dat" % (ii+off))
ic_smooth = savitzky_golay(ic)
assert isinstance(ic_smooth, IonChromatogram)
ic_bc = tophat(ic_smooth, struct="1.5m")
assert isinstance(ic_bc, IonChromatogram)
# if ((ii+off) in [319, 205, 160, 217]):
# ic_bc.write("output/ic-flt-%d.dat" % (ii+off))
im.set_ic_at_index(ii, ic_bc)
assert im.get_ic_at_index(ii) == ic_bc
def expr_list(pyms_datadir):
with tempfile.TemporaryDirectory() as tmpdir:
outputdir = pathlib.Path(tmpdir)
# Create experiment files
for jcamp_file in eley_codes:
im = build_intensity_matrix_i(
JCAMP_reader(pyms_datadir / f"{jcamp_file}.JDX"))
# Intensity matrix size (scans, masses)
n_scan, n_mz = im.size
# noise filter and baseline correct
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_bc)
peak_list = BillerBiemann(im, points=9, scans=2)
print('#')
apl = rel_threshold(peak_list, 2)
new_peak_list = num_ions_threshold(apl, 3, 3000)
print('#')
# ignore TMS ions and set mass range
for peak in new_peak_list:
peak.crop_mass(50, 400)
peak.null_mass(73)
peak.null_mass(147)
# find area
area = peak_sum_area(im, peak)
peak.area = area
area_dict = peak_top_ion_areas(im, peak)
peak.ion_areas = area_dict
expr = Experiment(jcamp_file, new_peak_list)
# set time range for all experiments
expr.sele_rt_range(["6.5m", "21m"])
print('#')
expr.dump(outputdir / f"{jcamp_file}.expr")
print('#')
# Load experiments
expr_list = []
for expr_code in eley_codes:
expr = load_expr(outputdir / f"{expr_code}.expr")
assert isinstance(expr, Experiment)
expr_list.append(expr)
yield expr_list
def _peak_list(im_i):
im_i = deepcopy(im_i)
# Intensity matrix size (scans, masses)
n_scan, n_mz = im_i.size
# noise filter and baseline correct
for ii in range(n_mz):
ic = im_i.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
im_i.set_ic_at_index(ii, ic_bc)
# Use Biller and Biemann technique to find apexing ions at a scan
# default is maxima over three scans and not to combine with any neighbouring
# scan.
peak_list = BillerBiemann(im_i, points=9, scans=2)
return peak_list
def Preprocess_IntensityMatrixes(matrixes):
# noise removal and baseline correction of Intensity Matricies
#input matrix list, outputs corrected matrix list
count = 1
for im in matrixes:
n_s, n_mz = im.get_size()
count += 1
for ii in range(n_mz):
print("Working on IC#", ii + 1, " Unit", count)
ic = im.get_ic_at_index(ii)
ic_smoof = savitzky_golay(ic)
ic_bc = tophat(ic_smoof, struct='1.5m')
im.set_ic_at_index(ii, ic_bc)
return (matrixes) #save to file
def Preprocess_IntensityMatrices(matrices):
"""
Baseline correction and smoothing of Intensity Matrices
input matrix list, outputs corrected/"cleansed" matrix list
@param matrices: List of matrices generated by the matrix_from_cdf method
@return: List of matrices that have been baseline corrected & smoothed for peak detection
"""
count = 1
for im in matrices:
n_s, n_mz = im.get_size()
count += 1
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smoof = savitzky_golay(ic)
ic_bc = tophat(ic_smoof, struct='1.5m')
im.set_ic_at_index(ii, ic_bc)
return (matrices) # save to file
def Preprocess_IntensityMatrixes(matrixes):
'''
noise removal and baseline correction of Intensity Matricies
input matrix list, outputs corrected/"cleansed" matrix list
@param matrixes: List of matrixes generated by the matrix_from_cdf method
@return: List of matrixes that have been 'cleansed'
'''
count = 1
for im in matrixes:
n_s, n_mz = im.get_size()
count += 1
for ii in range(n_mz):
# print("Working on IC#", ii+1, " Unit", count)
ic = im.get_ic_at_index(ii)
ic_smoof = savitzky_golay(ic)
ic_bc = tophat(ic_smoof, struct='1.5m')
im.set_ic_at_index(ii, ic_bc)
# print(matrixes)
return (matrixes) # save to file
def test_savitzky_golay(tic):
assert isinstance(tic, IonChromatogram)
# apply noise smoothing
tic1 = savitzky_golay(tic)
assert isinstance(tic1, IonChromatogram)
assert tic1 != tic
assert tic1.is_tic()
assert len(tic1) == 2103
assert len(tic) == len(tic1) # Length should be unchanged
assert tic1.get_intensity_at_index(test_int) == 421885.76190476184
assert tic1.get_time_at_index(test_int) == 1304.15599823
assert tic1.get_time_at_index(test_int) == tic.get_time_at_index(test_int)
assert tic1.time_list[0] == 1.05200003833
assert tic1.time_list[0] == tic.time_list[0]
assert tic1.time_step == 1.0560000035830972
assert tic1.time_step == tic1.time_step
assert tic1.get_index_at_time(12) == 10
assert tic1.get_index_at_time(12) == tic1.get_index_at_time(12)
with pytest.warns(Warning):
tic1.mass
# Test Errors
for obj in [test_string, *test_numbers, *test_lists, test_dict]:
with pytest.raises(TypeError):
savitzky_golay(obj) # type: ignore
for obj in [test_string, test_float, *test_lists, test_dict]:
with pytest.raises(TypeError):
savitzky_golay(tic, degree=obj) # type: ignore
for obj in [test_float, *test_lists, test_dict]:
with pytest.raises(TypeError):
savitzky_golay(tic, window=obj) # type: ignore
def run(self):
print("Quantitative Processing in Progress...")
# TODO: Include data etc. in experiment file
self.update_pbar()
if self.filetype == ID_Format_jcamp:
# Load data using JCAMP_reader
from pyms.GCMS.IO.JCAMP import JCAMP_reader
data = JCAMP_reader(self.properties["Original Filename"])
elif self.filetype == ID_Format_mzML:
# Load data using JCAMP_reader
from pyms.GCMS.IO.MZML import MZML_reader
data = MZML_reader(self.properties["Original Filename"])
elif self.filetype == ID_Format_ANDI:
# Load data using JCAMP_reader
from pyms.GCMS.IO.ANDI import ANDI_reader
data = ANDI_reader(self.properties["Original Filename"])
else:
# Unknown Format
return
# TODO: Waters RAW, Thermo RAW, Agilent .d
self.update_pbar()
method = Method.Method(self.properties["Method"])
self.update_pbar()
# list of all retention times, in seconds
times = data.get_time_list()
# get Total Ion Chromatogram
tic = data.get_tic()
# RT Range, time step, no. scans, min, max, mean and median m/z
data.info()
# Build "intensity matrix" by binning data with integer bins and a
# window of -0.3 to +0.7, the same as NIST uses
im = build_intensity_matrix_i(data)
self.update_pbar()
# Show the m/z of the maximum and minimum bins
print(" Minimum m/z bin: {}".format(im.get_min_mass()))
print(" Maximum m/z bin: {}".format(im.get_max_mass()))
# Crop masses
min_mass, max_mass, *_ = method.mass_range
if min_mass < im.get_min_mass():
min_mass = im.get_min_mass()
if max_mass > im.get_max_mass():
max_mass = im.get_max_mass()
im.crop_mass(min_mass, max_mass)
self.update_pbar()
# Perform Data filtering
n_scan, n_mz = im.get_size()
# Iterate over each IC in the intensity matrix
for ii in range(n_mz):
# print("\rWorking on IC#", ii+1, ' ',end='')
ic = im.get_ic_at_index(ii)
if method.enable_sav_gol:
# Perform Savitzky-Golay smoothing.
# Note that Turbomass does not use smoothing for qualitative method.
ic = savitzky_golay(ic)
if method.enable_tophat:
# Perform Tophat baseline correction
# Top-hat baseline Correction seems to bring down noise,
# retaining shapes, but keeps points on actual peaks
ic = tophat(ic, struct=method.tophat_struct)
# Set the IC in the intensity matrix to the filtered one
im.set_ic_at_index(ii, ic)
self.update_pbar()
# Peak Detection based on Biller and Biemann (1974), with a window
# of <points>, and combining <scans> if they apex next to each other
peak_list = BillerBiemann(im,
points=method.bb_points,
scans=method.bb_scans)
self.update_pbar()
print(" Number of peaks identified before filtering: {}".format(
len(peak_list)))
if method.enable_noise_filter:
# Filtering peak lists with automatic noise filtering
noise_level = window_analyzer(tic)
# should we also do rel_threshold() here?
# https://pymassspec.readthedocs.io/en/master/pyms/BillerBiemann.html#pyms.BillerBiemann.rel_threshold
peak_list = num_ions_threshold(peak_list, method.noise_thresh,
noise_level)
self.update_pbar()
filtered_peak_list = []
for peak in peak_list:
# Get mass and intensity lists for the mass spectrum at the apex of the peak
apex_mass_list = peak.mass_spectrum.mass_list
apex_mass_spec = peak.mass_spectrum.mass_spec
# Determine the intensity of the base peak in the mass spectrum
base_peak_intensity = max(apex_mass_spec)
# Determine the index of the base peak in the mass spectrum
base_peak_index = [
index for index, intensity in enumerate(apex_mass_spec)
if intensity == base_peak_intensity
][0]
# Finally, determine the mass of the base peak
base_peak_mass = apex_mass_list[base_peak_index]
# skip the peak if the base peak is at e.g. m/z 73, i.e. septum bleed
if base_peak_mass in method.base_peak_filter:
continue
area = peak_sum_area(im, peak)
peak.set_area(area)
filtered_peak_list.append(peak)
self.update_pbar()
print(" Number of peaks identified: {}".format(
len(filtered_peak_list)))
# Create an experiment
self.expr = Experiment(self.sample_name, filtered_peak_list)
self.expr.sele_rt_range([
"{}m".format(method.target_range[0]),
"{}m".format(method.target_range[1])
])
self.update_pbar()
current_time = time_now()
# The date and time the experiment was created
self.properties["Date Created"] = current_time
# The date and time the experiment was last modified
self.properties["Date Modified"] = current_time
if self.pbar:
self.pbar.Update(self.pbar.Range)
self.tic = tic
self.filtered_peak_list = filtered_peak_list
def test_align_2_alignments(A1, pyms_datadir, tmp_pathplus):
expr_list = []
for jcamp_file in geco_codes:
im = build_intensity_matrix_i(
JCAMP_reader(pyms_datadir / f"{jcamp_file}.JDX"))
# Intensity matrix size (scans, masses)
n_scan, n_mz = im.size
# noise filter and baseline correct
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_bc)
peak_list = BillerBiemann(im, points=9, scans=2)
apl = rel_threshold(peak_list, 2)
new_peak_list = num_ions_threshold(apl, 3, 3000)
# ignore TMS ions and set mass range
for peak in new_peak_list:
peak.crop_mass(50, 400)
peak.null_mass(73)
peak.null_mass(147)
# find area
area = peak_sum_area(im, peak)
peak.area = area
area_dict = peak_top_ion_areas(im, peak)
peak.ion_areas = area_dict
expr = Experiment(jcamp_file, new_peak_list)
# set time range for all experiments
expr.sele_rt_range(["6.5m", "21m"])
expr_list.append(expr)
F2 = exprl2alignment(expr_list)
T2 = PairwiseAlignment(F2, Dw, Gw)
A2 = align_with_tree(T2, min_peaks=2)
# top_ion_list = A2.common_ion()
# A2.write_common_ion_csv(tmp_pathplus/'area1.csv', top_ion_list)
# between replicates alignment parameters
Db = 10.0 # rt modulation
Gb = 0.30 # gap penalty
print("Aligning input {1,2}")
T9 = PairwiseAlignment([A1, A2], Db, Gb)
A9 = align_with_tree(T9)
A9.write_csv(tmp_pathplus / "rt.csv", tmp_pathplus / "area.csv")
aligned_peaks = list(filter(None, A9.aligned_peaks()))
store_peaks(aligned_peaks, tmp_pathplus / "peaks.bin")
top_ion_list = A9.common_ion()
A9.write_common_ion_csv(tmp_pathplus / "area.csv", top_ion_list)
"""proc.py
"""
import sys
sys.path.append("/x/PyMS/")
from pyms.GCMS.IO.ANDI.Function import ANDI_reader
from pyms.Noise.SavitzkyGolay import savitzky_golay
from pyms.Baseline.TopHat import tophat
# read the raw data
andi_file = "/x/PyMS/data/gc01_0812_066.cdf"
data = ANDI_reader(andi_file)
# get the TIC
tic = data.get_tic()
# apply noise smoothing and baseline correction
tic1 = savitzky_golay(tic)
tic2 = tophat(tic1, struct="1.5m")
# save smoothed/baseline corrected TIC
tic.write("output/tic.dat", minutes=True)
tic1.write("output/tic_smooth.dat", minutes=True)
tic2.write("output/tic_smooth_bc.dat", minutes=True)
ic_smooth1 = im_smooth1.get_ic_at_index(73)
ic.write(output_directory / "noise_smoothing_ic.dat", minutes=True)
ic_smooth1.write(output_directory / "noise_smoothing_ic_smooth1.dat",
minutes=True)
# ## Savitzky--Golay noise filter
#
# A more sophisticated noise filter is the Savitzky-Golay filter.
# Given the data loaded as above, this filter can be applied as
# follows:
# In[9]:
from pyms.Noise.SavitzkyGolay import savitzky_golay
tic4 = savitzky_golay(tic)
# Write the smoothed TIC to disk:
# In[10]:
tic4.write(output_directory / "noise_smoothing_tic4.dat", minutes=True)
# In this example the default parameters were used.
#
# ### Savitzky-Golay Noise filtering of Intensity Matrix Object
#
# The |savitzky_golay()| function described above acts on a single
# |IonChromatogram|. Where it is desired to perform Savitzky Golay
# filtering on the whole |IntensityMatrix| the function
# |savitzky_golay_im()| may be used as follows:
# read in raw data
andi_file = "/x/PyMS/data/gc01_0812_066.cdf"
data = ANDI_reader(andi_file)
data.trim(4101, 4350)
# Build Intensity Matrix
real_im = build_intensity_matrix_i(data)
n_scan, n_mz = real_im.get_size()
# perform necessary pre filtering
for ii in range(n_mz):
ic = real_im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
real_im.set_ic_at_index(ii, ic_bc)
# Detect Peaks
peak_list = BillerBiemann(real_im, points=3, scans=2)
print "Number of peaks found in real data: ", len(peak_list)
######### Filter peaks###############
# Filter the peak list,
# 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
def missing_peak_finder(sample, andi_file, points=7, null_ions=[73, 207],\
crop_ions=[45,300], threshold=100000, rt_window=10):
"""
@summary: Integrates raw data around missing peak locations
to fill in NAs in the data matrix
@param sample: The sample object containing missing peaks
@type sample: pyms.MissingPeak.Class.Sample
@param andi_file: Name of the raw data file
@type andi_file: stringType
@param points: Peak finding - Peak if maxima over 'points' \
number of scans (Default 3)
@type points: intType
@param null_ions: Ions to be deleted in the matrix
@type null_ions: listType
@param crop_ions: Range of Ions to be considered
@type crop_ions: listType
@param threshold: Minimum intensity of IonChromatogram allowable to fill\
missing peak
@type threshold: intType
@param rt_window: Window in seconds around average RT to look for \
missing peak
@type rt_window: floatType
@author: Sean O'Callaghan
"""
### some error checks on null and crop ions
### a for root,files,dirs in os.path.walk(): loop
print "Sample:", sample.get_name(), "andi_file:", andi_file
data = ANDI_reader(andi_file)
# build integer intensity matrix
im = build_intensity_matrix_i(data)
for null_ion in null_ions:
im.null_mass(null_ion)
im.crop_mass(crop_ions[0], crop_ions[1])
# get the size of the intensity matrix
n_scan, n_mz = im.get_size()
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic, points)
ic_smooth = savitzky_golay(ic1, points)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
for mp in sample.get_missing_peaks():
#JT: Debug peak attributes
#attrs = vars(mp)
#print ', '.join("%s: %s" % item for item in attrs.items())
mp_rt = mp.get_rt()
#print(repr(mp_rt))
common_ion = mp.get_ci()
qual_ion_1 = float(mp.get_qual_ion1())
qual_ion_2 = float(mp.get_qual_ion2())
ci_ion_chrom = im.get_ic_at_mass(common_ion)
#print "ci = ",common_ion
qi1_ion_chrom = im.get_ic_at_mass(qual_ion_1)
#print "qi1 = ", qual_ion_1
qi2_ion_chrom = im.get_ic_at_mass(qual_ion_2)
#print "qi2 = ", qual_ion_2
######
# Integrate the CI around that particular RT
#######
#Convert time to points
# How long between scans?
points_1 = ci_ion_chrom.get_index_at_time(float(mp_rt))
points_2 = ci_ion_chrom.get_index_at_time(float(mp_rt) - rt_window)
#print "rt_window = ", points_1 - points_2
rt_window_points = points_1 - points_2
maxima_list = get_maxima_list_reduced(ci_ion_chrom, mp_rt, \
rt_window_points)
large_peaks = []
for rt, intens in maxima_list:
if intens > threshold:
q1_index = qi1_ion_chrom.get_index_at_time(rt)
q2_index = qi2_ion_chrom.get_index_at_time(rt)
q1_intensity = qi1_ion_chrom.get_intensity_at_index(q1_index)
q2_intensity = qi2_ion_chrom.get_intensity_at_index(q2_index)
if q1_intensity > threshold / 2 and q2_intensity > threshold / 2:
large_peaks.append([rt, intens])
#print('found %d peaks above threshold'%len(large_peaks))
areas = []
for peak in large_peaks:
apex = ci_ion_chrom.get_index_at_time(peak[0])
ia = ci_ion_chrom.get_intensity_array().tolist()
area, left, fight, l_share, r_share = ion_area(ia, apex, 0)
areas.append(area)
########################
areas.sort()
if len(areas) > 0:
biggest_area = areas[-1]
mp.set_ci_area(biggest_area)
#print "found area:", biggest_area, "at rt:", mp_rt
else:
#print "Missing peak at rt = ", mp_rt
mp.set_ci_area('NA')
def import_processing(jcamp_file, spectrum_csv_file, report_csv_file, combined_csv_file, bb_points = 9, bb_scans = 2, noise_thresh = 2, target_range = (0,120), tophat_struct="1.5m", nistpath = "../MSSEARCH", base_peak_filter = ['73'], ExprDir = "."):
global nist_path
nist_path = nistpath
# Parameters
base_peak_filter = [int(x) for x in base_peak_filter]
target_range = tuple(target_range)
sample_name = os.path.splitext(os.path.basename(jcamp_file))[0]
number_of_peaks = 80
data = JCAMP_reader(jcamp_file)
# list of all retention times, in seconds
times = data.get_time_list()
# get Total Ion Chromatogram
tic = data.get_tic()
# RT Range, time step, no. scans, min, max, mean and median m/z
data.info()
#data.write("output/data") # save output
# Mass Binning
im = build_intensity_matrix_i(data) # covnert to intensity matrix
#im.get_size() #number of scans, number of bins
masses = im.get_mass_list() # list of mass bins
print(" Minimum m/z bin: {}".format(im.get_min_mass()))
print(" Maximum m/z bin: {}".format(im.get_max_mass()))
# Write Binned Mass Spectra to OpenChrom-like CSV file
ms = im.get_ms_at_index(0) # first mass spectrum
spectrum_csv = open(spectrum_csv_file, 'w')
spectrum_csv.write('RT(milliseconds);RT(minutes) - NOT USED BY IMPORT;RI;')
spectrum_csv.write(';'.join(str(mz) for mz in ms.mass_list))
spectrum_csv.write("\n")
for scan in range(len(times)):
spectrum_csv.write("{};{};{};".format(int(times[scan]*1000),rounders((times[scan]/60),"0.0000000000"),0))
ms = im.get_ms_at_index(scan)
spectrum_csv.write(';'.join(str(intensity) for intensity in ms.mass_spec))
spectrum_csv.write('\n')
spectrum_csv.close()
## Data filtering
# Note that Turbomass does not use smoothing for qualitative method.
# Top-hat baseline Correction seems to bring down noise,
# retaning shapes, but keeps points on actual peaks
#dump_object(im, "output/im.dump") # un-processed output
n_scan, n_mz = im.get_size()
for ii in range(n_mz):
#print("\rWorking on IC#", ii+1, ' ',end='')
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct=tophat_struct)
im.set_ic_at_index(ii, ic_bc)
#dump_object(im, "output/im-proc.dump") # processed output
# Peak Detection based on Biller and Biemann, 1974, with a window
# of n points, and combining y scans if they apex next to each other
peak_list = BillerBiemann(im, points=bb_points, scans=bb_scans)
print(" Number of peaks identified before filtering: {}".format(len(peak_list)))
# Filtering peak lists with automatic noise filtering
noise_level = window_analyzer(tic)
peak_list = num_ions_threshold(peak_list, noise_thresh, noise_level)
# why use 2 for number of ions above threshold?
print(" Number of peaks identified: {}".format(len(peak_list)))
# Peak Areas
peak_area_list = []
filtered_peak_list = []
for peak in peak_list:
apex_mass_list = peak.get_mass_spectrum().mass_list
apex_mass_spec = peak.get_mass_spectrum().mass_spec
base_peak_intensity = max(apex_mass_spec)
base_peak_index = [index for index, intensity in enumerate(apex_mass_spec) if intensity == base_peak_intensity][0]
base_peak_mass = apex_mass_list[base_peak_index]
#print(base_peak_mass)
if base_peak_mass in base_peak_filter:
continue # skip the peak if the base peak is at e.g. m/z 73, i.e. septum bleed
area = peak_sum_area(im, peak)
peak.set_area(area)
peak_area_list.append(area)
filtered_peak_list.append(peak)
# Save the TIC and Peak List
tic.write(os.path.join(ExprDir,"{}_tic.dat".format(sample_name)),formatting=False)
store_peaks(filtered_peak_list,os.path.join(ExprDir,"{}_peaks.dat".format(sample_name)))
# from https://stackoverflow.com/questions/16878715/how-to-find-the-index-of-n-largest-elements-in-a-list-or-np-array-python?lq=1
top_peaks = sorted(range(len(peak_area_list)), key=lambda x: peak_area_list[x])
# Write to turbomass-like CSV file
report_csv = open(report_csv_file, "w")
# Write to GunShotMatch Combine-like CSV file
combine_csv = open(combined_csv_file, "w")
combine_csv.write(sample_name)
combine_csv.write("\n")
report_csv.write("#;RT;Scan;Height;Area\n")
combine_csv.write("Retention Time;Peak Area;;Lib;Match;R Match;Name;CAS Number;Scan\n")
report_buffer = []
for index in top_peaks:
# Peak Number (1-80)
peak_number = top_peaks.index(index)+1
# Retention time (minutes, 3dp)
RT = rounders(filtered_peak_list[index].get_rt()/60,"0.000")
if not target_range[0] < RT <= target_range[1]:
continue # skip the peak if it is outside the desired range
# scan number, not that we really nead it as the peak object has the spectrum
Scan = data.get_index_at_time(filtered_peak_list[index].get_rt())+1
# the binned mass spectrum
filtered_peak_list[index].get_mass_spectrum()
# TIC intensity, as proxy for Peak height, which should be from baseline
Height = '{:,}'.format(rounders(tic.get_intensity_at_index(data.get_index_at_time(filtered_peak_list[index].get_rt())),"0"))
# Peak area, originally in "intensity seconds", so dividing by 60 to
# get "intensity minutes" like turbomass uses
Area = '{:,}'.format(rounders(filtered_peak_list[index].get_area()/60,"0.0"))
#report_csv.write("{};{};{};{};{};{}\n".format(peak_number, RT, Scan, Height, Area,bounds))
report_buffer.append([peak_number, RT, Scan, Height, Area])
report_buffer = report_buffer[::-1] # Reverse list order
# List of peaks already added to report
existing_peaks = []
filtered_report_buffer = []
for row in report_buffer:
filtered_report_buffer.append(row)
filtered_report_buffer = filtered_report_buffer[:number_of_peaks]
filtered_report_buffer.sort(key=operator.itemgetter(2))
for row in filtered_report_buffer:
index = filtered_report_buffer.index(row)
report_csv.write(";".join([str(i) for i in row]))
ms = im.get_ms_at_index(row[2]-1)
create_msp("{}_{}".format(sample_name,row[1]),ms.mass_list, ms.mass_spec)
matches_dict = nist_ms_comparison("{}_{}".format(sample_name,row[1]),ms.mass_list, ms.mass_spec)
combine_csv.write("{};{};Page {} of 80;;;;;;{}\n".format(row[1],row[4],index+1,row[2]))
for hit in range(1,6):
report_csv.write(str(matches_dict["Hit{}".format(hit)]))
report_csv.write(";")
combine_csv.write(";;{};{};{};{};{};{};\n".format(hit,
matches_dict["Hit{}".format(hit)]["Lib"],
matches_dict["Hit{}".format(hit)]["MF"],
matches_dict["Hit{}".format(hit)]["RMF"],
matches_dict["Hit{}".format(hit)]["Name"],
matches_dict["Hit{}".format(hit)]["CAS"],
))
report_csv.write("\n")
time.sleep(2)
report_csv.close()
combine_csv.close()
# Create an experiment
expr = Experiment(sample_name, filtered_peak_list)
expr.sele_rt_range(["{}m".format(target_range[0]),"{}m".format(target_range[1])])
store_expr(os.path.join(ExprDir,"{}.expr".format(sample_name)), expr)
return 0
# read raw data
andi_file = data_directory / "data/gc01_0812_066.cdf"
data = ANDI_reader(andi_file)
data.trim(4101, 4350)
# Build Intensity Matrix
real_im = build_intensity_matrix_i(data)
n_scan, n_mz = real_im.size
# perform necessary pre filtering
for ii in range(n_mz):
ic = real_im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
real_im.set_ic_at_index(ii, ic_bc)
# Detect Peaks
peak_list = BillerBiemann(real_im, points=3, scans=2)
print("Number of peaks found in real data: ", len(peak_list))
######### Filter peaks###############
# Filter the peak list,
# 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
rel_threshold, num_ions_threshold
# read the raw data as a GCMS_data object
andi_file = "data/gc01_0812_066.cdf"
data = ANDI_reader(andi_file)
im = build_intensity_matrix_i(data)
n_scan, n_mz = im.size
print("Intensity matrix size (scans, masses):", (n_scan, n_mz))
# noise filter and baseline correct
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_bc = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_bc)
# Use Biller and Biemann technique to find apexing ions at a scan.
# Find apex oven 9 points and combine with neighbouring peak if two scans apex
# next to each other.
peak_list = BillerBiemann(im, points=9, scans=2)
print("Number of peaks found: ", len(peak_list))
# Filter the peak list,
# 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
def missing_peak_finder(sample, filename, points=13, null_ions=[73, 147],\
crop_ions=[50,540], threshold=1000, rt_window=1, filetype='cdf'):
"""
@summary: Integrates raw data around missing peak locations
to fill in NAs in the data matrix
@param sample: The sample object containing missing peaks
@type sample: pyms.MissingPeak.Class.Sample
@param andi_file: Name of the raw data file
@type andi_file: stringType
@param points: Peak finding - Peak if maxima over 'points' \
number of scans (Default 3)
@type points: intType
@param null_ions: Ions to be deleted in the matrix
@type null_ions: listType
@param crop_ions: Range of Ions to be considered
@type crop_ions: listType
@param threshold: Minimum intensity of IonChromatogram allowable to fill\
missing peak
@type threshold: intType
@param rt_window: Window in seconds around average RT to look for \
missing peak
@type rt_window: floatType
@author: Sean O'Callaghan
"""
### some error checks on null and crop ions
### a for root,files,dirs in os.path.walk(): loop
print "Sample:", sample.get_name(), "File:", filename
if filetype == 'cdf':
data = ANDI_reader(filename)
elif filetype == 'mzml':
data = mzML_reader(filename)
else:
print "file type not valid"
# build integer intensity matrix
im = build_intensity_matrix_i(data)
for null_ion in null_ions:
im.null_mass(null_ion)
im.crop_mass(crop_ions[0], crop_ions[1])
# get the size of the intensity matrix
n_scan, n_mz = im.get_size()
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic, points)
ic_smooth = savitzky_golay(ic1, points)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
for mp in sample.get_missing_peaks():
mp_rt = mp.get_rt()
common_ion = mp.get_ci()
qual_ion_1 = float(mp.get_qual_ion1())
qual_ion_2 = float(mp.get_qual_ion2())
ci_ion_chrom = im.get_ic_at_mass(common_ion)
print "ci = ",common_ion
qi1_ion_chrom = im.get_ic_at_mass(qual_ion_1)
print "qi1 = ", qual_ion_1
qi2_ion_chrom = im.get_ic_at_mass(qual_ion_2)
print "qi2 = ", qual_ion_2
######
# Integrate the CI around that particular RT
#######
#Convert time to points
# How long between scans?
points_1 = ci_ion_chrom.get_index_at_time(float(mp_rt))
points_2 = ci_ion_chrom.get_index_at_time(float(mp_rt)-rt_window)
print "rt_window = ", points_1 - points_2
rt_window_points = points_1 - points_2
maxima_list = get_maxima_list_reduced(ci_ion_chrom, mp_rt, \
rt_window_points)
large_peaks = []
for rt, intens in maxima_list:
if intens > threshold:
q1_index = qi1_ion_chrom.get_index_at_time(rt)
q2_index = qi2_ion_chrom.get_index_at_time(rt)
q1_intensity = qi1_ion_chrom.get_intensity_at_index(q1_index)
q2_intensity = qi2_ion_chrom.get_intensity_at_index(q2_index)
if q1_intensity > threshold/2 and q2_intensity > threshold/2:
large_peaks.append([rt, intens])
print('found %d peaks above threshold'%len(large_peaks))
areas = []
for peak in large_peaks:
apex = ci_ion_chrom.get_index_at_time(peak[0])
ia = ci_ion_chrom.get_intensity_array().tolist()
area, left, fight, l_share, r_share = ion_area(ia, apex, 0)
areas.append(area)
########################
areas.sort()
if len(areas)>0:
biggest_area = areas[-1]
mp.set_ci_area(biggest_area)
print "found area:", biggest_area, "at rt:", mp_rt
else:
print "Missing peak at rt = ", mp_rt
mp.set_ci_area('na')
def missing_peak_finder(
sample: Sample,
file_name: str,
points: int = 3,
null_ions: Optional[List] = None,
crop_ions: Optional[List] = None,
threshold: int = 1000,
rt_window: float = 1,
filetype: MissingPeakFiletype = MZML,
):
r"""
Integrates raw data around missing peak locations to fill ``NA``\s in the data matrix.
:param sample: The sample object containing missing peaks
:param file_name: Name of the raw data file
:param points: Peak finding - Peak if maxima over 'points' number of scans.
:param null_ions: Ions to be deleted in the matrix.
:default null_ions: ``[73, 147]``
:param crop_ions: Range of Ions to be considered.
:default crop_ions: ``[50, 540]``
:param threshold: Minimum intensity of IonChromatogram allowable to fill.
:param rt_window: Window in seconds around average RT to look for.
:param filetype:
:author: Sean O'Callaghan
"""
if not null_ions:
null_ions = [73, 147]
if not crop_ions:
crop_ions = [50, 540]
# TODO: some error checks on null and crop ions
# TODO: a for root,files,dirs in os.path.walk(): loop
print("Sample:", sample.name, "File:", file_name)
if filetype == NETCDF:
# this package
from pyms.GCMS.IO.ANDI import ANDI_reader
data = ANDI_reader(file_name)
elif filetype == MZML:
# this package
from pyms.GCMS.IO.MZML import mzML_reader
data = mzML_reader(file_name)
else:
print("file type not valid")
# build integer intensity matrix
im = build_intensity_matrix_i(data)
for null_ion in null_ions:
im.null_mass(null_ion)
im.crop_mass(crop_ions[0], crop_ions[1])
# get the size of the intensity matrix
n_scan, n_mz = im.size
# smooth data
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic, points)
ic_smooth = savitzky_golay(ic1, points)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
for mp in sample.missing_peaks:
mp_rt = mp.rt
common_ion = mp.common_ion
qual_ion_1 = float(mp.qual_ion1)
qual_ion_2 = float(mp.qual_ion2)
ci_ion_chrom = im.get_ic_at_mass(common_ion)
print("ci = ", common_ion)
qi1_ion_chrom = im.get_ic_at_mass(qual_ion_1)
print("qi1 = ", qual_ion_1)
qi2_ion_chrom = im.get_ic_at_mass(qual_ion_2)
print("qi2 = ", qual_ion_2)
######
# Integrate the CI around that particular RT
#######
# Convert time to points
# How long between scans?
points_1 = ci_ion_chrom.get_index_at_time(float(mp_rt))
points_2 = ci_ion_chrom.get_index_at_time(float(mp_rt) - rt_window)
print("rt_window = ", points_1 - points_2)
rt_window_points = points_1 - points_2
maxima_list = get_maxima_list_reduced(ci_ion_chrom, mp_rt,
rt_window_points)
large_peaks = []
for rt, intens in maxima_list:
if intens > threshold:
q1_index = qi1_ion_chrom.get_index_at_time(rt)
q2_index = qi2_ion_chrom.get_index_at_time(rt)
q1_intensity = qi1_ion_chrom.get_intensity_at_index(q1_index)
q2_intensity = qi2_ion_chrom.get_intensity_at_index(q2_index)
if q1_intensity > threshold / 2 and q2_intensity > threshold / 2:
large_peaks.append([rt, intens])
print(f"found {len(large_peaks):d} peaks above threshold")
areas = []
for peak in large_peaks:
apex = ci_ion_chrom.get_index_at_time(peak[0])
ia = ci_ion_chrom.intensity_array.tolist()
area, left, right, l_share, r_share = ion_area(ia, apex, 0)
areas.append(area)
########################
areas.sort()
if len(areas) > 0:
biggest_area = areas[-1]
mp.common_ion_area = biggest_area
# mp.exact_rt = f"{float(mp_rt) / 60.0:.3f}"
mp.exact_rt = float(mp_rt) / 60.0
print("found area:", biggest_area, "at rt:", mp_rt)
else:
print("Missing peak at rt = ", mp_rt)
mp.common_ion_area = None
"""proc.py
"""
import sys
sys.path.append("/x/PyMS/")
from pyms.GCMS.IO.ANDI.Function import ANDI_reader
from pyms.Noise.SavitzkyGolay import savitzky_golay
from pyms.Baseline.TopHat import tophat
# read the raw data
andi_file = "/x/PyMS/data/gc01_0812_066.cdf"
data = ANDI_reader(andi_file)
# get the TIC
tic = data.get_tic()
# apply noise smoothing and baseline correction
tic1 = savitzky_golay(tic)
tic2 = tophat(tic1, struct="1.5m")
# save smoothed/baseline corrected TIC
tic.write("output/tic.dat",minutes=True)
tic1.write("output/tic_smooth.dat",minutes=True)
tic2.write("output/tic_smooth_bc.dat",minutes=True)
andi_file = data_directory / "a0806_077.cdf"
data = ANDI_reader(andi_file)
im = build_intensity_matrix_i(data)
# Preprocess the data (Savitzky-Golay smoothing and Tophat baseline detection)
# In[3]:
from pyms.Noise.SavitzkyGolay import savitzky_golay
from pyms.TopHat import tophat
n_scan, n_mz = im.size
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic1 = savitzky_golay(ic)
ic_smooth = savitzky_golay(ic1) # Why the second pass here?
ic_bc = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_bc)
# Now the Biller and Biemann based technique can be applied to detect peaks.
# In[4]:
from pyms.BillerBiemann import BillerBiemann
pl = BillerBiemann(im, points=9, scans=2)
len(pl)
# Trim the peak list by relative intensity
# read the raw data as a GCMS_data object
data = ANDI_reader(andi_file)
#data.trim(2431, 2469)
# IntensityMatrix
# default, float masses with interval (bin interval) of one from min mass
print "default intensity matrix, bin interval = 1, boundary +/- 0.5"
im = build_intensity_matrix(data)
im.null_mass(73)
im.null_mass(147)
n_scan, n_mz = im.get_size()
for ii in range(n_mz):
ic = im.get_ic_at_index(ii)
ic_smooth = savitzky_golay(ic)
ic_base = tophat(ic_smooth, struct="1.5m")
im.set_ic_at_index(ii, ic_base)
# Load the experiment
exper = load_expr(expr_file)
# Load the peak list
peak_list = exper.get_peak_list()
# Pass Ion Chromatograms into a list of ICs
n_mz = len(im.get_mass_list())
ic = []
for m in range(n_mz):
ic.append(im.get_ic_at_index(m))
def quantitative_processing(self, jcamp_file, log_stdout=True):
"""
Import JCAMP-DX Files
:param jcamp_file:
:type jcamp_file:
:param log_stdout:
:type log_stdout:
:return:
:rtype:
"""
# Determine the name of the sample from the filename
sample_name = os.path.splitext(os.path.basename(jcamp_file))[0]
# Log Stdout to File
if log_stdout:
sys.stdout = open(os.path.join(self.config.log_dir, sample_name + ".log"), "w")
# Load data using JCAMP_reader
data = JCAMP_reader(jcamp_file)
# list of all retention times, in seconds
times = data.get_time_list()
# get Total Ion Chromatogram
tic = data.get_tic()
# RT Range, time step, no. scans, min, max, mean and median m/z
data.info()
# Build "intensity matrix" by binning data with integer bins and a
# window of -0.3 to +0.7, the same as NIST uses
im = build_intensity_matrix_i(data)
# Show the m/z of the maximum and minimum bins
print(" Minimum m/z bin: {}".format(im.get_min_mass()))
print(" Maximum m/z bin: {}".format(im.get_max_mass()))
# Crop masses
min_mass, max_mass, *_ = self.config.mass_range
if min_mass < im.get_min_mass():
min_mass = im.get_min_mass()
if max_mass > im.get_max_mass():
max_mass = im.get_max_mass()
im.crop_mass(min_mass, max_mass)
# Perform Data filtering
n_scan, n_mz = im.get_size()
# Iterate over each IC in the intensity matrix
for ii in range(n_mz):
# print("\rWorking on IC#", ii+1, ' ',end='')
ic = im.get_ic_at_index(ii)
# Perform Savitzky-Golay smoothing.
# Note that Turbomass does not use smoothing for qualitative method.
ic_smooth = savitzky_golay(ic)
# Perform Tophat baseline correction
# Top-hat baseline Correction seems to bring down noise,
# retaining shapes, but keeps points on actual peaks
ic_bc = tophat(ic_smooth, struct=self.config.tophat_struct)
# Set the IC in the intensity matrix to the filtered one
im.set_ic_at_index(ii, ic_bc)
# Peak Detection based on Biller and Biemann (1974), with a window
# of <points>, and combining <scans> if they apex next to each other
peak_list = BillerBiemann(im, points=self.config.bb_points, scans=self.config.bb_scans)
print(" Number of peaks identified before filtering: {}".format(len(peak_list)))
# Filtering peak lists with automatic noise filtering
noise_level = window_analyzer(tic)
# should we also do rel_threshold() here?
# https://pymassspec.readthedocs.io/en/master/pyms/BillerBiemann.html#pyms.BillerBiemann.rel_threshold
peak_list = num_ions_threshold(peak_list, self.config.noise_thresh, noise_level)
filtered_peak_list = []
for peak in peak_list:
# Get mass and intensity lists for the mass spectrum at the apex of the peak
apex_mass_list = peak.mass_spectrum.mass_list
apex_mass_spec = peak.mass_spectrum.mass_spec
# Determine the intensity of the base peak in the mass spectrum
base_peak_intensity = max(apex_mass_spec)
# Determine the index of the base peak in the mass spectrum
base_peak_index = [
index for index, intensity in enumerate(apex_mass_spec)
if intensity == base_peak_intensity][0]
# Finally, determine the mass of the base peak
base_peak_mass = apex_mass_list[base_peak_index]
# skip the peak if the base peak is at e.g. m/z 73, i.e. septum bleed
if base_peak_mass in self.config.base_peak_filter:
continue
area = peak_sum_area(im, peak)
peak.set_area(area)
filtered_peak_list.append(peak)
print(" Number of peaks identified: {}".format(len(filtered_peak_list)))
# Save the TIC and Peak List
tic.write(os.path.join(self.config.expr_dir, "{}_tic.dat".format(sample_name)), formatting=False)
store_peaks(filtered_peak_list, os.path.join(self.config.expr_dir, "{}_peaks.dat".format(sample_name)))
# Create an experiment
expr = Experiment(sample_name, filtered_peak_list)
expr.sele_rt_range(["{}m".format(self.config.target_range[0]), "{}m".format(self.config.target_range[1])])
store_expr(os.path.join(self.config.expr_dir, "{}.expr".format(sample_name)), expr)