def test0():
fh = pyopenms.MzXMLFile()
here = os.path.dirname(os.path.abspath(__file__))
path = os.path.join(here, "test2.mzXML").encode()
class Consumer(object):
def __init__(self):
self.speclevels = []
self.rts = []
def consumeSpectrum(self, spec):
self.speclevels.append(spec.getMSLevel())
self.rts.append(spec.getRT())
def consumeChromatogram(self, chromo):
raise Exception(
"should never be called as we have no chromoatograms in example file"
)
def setExpectedSize(self, num_specs, num_chromo):
assert num_specs == 5, num_specs
assert num_chromo == 0, num_chromo
def setExperimentalSettings(self, exp):
assert isinstance(exp, pyopenms.ExperimentalSettings)
consumer = Consumer()
fh.transform(path, consumer)
cc = Counter(consumer.speclevels)
assert set(cc.keys()) == set([1, 2])
assert cc[1] == 2
assert cc[2] == 3
assert abs(min(consumer.rts) - 4200.76) < 0.01
assert abs(max(consumer.rts) - 4202.03) < 0.01
def __get_mzml(self, file):
b_content = file.bcore
if self.ext == 'raw':
self.tf = store_byte_in_tmp(
b_content,
prefix=self.fname,
suffix='.RAW',
directory=self.target_dir.absolute().as_posix()
)
self.cmd_msconvert = self.__build_cmd_msconvert()
self.__run_cmd()
elif self.ext == 'mzml':
self.tf = store_byte_in_tmp(
b_content,
prefix=self.fname,
suffix='.mzML',
directory=self.target_dir.absolute().as_posix()
)
elif self.ext == 'mzxml':
self.tf = store_byte_in_tmp(
b_content,
prefix=self.fname,
suffix='.mzXML',
directory=self.target_dir.absolute().as_posix()
)
exp = pyopenms.MSExperiment()
pyopenms.MzXMLFile().load(self.tf.name, exp)
target_path = self.__get_mzml_path().absolute().as_posix()
pyopenms.MzMLFile().store(target_path, exp)
def _getFileHandeler(iftype: FileType):
if iftype == FileType.MZML:
return pyopenms.MzMLFile()
elif iftype == FileType.MZXML:
return pyopenms.MzXMLFile()
elif iftype == FileType.MS2:
return MS2File()
elif iftype == FileType.MGF:
return MascotGenericFile()
else:
raise NotImplementedError('{} not implemented!'.format(iftype.value))
def get_openms_file_type(self, suffix):
import pyopenms
# Define file format and return corresponding pyopenms file object
if suffix.lower() == '.mzxml':
return pyopenms.MzXMLFile()
elif suffix.lower() == '.mzml':
return pyopenms.MzMLFile()
elif suffix.lower() == '.mzdata':
return pyopenms.MzDataFile()
else:
print('Data format is not supported!!')
def read_mzml_or_mzxml_impl(path, psms, theoretical, max_delta_ppm, filetype):
assert filetype in ('mzml', 'mzxml')
fh = po.MzMLFile() if filetype == 'mzml' else po.MzXMLFile()
fh.setLogType(po.LogType.CMD)
input_map = po.MSExperiment()
fh.load(path, input_map)
peaks_list = []
for scan_id, modified_peptide, precursor_charge in psms.itertuples(
index=None):
peaks_list.append(
psm_df(input_map, theoretical, max_delta_ppm, scan_id,
modified_peptide, precursor_charge))
if len(peaks_list) > 0:
reps = np.array([e[0] for e in peaks_list])
transitions = pd.DataFrame({
'fragment':
np.concatenate([e[1] for e in peaks_list]),
'product_mz':
np.concatenate([e[2] for e in peaks_list]),
'intensity':
np.concatenate([e[3] for e in peaks_list]),
'scan_id':
np.repeat([e[4] for e in peaks_list], reps),
'precursor_mz':
np.repeat([e[5] for e in peaks_list], reps),
'modified_peptide':
np.repeat([e[6] for e in peaks_list], reps),
'precursor_charge':
np.repeat([e[7] for e in peaks_list], reps)
})
# Multiple peaks might be identically annotated, only use most intense
transitions = transitions.groupby([
'scan_id', 'modified_peptide', 'precursor_charge', 'precursor_mz',
'fragment', 'product_mz'
])['intensity'].max().reset_index()
else:
transitions = pd.DataFrame({
'scan_id': [],
'modified_peptide': [],
'precursor_charge': [],
'precursor_mz': [],
'fragment': [],
'product_mz': [],
'intensity': []
})
return (transitions)
def oms_ffmetabo_single_file(filename, max_peaks_per_file=5000):
feature_map = oms.FeatureMap()
mass_traces = []
mass_traces_split = []
mass_traces_filtered = []
exp = oms.MSExperiment()
peak_map = oms.PeakMap()
options = oms.PeakFileOptions()
options.setMSLevels([1])
if filename.lower().endswith('.mzxml'):
fh = oms.MzXMLFile()
elif filename.lower().endswith('.mzml'):
fh = oms.MzMLFile()
else:
assert False, filename
fh.setOptions(options)
# Peak map
fh.load(filename, exp)
#for chrom in exp.getChromatograms():
# peak_map.addChrom(chrom)
for spec in exp.getSpectra():
peak_map.addSpectrum(spec)
mass_trace_detect = oms.MassTraceDetection()
mass_trace_detect.run(peak_map, mass_traces, max_peaks_per_file)
elution_peak_detection = oms.ElutionPeakDetection()
elution_peak_detection.detectPeaks(mass_traces, mass_traces_split)
feature_finding_metabo = oms.FeatureFindingMetabo()
feature_finding_metabo.run(
mass_traces_split,
feature_map,
mass_traces_filtered)
feature_map.sortByOverallQuality()
return feature_map
def read_mzml_or_mzxml_impl(path, psms, theoretical, max_delta_ppm, filetype):
assert filetype in ('mzml', 'mzxml')
fh = po.MzMLFile() if filetype=='mzml' else po.MzXMLFile()
fh.setLogType(po.LogType.CMD)
input_map = po.MSExperiment()
fh.load(path, input_map)
peaks_list = []
for ix, psm in psms.iterrows():
scan_id = psm['scan_id']
ionseries = theoretical[psm['modified_peptide']][psm['precursor_charge']]
spectrum = input_map.getSpectrum(scan_id - 1)
fragments = []
product_mzs = []
intensities = []
for peak in spectrum:
fragment, product_mz = annotate_mass(peak.getMZ(), ionseries, max_delta_ppm)
if fragment is not None:
fragments.append(fragment)
product_mzs.append(product_mz)
intensities.append(peak.getIntensity())
peaks = pd.DataFrame({'fragment': fragments, 'product_mz': product_mzs, 'intensity': intensities})
peaks['scan_id'] = scan_id
peaks['precursor_mz'] = po.AASequence.fromString(po.String(psm['modified_peptide'])).getMonoWeight(po.Residue.ResidueType.Full, psm['precursor_charge']) / psm['precursor_charge'];
peaks['modified_peptide'] = psm['modified_peptide']
peaks['precursor_charge'] = psm['precursor_charge']
# Baseline normalization to highest annotated peak
max_intensity = np.max(peaks['intensity'])
if max_intensity > 0:
peaks['intensity'] = peaks['intensity'] * (10000 / max_intensity)
peaks_list.append(peaks)
if len(peaks_list) > 0:
transitions = pd.concat(peaks_list)
# Multiple peaks might be identically annotated, only use most intense
transitions = transitions.groupby(['scan_id','modified_peptide','precursor_charge','precursor_mz','fragment','product_mz'])['intensity'].max().reset_index()
else:
transitions = pd.DataFrame({'scan_id': [], 'modified_peptide': [], 'precursor_charge': [], 'precursor_mz': [], 'fragment': [], 'product_mz': [], 'intensity': []})
return(transitions)
def testMxxxFile():
"""
@tests:
MzDataFile.__init__
MzDataFile.endProgress
MzDataFile.getLogType
MzDataFile.load
MzDataFile.setLogType
MzDataFile.setProgress
MzDataFile.startProgress
MzDataFile.store
MzMLFile.__init__
MzMLFile.endProgress
MzMLFile.getLogType
MzMLFile.load
MzMLFile.setLogType
MzMLFile.setProgress
MzMLFile.startProgress
MzMLFile.store
MzXMLFile.__init__
MzXMLFile.endProgress
MzXMLFile.getLogType
MzXMLFile.load
MzXMLFile.setLogType
MzXMLFile.setProgress
MzXMLFile.startProgress
MzXMLFile.store
"""
mse = pyopenms.MSExperiment()
fh = pyopenms.MzDataFile()
_testProgressLogger(fh)
fh.store("test.mzData", mse)
fh.load("test.mzData", mse)
fh = pyopenms.MzMLFile()
_testProgressLogger(fh)
fh.store("test.mzML", mse)
fh.load("test.mzML", mse)
fh = pyopenms.MzXMLFile()
_testProgressLogger(fh)
fh.store("test.mzXML", mse)
fh.load("test.mzXML", mse)
def readms(input_file): #only 'mzml,mzdata or mzxml' format
#ms_format = re.search('\.\w+',input_file)
import pyopenms
ms_format = os.path.splitext(input_file)[1]
#ms_format = ms_format.group()
ms_format = ms_format.lower()
msdata = pyopenms.MSExperiment()
if ms_format == '.mzxml':
file = pyopenms.MzXMLFile()
elif ms_format == '.mzml':
file = pyopenms.MzMLFile()
elif ms_format == '.mzdata':
file = pyopenms.MzDataFile()
else:
raise Exception('ERROR: %s is wrong format' % input_file)
file.load(r'%s' % input_file, msdata)
ms = []
intensity = []
rt = []
for spectrum in msdata:
if spectrum.getMSLevel() == 1:
rt.append(spectrum.getRT())
p_ms = []
p_intensity = []
for peak in spectrum:
if peak.getIntensity() != 0:
p_ms.append(peak.getMZ())
p_intensity.append(peak.getIntensity())
#print len(p_intensity)
ms_index = np.argsort(-np.array(p_intensity))
ms.append(np.array(p_ms)[ms_index])
intensity.append(np.array(p_intensity)[ms_index])
#scan+=1
rt1 = np.array(rt)
rt_mean_interval = np.mean(np.diff(rt1))
#print rt_mean_interval
#rt_mean_interval = np.mean(rt1[1:]-rt1[:-1])
#return ms,intensity,rt,scan,rt_max_interval
return ms, intensity, rt, rt_mean_interval
def main():
parser = argparse.ArgumentParser(description="PeakPickerHiRes")
parser.add_argument(
"-in",
action="store",
type=str,
dest="in_",
metavar="input_file",
)
parser.add_argument(
"-out",
action="store",
type=str,
metavar="output_file",
)
parser.add_argument(
"-ini",
action="store",
type=str,
metavar="ini_file",
)
parser.add_argument(
"-dict_ini",
action="store",
type=str,
metavar="python_dict_ini_file",
)
parser.add_argument(
"-write_ini",
action="store",
type=str,
metavar="ini_file",
)
parser.add_argument(
"-write_dict_ini",
action="store",
type=str,
metavar="python_dict_ini_file",
)
args = parser.parse_args()
run_mode = args.in_ is not None and args.out is not None\
and (args.ini is not None or args.dict_ini is not None)
write_mode = args.write_ini is not None or args.write_dict_ini is not None
ok = run_mode or write_mode
if not ok:
parser.error("either specify -in, -out and -(dict)ini for running "
"the peakpicker\nor -write(dict)ini for creating std "
"ini file")
defaults = pms.PeakPickerHiRes().getDefaults()
if args.write_dict_ini or args.write_ini:
if args.write_dict_ini:
with open(args.write_dict_ini, "w") as fp:
pprint.pprint(defaults.asDict(), stream=fp)
if args.write_ini:
defaults.store(args.write_ini)
else:
if args.ini:
param = pms.Param()
param.load(args.ini)
defaults.update(param, False, False)
elif args.dict_ini:
with open(args.dict_ini, "r") as fp:
try:
dd = eval(fp.read())
except:
raise Exception("could not parse %s" % args.dict_ini)
defaults.updateFrom(dd)
fh = pms.MzXMLFile()
fh.setLogType(pms.LogType.CMD)
input_map = pms.MSExperiment()
fh.load(args.in_, input_map)
run_peak_picker(input_map, defaults, args.out)
def load_ms_file(ms_experiment, path_to_file):
"""
Load mzML / mzXML file into given ms_experiment object, filter to MSLevel = 1 - as only those supported for peakFinders
:param ms_experiment:
:param path_to_file:
:param set_options:
:return:
"""
options = oms.PeakFileOptions()
options.setMSLevels([1]) # MS1 is comparable to mcc-ims input
# RuntimeError: FeatureFinder can only operate on MS level 1 data. Please do not use MS/MS data
# support mzXML and mzML -file
suffix = Path(path_to_file).suffix.lower()
if suffix == ".mzxml":
fh = oms.MzXMLFile()
elif suffix == ".mzml":
fh = oms.MzMLFile()
else:
raise UnsupportedGCMSFiletypeError(
"Unsupported filetype. Only mzXML and mzML format is supported.")
fh.setOptions(options)
# load data into experiment
fh.load(
str(path_to_file),
ms_experiment) # if problems loading - let pyopenms error bubble up
ms_experiment.updateRanges()
# get keys function loads the return into an empty list - very straightforward to guess
# k = []
# ms_experiment[0].getKeys(k)
# ms_experiment[1].getKeys(k)
# ms_experiment[2].getKeys(k)
# ms_experiment[3].getKeys(k)
# list_functions(ms_experiment[0])
#
# ms_experiment[0].getAcquisitionInfo()#
#
# oms.CachedmzML.store("myCache.mzML", ms_experiment)
#
# # Now load data
# cfile = oms.CachedmzML()
# oms.CachedmzML.load("myCache.mzML", cfile)
#
# meta_data = cfile.getMetaData()
# meta_data.metaRegistry()
# help(meta_data)
# list_functions(meta_data)
# meta_data.getKeys(k)
#
#
# k = []
# list_functions(\
# ms_experiment[0].getDataProcessing()[0].getMetaValue(k))
# print(k)
# list_functions(fh.getOptions())
# try centroided approach to pickPeaks
# if not centroided,
# apply smoothing and peak detection to form centroided data = peakMap / FeatureXML file
return ms_experiment
