def test_ms1_controller_with_simulated_chems(self):
logger.info('Testing MS1 controller with simulated chemicals')
# create some chemical objects
chems = ChemicalCreator(self.ps, ROI_Sources, hmdb)
dataset = chems.sample(mz_range, rt_range, min_ms1_intensity, n_chems, self.ms_level)
self.assertEqual(len(dataset), n_chems)
# create a simulated mass spec and MS1 controller
mass_spec = IndependentMassSpectrometer(POSITIVE, dataset, self.ps)
controller = SimpleMs1Controller()
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, min_rt, max_rt, progress_bar=True)
# set the log level to WARNING so we don't see too many messages when environment is running
set_log_level_warning()
# run the simulation
env.run()
# set the log level back to DEBUG
set_log_level_debug()
# write simulated output to mzML file
filename = 'ms1_controller_simulated_chems.mzML'
out_file = os.path.join(out_dir, filename)
env.write_mzML(out_dir, filename)
self.assertTrue(os.path.exists(out_file))
print()
def test_multiple_adducts(self):
fs = DatabaseFormulaSampler(HMDB)
ri = UniformRTAndIntensitySampler(min_rt=100, max_rt=101)
cs = ConstantChromatogramSampler()
adduct_prior_dict = {POSITIVE: {'M+H': 100, 'M+Na': 100, 'M+K': 100}}
cm = ChemicalMixtureCreator(fs,
rt_and_intensity_sampler=ri,
chromatogram_sampler=cs,
adduct_prior_dict=adduct_prior_dict,
adduct_proportion_cutoff=0.0)
n_adducts = len(adduct_prior_dict[POSITIVE])
n_chems = 5
dataset = cm.sample(n_chems, 2)
for c in dataset:
c.isotopes = [(c.mass, 1, "Mono")]
# should be 15 peaks or less all the time
# some adducts might not be sampled if the probability is less than 0.2
controller = SimpleMs1Controller()
ms = IndependentMassSpectrometer(POSITIVE, dataset)
env = Environment(ms, controller, 102, 110, progress_bar=True)
set_log_level_warning()
env.run()
for scan in controller.scans[1]:
assert len(scan.mzs) <= n_chems * n_adducts
def test_ms1_controller_with_qcbeer_chems(self):
logger.info('Testing MS1 controller with QC beer chemicals')
# create a simulated mass spec and MS1 controller
mass_spec = IndependentMassSpectrometer(POSITIVE, beer_chems, self.ps)
controller = SimpleMs1Controller()
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, min_rt, max_rt, progress_bar=True)
# set the log level to WARNING so we don't see too many messages when environment is running
set_log_level_warning()
# run the simulation
env.run()
# set the log level back to DEBUG
set_log_level_debug()
# write simulated output to mzML file
filename = 'ms1_controller_qcbeer_chems.mzML'
out_file = os.path.join(out_dir, filename)
env.write_mzML(out_dir, filename)
self.assertTrue(os.path.exists(out_file))
print()
def test_peaks_in_range(self):
min_mz = 100.
max_mz = 200.
logger.info('Testing MS1 controller with narrow m/z range')
# create a simulated mass spec and MS1 controller
mass_spec = IndependentMassSpectrometer(POSITIVE, BEER_CHEMS)
params = AdvancedParams()
params.default_ms1_scan_window = (min_mz, max_mz)
controller = SimpleMs1Controller(params=params)
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, BEER_MIN_BOUND, BEER_MAX_BOUND, progress_bar=True)
run_environment(env)
# write simulated output to mzML file
filename = 'ms1_controller_qcbeer_chems_narrow.mzML'
check_mzML(env, OUT_DIR, filename)
for scan_level, scans in controller.scans.items():
for s in scans:
assert min(s.mzs) >= min_mz
assert max(s.mzs) <= max_mz
def generate_mzmls(self, output_dir, params):
scan_duration_dicts = self.time_gen(params)
if (self.filenames is None):
self.filenames = [
os.path.join(output_dir, "time_exp_data_{:04d}.mzML".format(i))
for i, _ in enumerate(scan_duration_dicts)
]
self.file_counter += len(scan_duration_dicts)
if (len(params) != len(self.filenames)):
raise ValueError(
"Parameter and filename list not the same length!")
for f, d in zip(self.filenames, scan_duration_dicts):
mass_spec = IndependentMassSpectrometer(POSITIVE,
self.chems,
None,
scan_duration_dict=d)
controller = SimpleMs1Controller()
env = Environment(mass_spec,
controller,
self.min_rt,
self.max_rt,
progress_bar=True)
set_log_level_warning()
env.run()
set_log_level_warning()
env.write_mzML(output_dir, os.path.basename(f))
def simple_ms1_processor():
print(
'#' * 10,
'Load previously trained spectral feature database and the list of extracted metabolites, \
created in 01. Download Data')
#-----------------
mypath = 'documents/simple_ms1/example_data'
#-----------------
base_dir = os.path.abspath(mypath)
ps = load_obj(Path(base_dir, 'peak_sampler_mz_rt_int_19_beers_fullscan.p'))
hmdb = load_obj(Path(base_dir, 'hmdb_compounds.p'))
# set_log_level_debug()
out_dir = Path(base_dir, 'results', 'MS1_single')
# the list of ROI sources created in the previous notebook '01. Download Data.ipynb'
ROI_Sources = [
str(Path(base_dir, 'DsDA', 'DsDA_Beer', 'beer_t10_simulator_files'))
]
# minimum MS1 intensity of chemicals
min_ms1_intensity = 1.75E5
# m/z and RT range of chemicals
rt_range = [(0, 1440)]
mz_range = [(0, 1050)]
# the number of chemicals in the sample
n_chems = 6500
# maximum MS level (we do not generate fragmentation peaks when this value is 1)
ms_level = 1
chems = ChemicalCreator(ps, ROI_Sources, hmdb)
dataset = chems.sample(mz_range, rt_range, min_ms1_intensity, n_chems,
ms_level)
save_obj(dataset, Path(out_dir, 'dataset.p'))
for chem in dataset[0:10]:
print(chem)
print('#' * 10,
'Run MS1 controller on the samples and generate .mzML files')
min_rt = rt_range[0][0]
max_rt = rt_range[0][1]
mass_spec = IndependentMassSpectrometer(POSITIVE, dataset, ps)
controller = SimpleMs1Controller()
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, min_rt, max_rt, progress_bar=True)
# set the log level to WARNING so we don't see too many messages when environment is running
set_log_level_warning()
# run the simulation
env.run()
set_log_level_debug()
mzml_filename = 'ms1_controller.mzML'
env.write_mzML(out_dir, mzml_filename)
return str(Path(mypath, 'results', 'MS1_single')) + '/' + mzml_filename
def test_fullscan_from_mzml(self, chems_from_mzml):
ionisation_mode = POSITIVE
controller = SimpleMs1Controller()
ms = IndependentMassSpectrometer(ionisation_mode, chems_from_mzml)
env = Environment(ms, controller, 500, 600, progress_bar=True)
set_log_level_warning()
env.run()
filename = 'fullscan_from_mzml.mzML'
check_mzML(env, OUT_DIR, filename)
def test_ms1_controller_with_qcbeer_chems(self):
logger.info('Testing MS1 controller with QC beer chemicals')
# create a simulated mass spec and MS1 controller
mass_spec = IndependentMassSpectrometer(POSITIVE, BEER_CHEMS)
controller = SimpleMs1Controller()
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, BEER_MIN_BOUND, BEER_MAX_BOUND, progress_bar=True)
run_environment(env)
# write simulated output to mzML file
filename = 'ms1_controller_qcbeer_chems.mzML'
check_mzML(env, OUT_DIR, filename)
def test_ms1_controller_with_simulated_chems(self, fragscan_dataset):
logger.info('Testing MS1 controller with simulated chemicals')
min_bound, max_bound = get_rt_bounds(fragscan_dataset, CENTRE_RANGE)
logger.info('RT bounds %s %s' % (min_bound, max_bound))
assert len(fragscan_dataset) == N_CHEMS
# create a simulated mass spec and MS1 controller
mass_spec = IndependentMassSpectrometer(POSITIVE, fragscan_dataset)
controller = SimpleMs1Controller()
# create an environment to run both the mass spec and controller
env = Environment(mass_spec, controller, min_bound, max_bound, progress_bar=True)
run_environment(env)
# write simulated output to mzML file
filename = 'ms1_controller_simulated_chems.mzML'
check_mzML(env, OUT_DIR, filename)