def evaluate_mzml(mzml_file, picked_peaks_file, half_isolation_window):
boxes = load_picked_boxes(picked_peaks_file)
mz_file = MZMLFile(mzml_file)
scans2boxes, boxes2scans = map_boxes_to_scans(
mz_file, boxes, half_isolation_window=half_isolation_window)
coverage = len(boxes2scans)
return coverage
def run_coverage_evaluation(box_file, mzml_file, half_isolation_window):
boxes = load_picked_boxes(box_file)
mz_file = MZMLFile(mzml_file)
scans2boxes, boxes2scans = map_boxes_to_scans(
mz_file, boxes, half_isolation_window=half_isolation_window)
coverage = len(boxes2scans) / len(boxes)
return coverage
def load_xcms_boxes(box_file):
boxes = load_picked_boxes(box_file)
for box in boxes:
box.rt_in_seconds /= 60.
box.rt_range_in_seconds = [r / 60. for r in box.rt_range_in_seconds]
box.rt /= 60.
box.rt_range = [r / 60. for r in box.rt_range]
return boxes
def add_picked_peaks(self,
mzml_file,
peak_file,
sample_name,
picking_method='mzmine',
sample_type=None,
half_isolation_window=0,
allow_last_overlap=False,
rt_shifts=None,
mz_shifts=None):
"""
TODO: add docstring comment
Adds picked peak information to the aligner
:param mzml_file: ???
:param peak_file: ???
:param sample_name: ???
:param picking_method: ???
:param sample_type: ???
:param half_isolation_window: ???
:param allow_last_overlap: ???
:param rt_shifts: ???
:param mz_shifts: ???
"""
self.sample_names.append(sample_name)
self.sample_types.append(sample_type)
these_peaks = []
frag_intensities = []
# load boxes
if picking_method == 'mzmine':
temp_boxes = load_picked_boxes(peak_file)
elif picking_method == 'peakonly':
temp_boxes = load_peakonly_boxes(peak_file) # not tested
elif picking_method == 'xcms':
temp_boxes = load_xcms_boxes(peak_file) # not tested
else:
sys.exit('Method not supported')
temp_boxes = update_picked_boxes(temp_boxes, rt_shifts, mz_shifts)
self.list_of_boxes.append(temp_boxes)
# Searching in boxes
mzml = MZMLFile(mzml_file)
scans2boxes, boxes2scans = map_boxes_to_scans(
mzml,
temp_boxes,
half_isolation_window=half_isolation_window,
allow_last_overlap=allow_last_overlap)
precursor_intensities, scores = get_precursor_intensities(
boxes2scans, temp_boxes, 'max')
for i, box in enumerate(temp_boxes):
source_id = sample_name + '_' + str(i)
peak_mz = box.mz
peak_rt = box.rt_in_seconds
these_peaks.append(
Peak(peak_mz, peak_rt, box.height, sample_name, source_id))
frag_intensities.append(precursor_intensities[i])
# do alignment, adding the peaks and boxes, and recalculating
# max frag intensity
self._align(these_peaks, temp_boxes, frag_intensities, sample_name)
def extract_boxes(seed_file, out_dir, mzmine_command, xml_file):
"""
Extract peak picked boxes using MzMine2 peak picking
:param seed_file: the seed file in mzML format, should be a DDA file
(containing MS1 and MS2 scans)
:param mzmine_command: path to MzMine2 batch file
:param xml_file: path to MzMine2 XML config file
:return: a list of boxes
"""
# construct the path to the resulting peak picked CSV
seed_picked_peaks_csv = get_peak_picked_csv(seed_file)
logger.info('Peak picking, results will be in %s' % seed_picked_peaks_csv)
# run peak picking using MzMine2
pick_peaks([seed_file],
xml_template=xml_file,
output_dir=out_dir,
mzmine_command=mzmine_command)
# the peak picked csv must exist at this point
assert Path(seed_picked_peaks_csv).is_file()
boxes = load_picked_boxes(seed_picked_peaks_csv)
logger.info('Loaded %d boxes from the seed file' % len(boxes))
return boxes
print("File exists")
else:
print("File does not exist, please specify an mzml file")
sys.exit(0)
else:
mzml_file_name = args.mzml_file
print()
print()
print("Loading: {}".format(mzml_file_name))
mzml_file = MZMLFile(mzml_file_name)
print()
print()
print("Loading: {}".format(args.box_file))
boxes = load_picked_boxes(args.box_file)
print("Loaded {} boxes".format(len(boxes)))
print()
print()
print("Adding ROIs to boxes")
add_rois_to_boxes(boxes, mzml_file)
print()
print()
print("Making edges")
edges = make_edges(boxes, scan_start_times, scan_levels,
args.min_ms1_intensity)
print("{} edges made".format(len(edges)))
scan_names, box_names, _ = zip(*edges)