def _get_peaks(spectrum):
mzs = spectrum.mz
rts = [get_rt(spectrum)] * len(mzs)
intensities = spectrum.i
peaklist = np.stack([mzs, rts, intensities], axis=1)
return peaklist
def get_precursor_info(fragfile):
"""
Get (MS1) precursor peaks and their associated MS2 scans from an mzML file
:param fragfile: path to an mzML file
:return: a pandas dataframe that contains all the ms1 and ms2 information
"""
run = pymzml.run.Reader(fragfile,
obo_version='4.0.1',
MS1_Precision=5e-6,
extraAccessions=[('MS:1000016',
['value', 'unitName'])])
last_ms1_peaklist = None
last_ms1_scan_no = 0
isolation_width = 1.0 # Dalton
data = []
for scan_no, scan in enumerate(run):
if scan.ms_level == 1: # save the last ms1 scan that we've seen
last_ms1_peaklist = _get_peaks(scan)
last_ms1_scan_no = scan_no
# TODO: it's better to use the "isolation window target m/z" field in the mzML file for matching
precursors = scan.selected_precursors
if len(precursors) > 0:
assert len(
precursors
) == 1 # assume exactly 1 precursor peak for each ms2 scan
precursor = precursors[0]
try:
scan_rt = get_rt(scan)
precursor_mz = precursor['mz']
precursor_intensity = precursor['i']
res = _find_precursor_peaks(precursor,
last_ms1_peaklist,
last_ms1_scan_no,
isolation_width=isolation_width)
ms2_peaklist = _get_peaks(scan)
row = [
scan_no, scan_rt, precursor_mz, precursor_intensity,
ms2_peaklist
]
row.extend(res)
data.append(row)
except ValueError as e:
logger.warning(e)
except KeyError as e:
continue # sometimes we can't find the intensity value precursor['i'] in precursors
columns = [
'ms2_scan_id', 'ms2_scan_rt', 'ms2_precursor_mz',
'ms2_precursor_intensity', 'ms2_peaklist', 'ms1_scan_id',
'ms1_scan_rt', 'ms1_mz', 'ms1_intensity'
]
df = pd.DataFrame(data, columns=columns)
# select only rows where we are sure of the matching, i.e. the intensity values aren't too different
df['intensity_diff'] = np.abs(df['ms2_precursor_intensity'] -
df['ms1_intensity'])
idx = (df['intensity_diff'] < 0.1)
ms1_df = df[idx]
return ms1_df