1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#!/usr/bin/env python
import os
from operator import itemgetter
import pymzml
def main():
"""
Extract the 10 most often fragmented precursors from the BSA example file.
This can e.g. be used for defining exclusion lists for further MS runs.
usage:
./get_precursors.py
"""
example_file = os.path.join(
os.path.dirname(__file__), os.pardir, "tests", "data", "BSA1.mzML.gz"
)
run = pymzml.run.Reader(example_file)
fragmented_precursors = {}
for spectrum in run:
if spectrum.ms_level == 2:
selected_precursors = spectrum.selected_precursors
if spectrum.selected_precursors is not None:
for precursor_dict in selected_precursors:
precursor_mz = precursor_dict["mz"]
precursor_i = precursor_dict["i"]
rounded_precursor_mz = round(precursor_mz, 3)
if rounded_precursor_mz not in fragmented_precursors.keys():
fragmented_precursors[rounded_precursor_mz] = []
fragmented_precursors[rounded_precursor_mz].append(spectrum.ID)
precursor_info_list = []
for rounded_precursor_mz, spectra_list in fragmented_precursors.items():
precursor_info_list.append(
(len(spectra_list), rounded_precursor_mz, spectra_list)
)
for pos, (number_of_spectra, rounded_precursor_mz, spectra_list) in enumerate(
sorted(precursor_info_list, reverse=True)
):
print(
"Found precursor: {0} in spectra: {1}".format(
rounded_precursor_mz, spectra_list
)
)
if pos > 8:
break
if __name__ == "__main__":
main()
|
