Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Read MGF and task-level inputs #22

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Read MGF and task-level inputs #22

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f126060
initial read mgf
benpullman Nov 22, 2021
4d10cf6
fix reading of task files
benpullman Nov 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 21 additions & 5 deletions tools/peptide_statistics_hpp/cosine_to_synthetics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,17 @@ def read_mzxml_spectrum(spectrum):
None
)

def read_mgf_spectrum(spectrum):
peaks = [processing.Peak(float(p[0]),float(p[1])) for p in zip(spectrum['m/z array'],spectrum['intensity array'])]
precursor = float(spectrum['params']['pepmass'][0])
return processing.Spectrum(
peaks,
precursor,
None,
"scan={}".format(spectrum['params']['scans']),
None
)

def get_mzxml_spectrum(mzxml_object, scan):
#thermo only for now
spectrum = mzxml_object.get_by_id(scan)
Expand Down Expand Up @@ -231,6 +242,8 @@ def main():
elif 'f.' in filename:
# checking uploads directory
filepath = filename.replace('f.','/data/ccms-data/uploads/')
if not Path(filepath).exists():
filepath = filename.replace('f.','/data/ccms-data/tasks/')
else:
filepath = filename

Expand Down Expand Up @@ -271,14 +284,19 @@ def main():
get_spectrum_func = None
read_scan = None

if len(psms_to_consider[filename]) >= min_spectra_to_load_file:
read_full_file = len(psms_to_consider[filename]) >= min_spectra_to_load_file or exts[0] == '.mgf'

if read_full_file:
if exts[0] == '.mzML':
file = open(filepath, 'rb')
file_object = mzml.MzML(file)
get_spectrum_func = read_mzml_spectrum
read_scan = lambda s: str(s['id'].split('scan=')[1])
if exts[0] == '.mgf':
pass
file = open(filepath, 'r')
file_object = mgf.MGF(file)
get_spectrum_func = read_mgf_spectrum
read_scan = lambda s: s['params']['scans']
if exts[0] == '.mzXML':
file = open(filepath, 'rb')
file_object = mzxml.MzXML(file)
Expand All @@ -289,8 +307,6 @@ def main():
file = open(filepath, 'rb')
file_object = mzml.PreIndexedMzML(file)
get_spectrum_func = get_mzml_spectrum
if exts[0] == '.mgf':
pass
if exts[0] == '.mzXML':
file = open(filepath, 'rb')
file_object = mzxml.MzXML(file,use_index = True)
Expand All @@ -299,7 +315,7 @@ def main():
if file:
if file_object and get_spectrum_func:
print("{}: Opened file {}, ready to load".format(datetime.now().strftime("%H:%M:%S"),filename))
if len(psms_to_consider[filename]) >= min_spectra_to_load_file:
if read_full_file:
file_cosine_to_synthetic, file_explained_intensity_per_spectrum = process_spectrum_read_file(psms_to_consider,filename,synthetic_scans,tol,args.low_mass_filter,args.min_snr,threshold,file_object,get_spectrum_func,read_scan)
else:
file_cosine_to_synthetic, file_explained_intensity_per_spectrum = process_spectrum(psms_to_consider,filename,synthetic_scans,tol,args.low_mass_filter,args.min_snr,threshold,file_object,get_spectrum_func)
Expand Down