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

lower score threshold - with adjustment to max PSM FDR of 2% MS2 branch #5

Open
wants to merge 3 commits into
base: ms2_recalibration
Choose a base branch
from
Open

lower score threshold - with adjustment to max PSM FDR of 2% MS2 branch #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8332eb9
lower score threshold - with adjustment to max PSM FDR of 2%
swlenz Jan 22, 2020
ae3f416
only start xi on mgf-files and only if they don't start with 'recal_'
lutzfischer Jan 23, 2020
39e6c63
reduced the maxfdr to 2% again
lutzfischer Jan 23, 2020
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
Binary file added ProteoFileReader.pyc
View file
Open in desktop
Binary file not shown.
Binary file added fragpair_scoring.pyc
View file
Open in desktop
Binary file not shown.
Binary file added gui.pyc
View file
Open in desktop
Binary file not shown.
12 changes: 10 additions & 2 deletions mass_recal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,15 @@ def run_xi_lin(peakfile, fasta, cnf, outpath, xipath, threads='1'):


def get_ppm_error(xi_df, outfile):
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > 6)] # TODO: new xi version requires lower score?
score_cutoff = 2
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > score_cutoff)]
xi_df_decoy = xi_df[(xi_df.decoy == 1) & (xi_df['match score'] > score_cutoff)]

while (len(xi_df_decoy.index)>0.02*len(xi_df.index))
score_cutoff=min(xi_df['match score'][xi_df['match score'] > score_cutoff]);
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > score_cutoff)]
xi_df_decoy = xi_df[(xi_df.decoy == 1) & (xi_df['match score'] > score_cutoff)]


median_err = np.median(xi_df['Precoursor Error'])
try:
Expand Down Expand Up @@ -134,7 +142,7 @@ def main(mgf, fasta, xi_cnf, outpath, threads, xi_jar='./resources/XiSearch_1.6.
fasta = '//130.149.167.198/rappsilbergroup/users/MitoProject/For Swantje/20170109_uniprot_mitoIDrun_FASTA.fasta'
outpath = base_dir + '/error_shift'
for in_file in os.listdir(mgf_dir):
if '.mgf' in in_file:
if in_file.endswith('.mgf') and not in_file.startswith('recal_') :
main(mgf=os.path.join(mgf_dir, in_file),
fasta=fasta,
xi_cnf='D:/user/Swantje/projects/pipeline_prepro_xi_fdr/resources/xi_linear_by_tryp.conf',
Expand Down
Binary file added mass_recal.pyc
View file
Open in desktop
Binary file not shown.
12 changes: 10 additions & 2 deletions mass_recal_ms2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,15 @@ def run_xi_lin(peakfile, fasta, cnf, outpath, xipath, threads='1'):


def get_ppm_error(xi_df, peaks_df, outfile):
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > 6)]
score_cutoff = 2
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > score_cutoff)]
xi_df_decoy = xi_df[(xi_df.decoy == 1) & (xi_df['match score'] > score_cutoff)]

while (len(xi_df_decoy.index)>0.02*len(xi_df.index)):
score_cutoff=min(xi_df['match score'][xi_df['match score'] > score_cutoff]);
xi_df = xi_df[(xi_df.decoy == 0) & (xi_df['match score'] > score_cutoff)]
xi_df_decoy = xi_df[(xi_df.decoy == 1) & (xi_df['match score'] > score_cutoff)]

median_err = np.median(xi_df['Precoursor Error'])
try:
fig, ax = plt.subplots()
Expand Down Expand Up @@ -156,7 +164,7 @@ def main(mgf, fasta, xi_cnf, outpath, threads, xi_jar='./resources/XiSearch_1.6.
fasta = '//130.149.167.198/rappsilbergroup/users/MitoProject/For Swantje/20170109_uniprot_mitoIDrun_FASTA.fasta'
outpath = base_dir + '/error_shift'
for in_file in os.listdir(mgf_dir):
if '.mgf' in in_file:
if in_file.endswith('.mgf') and not in_file.startswith('recal_'):
main(mgf=os.path.join(mgf_dir, in_file),
fasta=fasta,
xi_cnf='D:/user/Swantje/projects/pipeline_prepro_xi_fdr/resources/xi_linear_by_tryp.conf',
Expand Down
2 changes: 1 addition & 1 deletion preprocessing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,7 +300,7 @@ def process_file(filepath, outdir, mscon_settings, split_acq, detector_filter, m
pool.close()
pool.join()

recal_in = [os.path.join(outdir, x) for x in os.listdir(outdir) if '.mgf' in x]
recal_in = [os.path.join(outdir, x) for x in os.listdir(outdir) if x.endswith('.mgf') and not x.startswith('recal_')]
if recal:
# pool = Pool(processes=nthr)
if not os.path.exists(outdir):
Expand Down
Binary file added preprocessing.pyc
View file
Open in desktop
Binary file not shown.
2 changes: 1 addition & 1 deletion preprocessing_ms2recal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -300,7 +300,7 @@ def process_file(filepath, outdir, mscon_settings, split_acq, detector_filter, m
pool.close()
pool.join()

recal_in = [os.path.join(outdir, x) for x in os.listdir(outdir) if '.mgf' in x]
recal_in = [os.path.join(outdir, x) for x in os.listdir(outdir) if x.endswith('.mgf') and not x.startswith('recal_')]
if recal:
# pool = Pool(processes=nthr)
if not os.path.exists(outdir):
Expand Down