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

[WIP] Switch inspect to proforma function to use codebase #36

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

[WIP] Switch inspect to proforma function to use codebase #36

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b1b8d5e
switch inspect to proforma function to use codebase
benpullman Oct 3, 2022
edd6ad8
update to use codebase function
benpullman Oct 4, 2022
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
19 changes: 2 additions & 17 deletions tools/peptide_statistics_hpp/peptide_protein_cosine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
from itertools import chain
import explorer_export
import read_mappings
from python_ms_utilities import mapping, resources, fdr, proteosafe
from python_ms_utilities import processing, mapping, resources, fdr, proteosafe
import pandas as pd
from datetime import datetime
import requests
Expand Down Expand Up @@ -96,21 +96,6 @@ def integer_mod_mass(sequence):
mods = [int(round(float(m))) if i == 0 else -int(round(float(m))) for ms in mods.split('+') for i,m in enumerate(ms.split('-')) if m != '' ]
return sum(mods)

def add_brackets(pep):
aa_breakpoints = []
pep = pep.replace('+','[+').replace('-','[-')
for i,aa in enumerate(pep[1:]):
if not pep[i-1].isalpha() and pep[i].isalpha():
aa_breakpoints.append(i)
elif not pep[i].isalpha() and i == (len(pep)-2):
aa_breakpoints.append(i+2)
for i,breakpoint in enumerate(reversed(aa_breakpoints)):
end_bracket = ']'
if i == len(aa_breakpoints)-1 and pep[0] == '[':
end_bracket = ']-'
pep = pep[:breakpoint] + end_bracket + pep[breakpoint:]
return pep

protein_type = lambda protein, proteome: 'Contaminant' if proteome.proteins[protein].db == 'con' else ('TrEMBL' if proteome.proteins[protein].db == 'tr' else ('Canonical' if proteome.proteins[protein].iso == None else 'Isoform'))

def msv_to_pxd(msv, msv_mapping):
Expand All @@ -126,7 +111,7 @@ def correct_usi(usi_input, msv_mapping):
else:
split_usi = usi_input.split(':')
split_usi[1] = msv_to_pxd(split_usi[1], msv_mapping)
split_usi[5] = '/'.join([add_brackets(split_usi[5].split('/')[0]),split_usi[5].split('/')[1]])
split_usi[5] = '/'.join([processing.inspect_to_proforma(split_usi[5].split('/')[0]),split_usi[5].split('/')[1]])
return ':'.join(split_usi)
except:
return ''
Expand Down