Skip to content

Add proper protein ids to percolator #145

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

Merged
merged 2 commits into from
Oct 10, 2024
Merged

Add proper protein ids to percolator #145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d2af5b7
Add proper protein ids to percolator
WassimG Oct 10, 2024
4e4ea3f
fix percolator tests
WassimG Oct 10, 2024
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
4 changes: 1 addition & 3 deletions spectrum_fundamentals/metrics/percolator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,9 +336,7 @@ def add_percolator_metadata_columns(self):
else:
spec_id_cols = ["RAW_FILE", "SCAN_NUMBER", "MODIFIED_SEQUENCE", "PRECURSOR_CHARGE"]
self.metrics_val["Peptide"] = self.metadata["MODIFIED_SEQUENCE"].apply(lambda x: "_." + x + "._")
self.metrics_val["Proteins"] = self.metadata[
"MODIFIED_SEQUENCE"
] # we don't need the protein ID to get PSM / peptide results, fill with peptide sequence
self.metrics_val["Proteins"] = self.metadata["PROTEINS"]

if "SCAN_EVENT_NUMBER" in self.metadata.columns:
spec_id_cols.append("SCAN_EVENT_NUMBER")
Expand Down
18 changes: 9 additions & 9 deletions tests/unit_tests/data/perc_input.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
,RAW_FILE,SCAN_NUMBER,MODIFIED_SEQUENCE,SEQUENCE,PRECURSOR_CHARGE,MASS,CALCULATED_MASS,SCORE,REVERSE,FRAGMENTATION,MASS_ANALYZER,SCAN_EVENT_NUMBER,RETENTION_TIME,PREDICTED_IRT,COLLISION_ENERGY
0,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,7978,AAIGEATRL,AAIGEATRL,2,900.50345678,900.50288029264,60.43600000000001,False,HCD,FTMS,1,0.5000000183883155,0.5000000323590892,30.0
1,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12304,AAVPRAAFL,AAVPRAAFL,2,914.53379,914.53379,34.006,True,HCD,FTMS,2,1.000000038995633,1.5000000246189773,30.0
2,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12398,AAYFGVYDTAK,AAYFGVYDTAK,2,1204.5764,1204.5764,39.97399999999999,True,HCD,FTMS,3,1.5000000993570157,2.500000056694346,30.0
3,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,11716,AAYYHPSYL,AAYYHPSYL,2,1083.5025,1083.5025,99.919,False,HCD,FTMS,4,2.0000000098074193,3.5000000203256407,30.0
4,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,87.802,False,HCD,FTMS,5,2.500000083793533,4.5000000747038005,30.0
5,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,62.802,False,HCD,FTMS,6,3.0000000338727677,5.5000000960095505,30.0
6,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,False,HCD,FTMS,7,3.500000001673834,6.5000000134594345,30.0
7,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,False,HCD,FTMS,8,4.000000066050141,7.500000085284446,30.0
,RAW_FILE,SCAN_NUMBER,MODIFIED_SEQUENCE,SEQUENCE,PRECURSOR_CHARGE,MASS,CALCULATED_MASS,SCORE,REVERSE,FRAGMENTATION,MASS_ANALYZER,SCAN_EVENT_NUMBER,RETENTION_TIME,PREDICTED_IRT,COLLISION_ENERGY,PROTEINS
0,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,7978,AAIGEATRL,AAIGEATRL,2,900.5034568,900.5028803,60.436,FALSE,HCD,FTMS,1,0.500000018,0.500000032,30,sp|O23523|RGGA_ARATH
1,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12304,AAVPRAAFL,AAVPRAAFL,2,914.53379,914.53379,34.006,TRUE,HCD,FTMS,2,1.000000039,1.500000025,30,sp|O23523|RGGA_ARATH
2,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,12398,AAYFGVYDTAK,AAYFGVYDTAK,2,1204.5764,1204.5764,39.974,TRUE,HCD,FTMS,3,1.500000099,2.500000057,30,sp|O23523|RGGA_ARATH
3,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,11716,AAYYHPSYL,AAYYHPSYL,2,1083.5025,1083.5025,99.919,FALSE,HCD,FTMS,4,2.00000001,3.50000002,30,sp|O23523|RGGA_ARATH
4,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,87.802,FALSE,HCD,FTMS,5,2.500000084,4.500000075,30,sp|O23523|RGGA_ARATH
5,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,62.802,FALSE,HCD,FTMS,6,3.000000034,5.500000096,30,sp|O23523|RGGA_ARATH
6,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,FALSE,HCD,FTMS,7,3.500000002,6.500000013,30,sp|O23523|RGGA_ARATH
7,20210122_0263_TMUCLHan_Peiru_DDA_IP_C797S_02,5174,AEDLNTRVA,AEDLNTRVA,2,987.49852,987.49852,79.802,FALSE,HCD,FTMS,8,4.000000066,7.500000085,30,sp|O23523|RGGA_ARATH
2 changes: 1 addition & 1 deletion tests/unit_tests/test_percolator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -395,7 +395,7 @@ def test_calc(self):
# np.testing.assert_almost_equal(percolator.metrics_val['ExpMass'][0], 900.50345678)
np.testing.assert_string_equal(percolator.metrics_val["Peptide"][0], "_.AAIGEATRL._")
np.testing.assert_string_equal(
percolator.metrics_val["Proteins"][0], "AAIGEATRL"
percolator.metrics_val["Proteins"][0], "sp|O23523|RGGA_ARATH"
) # we don't need the protein ID to get PSM / peptide results

# features
Expand Down