Merge pull request #130 from Proteobench/add_tests_parsing

✅Test MQ parameter extraction, document output

proteobench/io/params/maxquant.py

@@ -2,7 +2,6 @@
 from __future__ import annotations
 
 import collections
-import json
 import logging
 import xml.etree.ElementTree as ET
 from pathlib import Path
@@ -207,6 +206,7 @@ def extract_params(fname, ms2frac="FTMS") -> ProteoBenchParameters:
 
 # create a first version of json files to match
 if __name__ == "__main__":
+    import json
     from pprint import pprint
 
     for test_file in [
@@ -231,3 +231,8 @@ def extract_params(fname, ms2frac="FTMS") -> ProteoBenchParameters:
         record.to_csv(Path(test_file).with_suffix(".csv"))
         params = extract_params(test_file, ms2frac="FTMS")
         pprint(params.__dict__)
+        test_file = Path(test_file)
+        fname = test_file.with_suffix(".json").with_stem(test_file.stem + "_sel")
+
+        with open(fname, "w") as f:
+            json.dump(params.__dict__, f, indent=4)

test/params/mqpar1.5.3.30_MBR_sel.json

@@ -0,0 +1,21 @@
+{
+    "software_name": null,
+    "software_version": "1.5.3.30",
+    "search_engine": "Andromeda",
+    "search_engine_version": null,
+    "ident_fdr_psm": null,
+    "ident_fdr_peptide": "0.01",
+    "ident_fdr_protein": "0.01",
+    "enable_match_between_runs": "true",
+    "precursor_mass_tolerance": "4.5 ppm",
+    "fragment_mass_tolerance": "20 ppm",
+    "enzyme": "Trypsin/P",
+    "allowed_miscleavages": "2",
+    "min_peptide_length": "7",
+    "max_peptide_length": null,
+    "fixed_mods": "Carbamidomethyl (C)",
+    "variable_mods": "Oxidation (M),Acetyl (Protein N-term)",
+    "max_mods": "5",
+    "min_precursor_charge": null,
+    "max_precursor_charge": "7"
+}

test/params/mqpar_MQ1.6.3.3_MBR_sel.json

@@ -0,0 +1,21 @@
+{
+    "software_name": null,
+    "software_version": "1.6.3.3",
+    "search_engine": "Andromeda",
+    "search_engine_version": null,
+    "ident_fdr_psm": null,
+    "ident_fdr_peptide": "0.01",
+    "ident_fdr_protein": "0.01",
+    "enable_match_between_runs": "True",
+    "precursor_mass_tolerance": "4.5 ppm",
+    "fragment_mass_tolerance": "20 ppm",
+    "enzyme": "Trypsin/P",
+    "allowed_miscleavages": "2",
+    "min_peptide_length": "7",
+    "max_peptide_length": null,
+    "fixed_mods": "Carbamidomethyl (C)",
+    "variable_mods": "Oxidation (M),Acetyl (Protein N-term)",
+    "max_mods": "5",
+    "min_precursor_charge": null,
+    "max_precursor_charge": "7"
+}

test/params/mqpar_MQ2.1.3.0_noMBR_sel.json

@@ -0,0 +1,21 @@
+{
+    "software_name": null,
+    "software_version": "2.1.3.0",
+    "search_engine": "Andromeda",
+    "search_engine_version": null,
+    "ident_fdr_psm": null,
+    "ident_fdr_peptide": "0.01",
+    "ident_fdr_protein": "0.01",
+    "enable_match_between_runs": "False",
+    "precursor_mass_tolerance": "4.5 ppm",
+    "fragment_mass_tolerance": "20 ppm",
+    "enzyme": "Trypsin/P",
+    "allowed_miscleavages": "2",
+    "min_peptide_length": "7",
+    "max_peptide_length": null,
+    "fixed_mods": "Carbamidomethyl (C)",
+    "variable_mods": "Oxidation (M),Acetyl (Protein N-term)",
+    "max_mods": "5",
+    "min_precursor_charge": null,
+    "max_precursor_charge": "7"
+}

test/test_parse_params_maxquant.py

@@ -9,13 +9,13 @@
 
 TESTDATA_DIR = Path(__file__).parent / "params"
 
-mq_paras = [
+mqpar_fnames = [
     "mqpar_MQ1.6.3.3_MBR.xml",
     "mqpar_MQ2.1.3.0_noMBR.xml",
     "mqpar1.5.3.30_MBR.xml",
 ]
 
-mq_paras = [TESTDATA_DIR / mq_para for mq_para in mq_paras]
+mqpar_fnames = [TESTDATA_DIR / mq_para for mq_para in mqpar_fnames]
 
 
 parameters = [
@@ -38,7 +38,7 @@ def test_list_of_tuple_expansion():
     assert actual == expected
 
 
-parameters = [(fname, Path(fname).with_suffix(".json")) for fname in mq_paras]
+parameters = [(fname, fname.with_suffix(".json")) for fname in mqpar_fnames]
 
 
 @pytest.mark.parametrize("file,json_expected", parameters)
@@ -96,7 +96,7 @@ def test_flatten_of_dicts(dict_in, list_expected):
     assert actual == list_expected
 
 
-parameters = [(fname, Path(fname).with_suffix(".csv")) for fname in mq_paras]
+parameters = [(fname, fname.with_suffix(".csv")) for fname in mqpar_fnames]
 
 
 @pytest.mark.parametrize("file,csv_expected", parameters)
@@ -107,3 +107,17 @@ def test_file_parsing_to_csv(file, csv_expected):
     actual = actual.to_frame("run_identifier")
     actual = pd.read_csv(io.StringIO(actual.to_csv()), index_col=[0, 1, 2, 3])
     assert actual.equals(expected)
+
+
+parameters = [
+    (fname, (fname.parent / (fname.stem + "_sel.json"))) for fname in mqpar_fnames
+]
+
+
+@pytest.mark.parametrize("file,json_expected", parameters)
+def test_extract_params(file, json_expected):
+    with open(json_expected) as f:
+        expected = json.load(f)
+    actual = mq_params.extract_params(file)
+    actual = actual.__dict__
+    assert actual == expected