🚧 start extracting MQ params

- most selected parameters are easy to get
- differences between version 1.6 and higher to previous (1.5)
- fragment_mass_tolerance
   -> which fragenation method was used?
   -> missing information in extracted data for v1.5

proteobench/io/params/maxquant.py

@@ -7,8 +7,11 @@
 import xml.etree.ElementTree as ET
 from pathlib import Path
 
+import numpy as np
 import pandas as pd
 
+from proteobench.io.params import ProteoBenchParameters
+
 logger = logging.getLogger()
 
 
@@ -127,45 +130,90 @@ def build_Series_from_records(records, index_length=4):
     return pd.Series((v for (k, v) in records), index=idx)
 
 
+# %%
+def extract_params(fname) -> ProteoBenchParameters:
+    params = ProteoBenchParameters()
+
+    record = read_file(fname)
+    record = build_Series_from_records(record, 4).sort_index()
+    params.search_engine = "Andromeda"
+    params.software_version = record.loc["maxQuantVersion"].squeeze()
+    params.ident_fdr_psm = None
+    params.ident_fdr_peptide = record.loc["peptideFdr"].squeeze()
+    params.ident_fdr_protein = record.loc["proteinFdr"].squeeze()
+    params.enable_match_between_runs = record.loc["matchBetweenRuns"].squeeze()
+    precursor_mass_tolerance = record.loc[
+        pd.IndexSlice["parameterGroups", "parameterGroup", "mainSearchTol", :]
+    ].squeeze()
+    params.precursor_mass_tolerance = f"{precursor_mass_tolerance} ppm"
+    fragment_mass_tolerance = None  # ! differences between version >1.6 and <=1.5
+    params.fragment_mass_tolerance = fragment_mass_tolerance
+    params.enzyme = record.loc[
+        ("parameterGroups", "parameterGroup", "enzymes", "string")
+    ].squeeze()
+    params.allowed_miscleavages = record.loc[
+        pd.IndexSlice["parameterGroups", "parameterGroup", "maxMissedCleavages", :]
+    ].squeeze()
+    params.min_peptide_length = record.loc["minPepLen"].squeeze()
+    params.max_peptide_length = None
+    # fixed mods
+    if params.software_version > "1.6.0.0":
+        fixed_mods = record.loc[
+            pd.IndexSlice["parameterGroups", "parameterGroup", "fixedModifications", :]
+        ].squeeze()
+        if isinstance(fixed_mods, str):
+            params.fixed_mods = fixed_mods
+        else:
+            params.fixed_mods = ",".join(fixed_mods)
+    else:
+        fixed_mods = record.loc[
+            pd.IndexSlice["fixedModifications", :]
+        ].squeeze()
+        if isinstance(fixed_mods, str):
+            params.fixed_mods = fixed_mods
+        else:
+            params.fixed_mods = ",".join(fixed_mods)
+
+    variable_mods = record.loc[
+        pd.IndexSlice["parameterGroups", "parameterGroup", "variableModifications", :]
+    ].squeeze()
+    if isinstance(variable_mods, str):
+        params.variable_mods = variable_mods
+    else:
+        params.variable_mods = ",".join(variable_mods)
+    params.max_mods = record.loc[
+        ("parameterGroups", "parameterGroup", "maxNmods")
+    ].squeeze()
+    params.min_precursor_charge = None
+    params.max_precursor_charge = record.loc[
+        pd.IndexSlice["parameterGroups", "parameterGroup", "maxCharge", :]
+    ].squeeze()
+    return params
+
+
 # create a first version of json files to match
 if __name__ == "__main__":
+    from pprint import pprint
+
     for test_file in [
         "../../../test/params/mqpar_MQ1.6.3.3_MBR.xml",
         "../../../test/params/mqpar_MQ2.1.3.0_noMBR.xml",
         "../../../test/params/mqpar1.5.3.30_MBR.xml",
     ]:
         print(f"{test_file = }")
-        record_example = read_file(test_file)
+        record = read_file(test_file)
         (
             Path(test_file)
             .with_suffix(".json")
             .write_text(
                 json.dumps(
-                    record_example,
+                    record,
                     indent=4,
                 )
             )
         )
-        flattend = build_Series_from_records(record_example, 4)
-        flattend = flattend.to_frame("run_identifier")
-        flattend.to_csv(Path(test_file).with_suffix(".csv"))
-
-    # %%
-    int(
-        flattend.loc["parameterGroups"]
-        .loc["parameterGroup"]
-        .loc["firstSearchTol"]
-        .squeeze()
-    )
-
-    # %%
-    # ! Parse msmsParamsArray
-    ms2_params = (
-        flattend.loc["msmsParamsArray"].loc["msmsParams"].reset_index(-1, drop=True)
-    )
-    ms2_params.loc["Name", "mode"] = ms2_params.loc["Name"].squeeze()
-    ms2_params["mode"] = ms2_params["mode"].fillna(method="ffill")
-    ms2_params = ms2_params.set_index("mode", append=True)
-    ms2_params.loc[("MatchTolerance", "FTMS")]
-    # ? reset_index level -1
-    # ? update and fillna -> then set as index again
+        record = build_Series_from_records(record, 4)
+        record = record.to_frame("run_identifier")
+        # flattend.to_csv(Path(test_file).with_suffix(".csv"))
+        params = extract_params(test_file)
+        pprint(params.__dict__)