✨ DataFrame and csv format for MQ parameters

- potential: allow to combine MaxQuant parameter files
- easy to inspect csv parameter file

ToDo:
- could update the 4th index level to reflect some of the groups
 -> see comments in maxquant.py

proteobench/io/params/maxquant.py

@@ -1,11 +1,14 @@
 """Functionality to parse Maxqunt mqpar.xml parameter files"""
 from __future__ import annotations
 
+import collections
 import json
 import logging
 import xml.etree.ElementTree as ET
 from pathlib import Path
 
+import pandas as pd
+
 logger = logging.getLogger()
 
 
@@ -82,6 +85,48 @@ def read_file(file: str) -> dict:
     return params
 
 
+def flatten_dict_of_dicts(d: dict, parent_key: str = "") -> dict:
+    """Build tuples for nested dictionaries for use as `pandas.MultiIndex`.
+
+    Parameters
+    ----------
+    d : dict
+        Nested dictionary for which all keys are flattened to tuples.
+    parent_key : str, optional
+        Outer key (used for recursion), by default ''
+
+    Returns
+    -------
+    dict
+        Flattend dictionary with tuple keys: {(outer_key, ..., inner_key) : value}
+    """
+    # simplified and adapted from: https://stackoverflow.com/a/6027615/9684872
+    items = []
+    for k, v in d.items():
+        new_key = parent_key + (k,) if parent_key else (k,)
+        if isinstance(v, collections.abc.MutableMapping):
+            items.extend(flatten_dict_of_dicts(v, parent_key=new_key))
+        elif isinstance(v, list):
+            for item in v:
+                if isinstance(item, collections.abc.MutableMapping):
+                    items.extend(flatten_dict_of_dicts(item, parent_key=new_key))
+                elif isinstance(item, str):
+                    items.append((new_key, item))
+                else:
+                    raise ValueError(f"Unknown item: {item:r}")
+        else:
+            items.append((new_key, v))
+    return items
+
+
+def build_Series_from_records(records, index_length=4):
+    records = flatten_dict_of_dicts(records)
+    idx = pd.MultiIndex.from_tuples(
+        (extend_tuple(k, index_length) for (k, v) in records)
+    )
+    return pd.Series((v for (k, v) in records), index=idx)
+
+
 # create a first version of json files to match
 if __name__ == "__main__":
     for test_file in [
@@ -101,3 +146,26 @@ def read_file(file: str) -> dict:
                 )
             )
         )
+        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

test/params/mqpar1.5.3.30_MBR.csv

@@ -0,0 +1,204 @@
+,,,,run_identifier
+name,,,,Session1
+maxQuantVersion,,,,1.5.3.30
+tempFolder,,,,
+numThreads,,,,3
+sendEmail,,,,false
+fixedCombinedFolder,,,,
+ionCountIntensities,,,,false
+verboseColumnHeaders,,,,false
+fullMinMz,,,,-1.7976931348623157E+308
+fullMaxMz,,,,1.7976931348623157E+308
+calcPeakProperties,,,,false
+showCentroidMassDifferences,,,,false
+showIsotopeMassDifferences,,,,false
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_01.raw"
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_02.raw"
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_A_Sample_Alpha_03.raw"
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_01.raw"
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_02.raw"
+filePaths,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\LFQ_Orbitrap_DDA_Condition_B_Sample_Alpha_03.raw"
+experiments,string,,,A_Sample_Alpha_01
+experiments,string,,,A_Sample_Alpha_02
+experiments,string,,,A_Sample_Alpha_03
+experiments,string,,,B_Sample_Alpha_01
+experiments,string,,,B_Sample_Alpha_02
+experiments,string,,,B_Sample_Alpha_03
+fractions,short,,,32767
+fractions,short,,,32767
+fractions,short,,,32767
+fractions,short,,,32767
+fractions,short,,,32767
+fractions,short,,,32767
+paramGroupIndices,int,,,0
+paramGroupIndices,int,,,0
+paramGroupIndices,int,,,0
+paramGroupIndices,int,,,0
+paramGroupIndices,int,,,0
+paramGroupIndices,int,,,0
+parameterGroups,parameterGroup,maxCharge,,7
+parameterGroups,parameterGroup,minPeakLen,,2
+parameterGroups,parameterGroup,useMs1Centroids,,false
+parameterGroups,parameterGroup,useMs2Centroids,,false
+parameterGroups,parameterGroup,cutPeaks,,true
+parameterGroups,parameterGroup,gapScans,,1
+parameterGroups,parameterGroup,minTime,,NaN
+parameterGroups,parameterGroup,maxTime,,NaN
+parameterGroups,parameterGroup,matchType,,MatchFromAndTo
+parameterGroups,parameterGroup,centroidMatchTol,,8
+parameterGroups,parameterGroup,centroidMatchTolInPpm,,true
+parameterGroups,parameterGroup,centroidHalfWidth,,35
+parameterGroups,parameterGroup,centroidHalfWidthInPpm,,true
+parameterGroups,parameterGroup,valleyFactor,,1.4
+parameterGroups,parameterGroup,advancedPeakSplitting,,false
+parameterGroups,parameterGroup,intensityThreshold,,500
+parameterGroups,parameterGroup,msInstrument,,0
+parameterGroups,parameterGroup,intensityDetermination,,0
+parameterGroups,parameterGroup,labelMods,string,
+parameterGroups,parameterGroup,reQuantify,,false
+parameterGroups,parameterGroup,lfqSkipNorm,,false
+parameterGroups,parameterGroup,lfqMinEdgesPerNode,,3
+parameterGroups,parameterGroup,lfqAvEdgesPerNode,,6
+parameterGroups,parameterGroup,lfqMaxFeatures,,100000
+parameterGroups,parameterGroup,fastLfq,,true
+parameterGroups,parameterGroup,lfqRestrictFeatures,,false
+parameterGroups,parameterGroup,lfqMinRatioCount,,2
+parameterGroups,parameterGroup,useNormRatiosForHybridLfq,,true
+parameterGroups,parameterGroup,maxLabeledAa,,0
+parameterGroups,parameterGroup,maxNmods,,5
+parameterGroups,parameterGroup,maxMissedCleavages,,2
+parameterGroups,parameterGroup,multiplicity,,1
+parameterGroups,parameterGroup,enzymes,string,Trypsin/P
+parameterGroups,parameterGroup,enzymesFirstSearch,,
+parameterGroups,parameterGroup,useEnzymeFirstSearch,,false
+parameterGroups,parameterGroup,useVariableModificationsFirstSearch,,false
+parameterGroups,parameterGroup,variableModifications,string,Oxidation (M)
+parameterGroups,parameterGroup,variableModifications,string,Acetyl (Protein N-term)
+parameterGroups,parameterGroup,useMultiModification,,false
+parameterGroups,parameterGroup,multiModifications,,
+parameterGroups,parameterGroup,isobaricLabels,,
+parameterGroups,parameterGroup,variableModificationsFirstSearch,,
+parameterGroups,parameterGroup,hasAdditionalVariableModifications,,false
+parameterGroups,parameterGroup,additionalVariableModifications,,
+parameterGroups,parameterGroup,additionalVariableModificationProteins,,
+parameterGroups,parameterGroup,doMassFiltering,,true
+parameterGroups,parameterGroup,firstSearchTol,,20
+parameterGroups,parameterGroup,mainSearchTol,,4.5
+parameterGroups,parameterGroup,searchTolInPpm,,true
+parameterGroups,parameterGroup,isotopeMatchTol,,2
+parameterGroups,parameterGroup,isotopeMatchTolInPpm,,true
+parameterGroups,parameterGroup,isotopeTimeCorrelation,,0.6
+parameterGroups,parameterGroup,theorIsotopeCorrelation,,0.6
+parameterGroups,parameterGroup,recalibrationInPpm,,true
+parameterGroups,parameterGroup,intensityDependentCalibration,,false
+parameterGroups,parameterGroup,minScoreForCalibration,,70
+parameterGroups,parameterGroup,matchLibraryFile,,false
+parameterGroups,parameterGroup,libraryFile,,
+parameterGroups,parameterGroup,matchLibraryMassTolPpm,,0
+parameterGroups,parameterGroup,matchLibraryTimeTolMin,,0
+parameterGroups,parameterGroup,matchLabelTimeTolMin,,0
+parameterGroups,parameterGroup,reporterMassTolerance,,NaN
+parameterGroups,parameterGroup,reporterPif,,NaN
+parameterGroups,parameterGroup,filterPif,,false
+parameterGroups,parameterGroup,reporterFraction,,NaN
+parameterGroups,parameterGroup,reporterBasePeakRatio,,NaN
+parameterGroups,parameterGroup,timsHalfWidth,,0
+parameterGroups,parameterGroup,timsStep,,0
+parameterGroups,parameterGroup,timsResolution,,0
+parameterGroups,parameterGroup,timsMinMsmsIntensity,,0
+parameterGroups,parameterGroup,timsRemovePrecursor,,true
+parameterGroups,parameterGroup,crosslinkSearch,,false
+parameterGroups,parameterGroup,crosslinkMaxMonoUnsaturated,,0
+parameterGroups,parameterGroup,crosslinkMaxMonoSaturated,,0
+parameterGroups,parameterGroup,crosslinkMaxDiUnsaturated,,0
+parameterGroups,parameterGroup,crosslinkMaxDiSaturated,,0
+parameterGroups,parameterGroup,crosslinkUseSeparateFasta,,false
+parameterGroups,parameterGroup,crosslinkFastaFiles,,
+parameterGroups,parameterGroup,crosslinkMode,,PeptidesWithCleavedLinker
+parameterGroups,parameterGroup,lcmsRunType,,Standard
+parameterGroups,parameterGroup,lfqMode,,1
+parameterGroups,parameterGroup,enzymeMode,,0
+parameterGroups,parameterGroup,enzymeModeFirstSearch,,0
+fixedModifications,string,,,Carbamidomethyl (C)
+fastaFiles,string,,,"/users/user/EuBIC benchmarking
+         project\MQ15330_MBR\BenchmarkFASTAModule1_DDA_NOCONTA.fasta"
+fastaFilesFirstSearch,,,,
+fixedSearchFolder,,,,
+advancedRatios,,,,true
+rtShift,,,,false
+separateLfq,,,,false
+lfqStabilizeLargeRatios,,,,true
+lfqRequireMsms,,,,true
+decoyMode,,,,revert
+includeContaminants,,,,true
+topxWindow,,,,100
+maxPeptideMass,,,,4600
+epsilonMutationScore,,,,true
+mutatedPeptidesSeparately,,,,true
+minDeltaScoreUnmodifiedPeptides,,,,0
+minDeltaScoreModifiedPeptides,,,,6
+minScoreUnmodifiedPeptides,,,,0
+minScoreModifiedPeptides,,,,40
+secondPeptide,,,,true
+matchBetweenRuns,,,,true
+matchUnidentifiedFeatures,,,,false
+matchBetweenRunsFdr,,,,false
+dependentPeptides,,,,false
+dependentPeptideFdr,,,,0
+dependentPeptideMassBin,,,,0
+msmsConnection,,,,false
+ibaq,,,,false
+useDeltaScore,,,,false
+splitProteinGroupsByTaxonomy,,,,false
+taxonomyLevel,,,,Species
+avalon,,,,false
+ibaqLogFit,,,,false
+razorProteinFdr,,,,true
+deNovoSequencing,,,,false
+deNovoVarMods,,,,true
+massDifferenceSearch,,,,false
+minPepLen,,,,7
+peptideFdr,,,,0.01
+proteinFdr,,,,0.01
+siteFdr,,,,0.01
+minPeptideLengthForUnspecificSearch,,,,8
+maxPeptideLengthForUnspecificSearch,,,,25
+useNormRatiosForOccupancy,,,,true
+minPeptides,,,,1
+minRazorPeptides,,,,1
+minUniquePeptides,,,,0
+useCounterparts,,,,false
+advancedSiteIntensities,,,,true
+customProteinQuantification,,,,false
+customProteinQuantificationFile,,,,
+minRatioCount,,,,2
+restrictProteinQuantification,,,,true
+restrictMods,string,,,Oxidation (M)
+restrictMods,string,,,Acetyl (Protein N-term)
+matchingTimeWindow,,,,0.7
+alignmentTimeWindow,,,,20
+numberOfCandidatesMultiplexedMsms,,,,25
+numberOfCandidatesMsms,,,,15
+massDifferenceMods,,,,
+mainSearchMaxCombinations,,,,200
+msmsParamsArray,msmsParams,MatchTolerance,,20
+msmsParamsArray,msmsParams,DeisotopeTolerance,,7
+msmsParamsArray,msmsParams,DeNovoTolerance,,10
+msmsParamsArray,msmsParams,MatchTolerance,,0.5
+msmsParamsArray,msmsParams,DeisotopeTolerance,,0.15
+msmsParamsArray,msmsParams,DeNovoTolerance,,0.25
+msmsParamsArray,msmsParams,MatchTolerance,,40
+msmsParamsArray,msmsParams,DeisotopeTolerance,,0.01
+msmsParamsArray,msmsParams,DeNovoTolerance,,0.02
+msmsParamsArray,msmsParams,MatchTolerance,,0.5
+msmsParamsArray,msmsParams,DeisotopeTolerance,,0.15
+msmsParamsArray,msmsParams,DeNovoTolerance,,0.25
+compositionPrediction,,,,0
+quantMode,,,,1
+variationMode,,,,none