msreport 0.0.26__py3-none-any.whl → 0.0.28__py3-none-any.whl

msreport/reader.py

@@ -1,4 +1,4 @@
-""" Module for reading result tables from various MS analysis tools and converting them
+"""Module for reading result tables from various MS analysis tools and converting them
 to a standardized format following the MsReport convention.
 
 Currently for MaxQuant and FragPipe protein, peptide, and ion tables are supported, and
@@ -20,19 +20,19 @@ Unified column names:
 - iBAQ intensity "sample name"
 """
 
-from collections import OrderedDict, defaultdict
 import os
-from typing import Any, Callable, Iterable, Optional, Protocol
 import pathlib
 import warnings
+from collections import OrderedDict, defaultdict
+from typing import Any, Callable, Iterable, Optional, Protocol
 
 import numpy as np
 import pandas as pd
 
 import msreport.helper as helper
-from msreport.helper.temp import extract_window_around_position
-from msreport.errors import ProteinsNotInFastaWarning
 import msreport.peptidoform
+from msreport.errors import ProteinsNotInFastaWarning
+from msreport.helper.temp import extract_window_around_position
 
 
 class Protein(Protocol):
@@ -54,6 +54,8 @@ class ProteinDatabase(Protocol):
 class ResultReader:
     """Base Reader class, is by itself not functional."""
 
+    data_directory: str
+    filenames: dict[str, str]
     default_filenames: dict[str, str]
     protected_columns: list[str]
     column_mapping: dict[str, str]
@@ -61,8 +63,8 @@ class ResultReader:
     sample_column_tags: list[str]
 
     def __init__(self):
-        self.data_directory: str = ""
-        self.filenames: dict[str, str] = {}
+        self.data_directory = ""
+        self.filenames = {}
 
     def _read_file(self, which: str, sep: str = "\t") -> pd.DataFrame:
         """Read a result table.
@@ -183,18 +185,16 @@ class MaxQuantReader(ResultReader):
         "MS/MS count",
         "Sequence coverage",
     ]
-    column_mapping: dict[str, str] = dict(
-        [
-            ("Peptides", "Total peptides"),
-            ("Sequence coverage [%]", "Sequence coverage"),
-            ("MS/MS count", "Spectral count Combined"),  # proteinGroups, evidence
-            ("MS/MS Count", "Spectral count Combined"),  # peptides
-            ("Sequence", "Peptide sequence"),  # peptides, evidence
-            ("Sequence length", "Protein length"),
-            ("Mol. weight [kDa]", "Molecular weight [kDa]"),
-            ("Experiment", "Sample"),
-        ]
-    )
+    column_mapping: dict[str, str] = {
+        "Peptides": "Total peptides",
+        "Sequence coverage [%]": "Sequence coverage",
+        "MS/MS count": "Spectral count Combined",  # proteinGroups, evidence
+        "MS/MS Count": "Spectral count Combined",  # peptides
+        "Sequence": "Peptide sequence",  # peptides, evidence
+        "Sequence length": "Protein length",
+        "Mol. weight [kDa]": "Molecular weight [kDa]",
+        "Experiment": "Sample",
+    }
     column_tag_mapping: OrderedDict[str, str] = OrderedDict(
         [("MS/MS count", "Spectral count"), ("iBAQ", "iBAQ intensity")]
     )
@@ -590,20 +590,18 @@ class FragPipeReader(ResultReader):
         "Intensity",
         "MaxLFQ Intensity",
     ]
-    column_mapping: dict[str, str] = dict(
-        [
-            ("Peptide Sequence", "Peptide sequence"),  # Peptide and ion
-            ("Modified Sequence", "Modified sequence"),  # Modified peptide and ion
-            ("Start", "Start position"),  # Peptide and ion
-            ("End", "End position"),  # Peptide and ion
-            ("Combined Total Peptides", "Total peptides"),  # From LFQ
-            ("Total Peptides", "Total peptides"),  # From TMT
-            ("Description", "Protein name"),
-            ("Protein Length", "Protein length"),
-            ("Entry Name", "Protein entry name"),
-            ("Gene", "Gene name"),
-        ]
-    )
+    column_mapping: dict[str, str] = {
+        "Peptide Sequence": "Peptide sequence",  # Peptide and ion
+        "Modified Sequence": "Modified sequence",  # Modified peptide and ion
+        "Start": "Start position",  # Peptide and ion
+        "End": "End position",  # Peptide and ion
+        "Combined Total Peptides": "Total peptides",  # From LFQ
+        "Total Peptides": "Total peptides",  # From TMT
+        "Description": "Protein name",
+        "Protein Length": "Protein length",
+        "Entry Name": "Protein entry name",
+        "Gene": "Gene name",
+    }
     column_tag_mapping: OrderedDict[str, str] = OrderedDict(
         [
             ("MaxLFQ Intensity", "LFQ intensity"),
@@ -1038,40 +1036,32 @@ class SpectronautReader(ResultReader):
         "design": "conditionsetup",
     }
     protected_columns: list[str] = []
-    column_mapping: dict[str, str] = dict(
-        [
-            ("R.FileName", "Filename"),
-            ("R.Label", "Sample"),
-            ("PG.Qvalue", "Protein qvalue"),
-            ("PG.Cscore", "Protein cscore"),
-            ("PG.NrOfStrippedSequencesIdentified (Experiment-wide)", "Total peptides"),
-            ("PG.NrOfPrecursorsIdentified (Experiment-wide)", "Total ions"),
-            ("PG.Cscore", "Cscore"),
-            ("PEP.StrippedSequence", "Peptide sequence"),
-            ("PEP.AllOccurringProteinAccessions", "Mapped proteins"),
-            ("EG.ModifiedSequence", "Modified sequence"),
-            ("EG.CompensationVoltage", "Compensation voltage"),
-            ("EG.Qvalue", "Qvalue"),
-            ("EG.ApexRT", "Apex retention time"),
-            ("EG.DatapointsPerPeak", "Datapoints per peak"),
-            ("EG.FWHM", "FWHM"),
-            ("EG.SignalToNoise", "Signal to noise"),
-            ("FG.FragmentCount", "Fragment count"),
-            ("FG.Charge", "Charge"),
-            ("FG.MS1Quantity", "MS1 intensity"),
-            ("FG.MS1RawQuantity", "MS1 raw intensity"),
-            ("FG.MS2Quantity", "MS2 intensity"),
-            ("FG.MS2RawQuantity", "MS2 raw intensity"),
-            ("FG.MeasuredMz", "Observed m/z"),
-            ("FG.TheoreticalMz", "Theoretical m/z"),
-            ("FG.CalibratedMz", "Calibrated m/z"),
-            # ("PG.ProteinAccessions", ""),
-            # ("EG.HasLocalizationInformation", ""),
-            # ("EG.PTMLocalizationProbabilities", ""),
-            # ("EG.UsedForProteinGroupQuantity", ""),
-            # Modified peptides need to be parsed and rewritten
-        ]
-    )
+    column_mapping: dict[str, str] = {
+        "R.FileName": "Filename",
+        "R.Label": "Sample",
+        "PG.Qvalue": "Protein qvalue",
+        "PG.Cscore": "Protein cscore",
+        "PG.NrOfStrippedSequencesIdentified (Experiment-wide)": "Total peptides",
+        "PG.NrOfPrecursorsIdentified (Experiment-wide)": "Total ions",
+        "PEP.StrippedSequence": "Peptide sequence",
+        "PEP.AllOccurringProteinAccessions": "Mapped proteins",
+        "EG.ModifiedSequence": "Modified sequence",
+        "EG.CompensationVoltage": "Compensation voltage",
+        "EG.Qvalue": "Qvalue",
+        "EG.ApexRT": "Apex retention time",
+        "EG.DatapointsPerPeak": "Datapoints per peak",
+        "EG.FWHM": "FWHM",
+        "EG.SignalToNoise": "Signal to noise",
+        "FG.FragmentCount": "Fragment count",
+        "FG.Charge": "Charge",
+        "FG.MS1Quantity": "MS1 intensity",
+        "FG.MS1RawQuantity": "MS1 raw intensity",
+        "FG.MS2Quantity": "MS2 intensity",
+        "FG.MS2RawQuantity": "MS2 raw intensity",
+        "FG.MeasuredMz": "Observed m/z",
+        "FG.TheoreticalMz": "Theoretical m/z",
+        "FG.CalibratedMz": "Calibrated m/z",
+    }
     sample_column_tags: list[str] = [
         ".PG.NrOfPrecursorsIdentified",
         ".PG.IBAQ",
@@ -1324,7 +1314,7 @@ class SpectronautReader(ResultReader):
         filename: Optional[str] = None,
         filetag: Optional[str] = None,
         rename_columns: bool = True,
-    ) -> None:
+    ) -> pd.DataFrame:
         """Reads an ion evidence file (long format) and returns a processed dataframe.
 
         Adds new columns to comply with the MsReport convention. "Protein reported
@@ -1462,7 +1452,7 @@ def sort_leading_proteins(
     if penalize_contaminants is not None:
         contaminant_encoding = {"False": 0, "True": 1, False: 0, True: 1}
 
-    for idx, row in table.iterrows():
+    for _, row in table.iterrows():
         protein_ids = row["Leading proteins"].split(";")
 
         sorting_info = [[] for _ in protein_ids]
@@ -1559,6 +1549,7 @@ def add_protein_annotation(
         warnings.warn(
             f"Some proteins could not be annotated: {repr(proteins_not_in_db)}",
             ProteinsNotInFastaWarning,
+            stacklevel=2,
         )
 
     annotations = {}
@@ -1636,9 +1627,10 @@ def add_protein_site_annotation(
         warnings.warn(
             f"Some proteins could not be annotated: {repr(proteins_not_in_db)}",
             ProteinsNotInFastaWarning,
+            stacklevel=2,
         )
 
-    annotations = {
+    annotations: dict[str, list[str]] = {
         "Modified residue": [],
         "Sequence window": [],
     }
@@ -1702,6 +1694,7 @@ def add_leading_proteins_annotation(
         warnings.warn(
             f"Some proteins could not be annotated: {repr(proteins_not_in_db)}",
             ProteinsNotInFastaWarning,
+            stacklevel=2,
         )
 
     annotations = {}
@@ -1853,7 +1846,7 @@ def add_peptide_positions(
             find matching entries in the FASTA files.
     """
     # not tested #
-    peptide_positions = {"Start position": [], "End position": []}
+    peptide_positions: dict[str, list[int]] = {"Start position": [], "End position": []}
     proteins_not_in_db = []
     for peptide, protein_id in zip(table[peptide_column], table[protein_column]):
         if protein_id in protein_db:
@@ -1875,6 +1868,7 @@ def add_peptide_positions(
         warnings.warn(
             f"Some peptides could not be annotated: {repr(proteins_not_in_db)}",
             ProteinsNotInFastaWarning,
+            stacklevel=2,
         )
 
 
@@ -1894,10 +1888,10 @@ def add_protein_modifications(table: pd.DataFrame):
             for peptide_site, mod in [m.split(":") for m in mod_entry.split(";")]:
                 protein_site = int(peptide_site) + start_pos - 1
                 protein_mods.append([str(protein_site), mod])
-            protein_mods = ";".join([f"{pos}:{mod}" for pos, mod in protein_mods])
+            protein_mod_string = ";".join([f"{pos}:{mod}" for pos, mod in protein_mods])
         else:
-            protein_mods = ""
-        protein_modification_entries.append(protein_mods)
+            protein_mod_string = ""
+        protein_modification_entries.append(protein_mod_string)
     table["Protein modifications"] = protein_modification_entries
 
 
@@ -2074,7 +2068,7 @@ def _process_protein_entries(
         A dataframe containing the columns "Protein reported by software",
         "Leading proteins", "Representative protein", and "Potential contaminant".
     """
-    new_entries = {
+    new_entries: dict[str, list[str | bool]] = {
         "Protein reported by software": [],
         "Representative protein": [],
         "Potential contaminant": [],
@@ -2189,7 +2183,7 @@ def extract_fragpipe_localization_probabilities(localization_entry: str) -> dict
     ... )
     {'15.9949': {3: 1.0}, '79.9663': {4: 0.334, 6: 0.666}}
     """
-    modification_probabilities = {}
+    modification_probabilities: dict[str, dict[int, float]] = {}
     for modification_entry in filter(None, localization_entry.split(";")):
         specified_modification, probability_sequence = modification_entry.split("@")
         _, modification = specified_modification.split(":")
@@ -2247,7 +2241,7 @@ def _create_protein_annotations_from_db(
     protein_db: ProteinDatabase,
     query_function: Callable,
     default_value: Any,
-) -> list[str]:
+) -> list[Any]:
     """Returns a list of multi protein entry annotations.
 
     Used to generate protein annotations for protein entries. For each protein id an
@@ -2274,9 +2268,9 @@ def _create_protein_annotations_from_db(
         if protein_id in protein_db:
             db_entry = protein_db[protein_id]
             query_result = query_function(db_entry, default_value)
+            annotation_values.append(query_result)
         else:
-            query_result = default_value
-        annotation_values.append(query_result)
+            annotation_values.append(default_value)
     return annotation_values
 
 

msreport/rinterface/__init__.py

@@ -1,3 +1,4 @@
-""" Python interface to custome R scripts. """
+"""Python interface to custome R scripts."""
+
 from .limma import multi_group_limma, two_group_limma
 from .rinstaller import r_package_version

msreport/rinterface/limma.py

@@ -1,4 +1,5 @@
-""" Python interface to custome R scripts. """
+"""Python interface to custome R scripts."""
+
 import os
 
 import pandas as pd

msreport/rinterface/rinstaller.py

@@ -1,9 +1,9 @@
-from rpy2.robjects.packages import importr
-import rpy2.robjects.packages as rpackages
 import rpy2.robjects as robjects
+import rpy2.robjects.packages as rpackages
+from rpy2.robjects.packages import importr
 
 
-def r_package_version(package_name: str) -> (str, str):
+def r_package_version(package_name: str) -> str:
     """Returns the version number of an installed R package."""
     with robjects.conversion.localconverter(robjects.default_converter):
         utils = importr("utils")

{msreport-0.0.26.dist-info → msreport-0.0.28.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.26
+Version: 0.0.28
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0
@@ -19,11 +19,15 @@ Requires-Dist: pandas>=1.4.4
 Requires-Dist: profasta>=0.0.4
 Requires-Dist: pyteomics>=4.6.0
 Requires-Dist: pyyaml>=6.0.0
-Requires-Dist: rpy2>=3.5.3
+Requires-Dist: rpy2!=3.5.13,>=3.5.3
 Requires-Dist: scikit-learn>=1.0.0
 Requires-Dist: scipy>=1.9.1
 Requires-Dist: seaborn>=0.12.0
 Requires-Dist: statsmodels>=0.13.2
+Requires-Dist: typing_extensions>=4
+Provides-Extra: dev
+Requires-Dist: mypy>=1.15.0; extra == "dev"
+Requires-Dist: pytest>=8.3.5; extra == "dev"
 Dynamic: license-file
 
 [![Project Status: WIP – Initial development is in progress, but there has not yet been a stable, usable release suitable for the public.](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)
@@ -117,7 +121,7 @@ command as described above.
 ### Additional requirements
 
 MsReport provides an interface to the R package LIMMA for differential expression
-analysis, which requires a local installation of R (R version 3.4 or higher) and the
+analysis, which requires a local installation of R (R version 4.0 or higher) and the
 system environment variable "R_HOME" to be set to the R home directory. Note that it
 might be necessary to restart the computer after adding the "R_HOME" variable. The R
 home directory can also be found from within R by using the command below, and might

msreport-0.0.28.dist-info/RECORD

@@ -0,0 +1,38 @@
+msreport/__init__.py,sha256=5-d_i-t9A3MV7hC-3z_vcWzaSAJSGY5T6McCBr4UGfc,339
+msreport/analyze.py,sha256=zNs0Vc2ODTfdiX6rSr79jXLJIh-6N11WH-vZpQzKDTE,30889
+msreport/errors.py,sha256=algGlR5iD9Q0U6Q3m25IwZryl9smtlPHsfhAL35PChc,295
+msreport/export.py,sha256=YvY3Nly5JC2CUM-JY1gydU1g2eqnennzToZfQQ5phO0,20156
+msreport/fasta.py,sha256=eXTmA4WGX4dT9wcTw7AdrvybLWG47p7ur48CxIjxjfg,1161
+msreport/impute.py,sha256=bf2Zy8VQNJ0Oh1sKn84Xp9iV5svi_Hp7iHxwRrFBwsI,10327
+msreport/isobar.py,sha256=m6NhLaKBiItIXuBhly_z2wEslxQGFC2f3-e1bzYXB78,6575
+msreport/normalize.py,sha256=K1x3DjL5Rep3t_eDIKIghMr0sAJiROnX6skHnOMPZ_k,20160
+msreport/peptidoform.py,sha256=26USj6WPrMgMIc7LttQ2n6Oq5jo1o7ayUQLR6gsRmZY,12015
+msreport/qtable.py,sha256=0e-TXmuiKBU6W5TL3tz06nNrjtEyT-CI9bvUq8W6qME,26768
+msreport/reader.py,sha256=ja4q8XtOHR_A6RL8ho-c6aGCVu1kzyhvil8ymiPx3PY,104612
+msreport/aggregate/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+msreport/aggregate/condense.py,sha256=eIh5A3RUvXrmoFUjRXagiPl0m-ucuRwYD8kDBI7voVs,5862
+msreport/aggregate/pivot.py,sha256=rn8li-FrtOZS4oWA8COk0uV2m71GCEbNu1ALNoMuHOA,5081
+msreport/aggregate/summarize.py,sha256=aYXi_i7MkqjA8k9WWpOgn029TeJ3H5Qo899msDVw89M,12165
+msreport/helper/__init__.py,sha256=UbBHKMcapSXCyNmfQm6rg-2OgS303txkgILtboE05KI,535
+msreport/helper/calc.py,sha256=J4XltEnMrFR9IQlPtrZhyxlSTj15072huHCMA_nqQ6E,4245
+msreport/helper/maxlfq.py,sha256=EP1UjV3IAz4NSpGOQSsWGbuxtGLmtw92dvXUwgBYmF0,14943
+msreport/helper/table.py,sha256=x-Wo8mTENsUxc_gtF-wgOyQa9g7W2fK6tuRiEX7bda0,11430
+msreport/helper/temp.py,sha256=jNulgDATf9sKXEFWMXAhjflciOZPAqlxg_7QZS7IkW8,3736
+msreport/plot/__init__.py,sha256=SnoQORfrjgz9SmqPZ-1J1aeVC5xu-cFfZINP4aYVCmY,1488
+msreport/plot/_partial_plots.py,sha256=tqZTSXEPuruMgVakaGR2tUQl5OrHgo2cROJ0S4cqkR0,5598
+msreport/plot/comparison.py,sha256=J8zWyQrzx7rxDLxeZQkfAlcSmLY3e_7wwPG-cGuWo2M,18564
+msreport/plot/distribution.py,sha256=a2Rw6HxQwGfDwRSy8dwpT7zvEQ968wYHjcVPOdXI3l8,10150
+msreport/plot/multivariate.py,sha256=0xzxggqbIGQYOfgiij93DTRWfG6GvvhqI9u1GNPHarY,13111
+msreport/plot/quality.py,sha256=dIo_dpdexEN_vp35WpUTt626E-QJ2qNbJmjUai_8uck,15861
+msreport/plot/style.py,sha256=67jWf4uA1ub9RJDu4xhuSoXAW0lbLj6SMP4QXQO76Pc,10591
+msreport/plot/style_sheets/msreport-notebook.mplstyle,sha256=SPYO_7vYT8Ha7tQ0KCTLtykiRQ13-_igAm7kyvsZj1I,1266
+msreport/plot/style_sheets/seaborn-whitegrid.mplstyle,sha256=eC8Zboy8R7ybBwbHPKvKbMIHACystN6X6I0lqm7B80U,833
+msreport/rinterface/__init__.py,sha256=g29j2cIrc71qBdF4Zys51feoXlC0dP6YcTIscPTqPdI,146
+msreport/rinterface/limma.py,sha256=fxYRUkkJKI-JpDvivjWj8bUS0ug7RRTMnaf2UOgRsXQ,5421
+msreport/rinterface/rinstaller.py,sha256=AGs6NFMSwTLrzrIJz1E5BE5jFUz8eQBHlpM_MWVChzA,1370
+msreport/rinterface/rscripts/limma.R,sha256=gr_yjMm_YoG45irDhWOo6gkRQSTwj_7uU_p3NBRHPm8,4331
+msreport-0.0.28.dist-info/licenses/LICENSE.txt,sha256=Pd-b5cKP4n2tFDpdx27qJSIq0d1ok0oEcGTlbtL6QMU,11560
+msreport-0.0.28.dist-info/METADATA,sha256=IVyUd3ZATwccffCWbgYYmUmPe8Y4vJvwZC6oMFuBBfw,5497
+msreport-0.0.28.dist-info/WHEEL,sha256=ck4Vq1_RXyvS4Jt6SI0Vz6fyVs4GWg7AINwpsaGEgPE,91
+msreport-0.0.28.dist-info/top_level.txt,sha256=Drl8mCckJHFIw-Ovh5AnyjKnqvLJltDOBUr1JAcHAlI,9
+msreport-0.0.28.dist-info/RECORD,,