msreport 0.0.29__py3-none-any.whl → 0.0.30__py3-none-any.whl

msreport/__init__.py

@@ -8,4 +8,4 @@ from msreport.fasta import import_protein_database
 from msreport.qtable import Qtable
 from msreport.reader import FragPipeReader, MaxQuantReader, SpectronautReader
 
-__version__ = "0.0.29"
+__version__ = "0.0.30"

msreport/plot/distribution.py

@@ -204,7 +204,8 @@ def experiment_ratios(
     mask = np.all([(qtable.data[f"Events {exp}"] > 0) for exp in experiments], axis=0)
     if exclude_invalid:
         mask = mask & qtable["Valid"]
-    experiment_data = experiment_data[mask]
+    # Use `mask.to_numpy` to solve issue with different indices of mask and dataframe
+    experiment_data = experiment_data[mask.to_numpy()]
     pseudo_reference = np.nanmean(experiment_data, axis=1)
     ratio_data = experiment_data.subtract(pseudo_reference, axis=0)
 

msreport/qtable.py

@@ -27,13 +27,11 @@ class Qtable:
         design: A pandas.DataFrame describing the experimental design.
     """
 
-    _default_id_column = "Representative protein"
-
     def __init__(
         self,
         data: pd.DataFrame,
-        design: Optional[pd.DataFrame] = None,
-        id_column: str = "Representative protein",
+        design: pd.DataFrame,
+        id_column: str,
     ):
         """Initializes the Qtable.
 
@@ -42,12 +40,13 @@ class Qtable:
 
         Args:
             data: A dataframe containing quantitative proteomics data in a wide format.
+                The index of the dataframe must contain unique values.
             design: A dataframe describing the experimental design that must at least
                 contain the columns "Sample" and "Experiment". The "Sample" entries
                 should correspond to the Sample names present in the quantitative
                 columns of the data.
             id_column: The name of the column that contains the unique identifiers for
-                the entries in the data table. Default is "Representative protein".
+                the entries in the data table.
 
         Raises:
             KeyError: If the specified id_column is not found in data.
@@ -76,8 +75,7 @@ class Qtable:
         self._id_column = id_column
         if "Valid" not in self.data.columns:
             self.data["Valid"] = True
-        if design is not None:
-            self.add_design(design)
+        self.add_design(design)
 
         self._expression_columns: list[str] = []
         self._expression_features: list[str] = []
@@ -438,6 +436,11 @@ class Qtable:
 
         Returns:
             An instance of Qtable loaded from the specified files.
+
+        Raises:
+            ValueError: If the loaded config file does not contain the
+                "Unique ID column" key. This is due to the qtable being saved with a
+                version of msreport <= 0.0.27.
         """
         filepaths = _get_qtable_export_filepaths(directory, basename)
         with open(filepaths["config"]) as openfile:
@@ -458,13 +461,20 @@ class Qtable:
                 filepaths["design"], sep="\t", index_col=0, keep_default_na=True
             )
 
-        qtable = Qtable(data, design)
+        if "Unique ID column" not in config_data:
+            # Mention that the qtable was likely saved with a version of msreport <= 0.0.27
+            raise ValueError(
+                "The qtable config file does not contain the 'Unique ID column' key. "
+                "This is likely due to the qtable being saved with a version of "
+                "msreport <= 0.0.27."
+            )
+        id_column = config_data["Unique ID column"]
+
+        qtable = Qtable(data, design, id_column)
         qtable._expression_columns = config_data["Expression columns"]
         qtable._expression_features = config_data["Expression features"]
         qtable._expression_sample_mapping = config_data["Expression sample mapping"]
         # This check is required for backwards compatibility with msreport <= 0.0.27
-        if "Unique ID column" in config_data:
-            qtable._id_column = config_data["Unique ID column"]
         return qtable
 
     def to_tsv(self, path: str, index: bool = False):
@@ -570,7 +580,7 @@ class Qtable:
         self._expression_sample_mapping = {}
 
     def __copy__(self) -> Qtable:
-        new_instance = Qtable(self.data, self.design)
+        new_instance = Qtable(self.data, self.design, self.id_column)
         # Copy all private attributes
         for attr in dir(self):
             if (

msreport/reader.py

@@ -541,6 +541,8 @@ class FragPipeReader(ResultReader):
     """FragPipe result reader.
 
     Methods:
+        import_design: Reads a "fragpipe-files.fp-manifest" file and returns a
+            processed design dataframe.
         import_proteins: Reads a "combined_protein.tsv" or "protein.tsv" file and
             returns a processed dataframe, conforming to the MsReport naming
             convention.
@@ -583,12 +585,19 @@ class FragPipeReader(ResultReader):
         "ions": "combined_ion.tsv",
         "ion_evidence": "ion.tsv",
         "psm_evidence": "psm.tsv",
+        "design": "fragpipe-files.fp-manifest",
     }
     isobar_filenames: dict[str, str] = {
         "proteins": "protein.tsv",
         "peptides": "peptide.tsv",
         "ions": "ion.tsv",
     }
+    sil_filenames: dict[str, str] = {
+        "proteins": "combined_protein_label_quant.tsv",
+        "peptides": "combined_modified_peptide_label_quant.tsv",
+        "ions": "combined_ion_label_quant.tsv",
+    }
+
     protected_columns: list[str] = []
     sample_column_tags: list[str] = [
         "Spectral Count",
@@ -609,6 +618,7 @@ class FragPipeReader(ResultReader):
         "Modified Sequence": "Modified sequence",  # Modified peptide and ion
         "Start": "Start position",  # Peptide and ion
         "End": "End position",  # Peptide and ion
+        "Mapped Proteins": "Mapped proteins",  # All PSM, ion, and peptide tables
         "Combined Total Peptides": "Total peptides",  # From LFQ
         "Total Peptides": "Total peptides",  # From TMT
         "Description": "Protein name",
@@ -638,7 +648,11 @@ class FragPipeReader(ResultReader):
     protein_info_tags: list[str] = []
 
     def __init__(
-        self, directory: str, isobar: bool = False, contaminant_tag: str = "contam_"
+        self,
+        directory: str,
+        isobar: bool = False,
+        sil: bool = False,
+        contaminant_tag: str = "contam_",
     ) -> None:
         """Initializes the FragPipeReader.
 
@@ -646,16 +660,69 @@ class FragPipeReader(ResultReader):
             directory: Location of the FragPipe result folder
             isobar: Set to True if quantification strategy was TMT, iTRAQ or similar;
                 default False.
+            sil: Set to True if the FragPipe result files are from a stable isotope
+                labeling experiment, such as SILAC; default False.
             contaminant_tag: Prefix of Protein ID entries to identify contaminants;
                 default "contam_".
         """
+        if sil and isobar:
+            raise ValueError("Cannot set both 'isobar' and 'sil' to True.")
         self._add_data_directory(directory)
         self._isobar: bool = isobar
+        self._sil: bool = sil
         self._contaminant_tag: str = contaminant_tag
-        if not isobar:
+        if isobar:
+            self.filenames = self.isobar_filenames
+        elif sil:
+            self.filenames = self.sil_filenames
+        else:
             self.filenames = self.default_filenames
+
+    def import_design(
+        self, filename: Optional[str] = None, sort: bool = False
+    ) -> pd.DataFrame:
+        """Reads a 'fp-manifest' file and returns a processed design dataframe.
+
+        Args:
+            filename: Allows specifying an alternative filename, otherwise the default
+                filename is used.
+            sort: If True, the design dataframe is sorted by "Experiment" and
+                "Replicate"; default False.
+
+        Returns:
+            A dataframe containing the processed design table with columns:
+            "Sample", "Experiment", "Replicate", "Rawfile".
+
+        Raises:
+            FileNotFoundError: If the specified manifest file does not exist.
+        """
+        if filename is None:
+            filepath = os.path.join(self.data_directory, self.filenames["design"])
         else:
-            self.filenames = self.isobar_filenames
+            filepath = os.path.join(self.data_directory, filename)
+        if not os.path.exists(filepath):
+            raise FileNotFoundError(
+                f"File '{filepath}' does not exist. Please check the file path."
+            )
+        fp_manifest = pd.read_csv(filepath, sep="\t", header=None, dtype=str)
+        fp_manifest.columns = ["Path", "Experiment", "Bioreplicate", "Data type"]
+
+        design = pd.DataFrame(
+            {
+                "Sample": fp_manifest["Experiment"] + "_" + fp_manifest["Bioreplicate"],
+                "Experiment": fp_manifest["Experiment"],
+                "Replicate": fp_manifest["Bioreplicate"],
+                "Rawfile": fp_manifest["Path"].apply(
+                    # Required to handle Windows and Unix style paths on either system
+                    lambda x: x.replace("\\", "/").split("/")[-1]
+                ),
+            }
+        )
+
+        if sort:
+            design.sort_values(by=["Experiment", "Replicate"], inplace=True)
+            design.reset_index(drop=True, inplace=True)
+        return design
 
     def import_proteins(
         self,
@@ -737,6 +804,7 @@ class FragPipeReader(ResultReader):
         df = self._read_file("peptides" if filename is None else filename)
         df["Protein reported by software"] = _extract_protein_ids(df["Protein"])
         df["Representative protein"] = df["Protein reported by software"]
+        df["Mapped Proteins"] = self._collect_mapped_proteins(df)
         # Note that _add_protein_entries would need to be adapted for the peptide table.
         # df = self._add_protein_entries(df)
         if rename_columns:
@@ -793,6 +861,8 @@ class FragPipeReader(ResultReader):
         #         'Indistinguishable Proteins' to the ion table.
         df["Protein reported by software"] = _extract_protein_ids(df["Protein"])
         df["Representative protein"] = df["Protein reported by software"]
+        df["Mapped Proteins"] = self._collect_mapped_proteins(df)
+
         if rename_columns:
             df = self._rename_columns(df, prefix_column_tags)
         if rewrite_modifications and rename_columns:
@@ -879,6 +949,8 @@ class FragPipeReader(ResultReader):
         #         'Indistinguishable Proteins' to the ion table.
         df["Protein reported by software"] = _extract_protein_ids(df["Protein"])
         df["Representative protein"] = df["Protein reported by software"]
+        df["Mapped Proteins"] = self._collect_mapped_proteins(df)
+
         if rename_columns:
             df = self._rename_columns(df, prefix_column_tags)
         if rewrite_modifications and rename_columns:
@@ -928,23 +1000,7 @@ class FragPipeReader(ResultReader):
 
         df["Protein reported by software"] = _extract_protein_ids(df["Protein"])
         df["Representative protein"] = df["Protein reported by software"]
-        df["Mapped Proteins"] = df["Mapped Proteins"].astype(str).replace("nan", "")
-
-        # FP only lists additional mapped proteins in the "Mapped Proteins" column
-        # MsReport reports all matching proteins in the "Mapped proteins" column
-        mapped_proteins_entries = []
-        for protein, mapped_protein_fp in zip(
-            df["Representative protein"], df["Mapped Proteins"], strict=True
-        ):
-            if mapped_protein_fp == "":
-                mapped_proteins = [protein]
-            else:
-                additional_mapped_proteins = msreport.reader._extract_protein_ids(
-                    mapped_protein_fp.split(", ")
-                )
-                mapped_proteins = [protein] + additional_mapped_proteins
-            mapped_proteins_entries.append(";".join(mapped_proteins))
-        df["Mapped proteins"] = mapped_proteins_entries
+        df["Mapped Proteins"] = self._collect_mapped_proteins(df)
 
         if rename_columns:
             df = self._rename_columns(df, prefix_tag=True)
@@ -980,6 +1036,35 @@ class FragPipeReader(ResultReader):
             df[key] = protein_entry_table[key]
         return df
 
+    def _collect_mapped_proteins(self, df: pd.DataFrame) -> list[str]:
+        """Generates a list of mapped proteins entries.
+
+        This method extracts protein IDs from the 'Representative protein' and the
+        'Mapped Proteins' column and combines them into a single string for each row,
+        where multiple protein IDs are separated by semicolons.
+
+        Args:
+            df: DataFrame containing the 'Mapped Proteins' column.
+
+        Returns:
+            A list of mapped proteins entries.
+        """
+        mapped_proteins_entries = []
+        for protein, mapped_protein_fp in zip(
+            df["Representative protein"],
+            df["Mapped Proteins"].astype(str).replace("nan", ""),
+            strict=True,
+        ):
+            if mapped_protein_fp == "":
+                mapped_proteins = [protein]
+            else:
+                additional_mapped_proteins = msreport.reader._extract_protein_ids(
+                    mapped_protein_fp.split(", ")
+                )
+                mapped_proteins = [protein] + additional_mapped_proteins
+            mapped_proteins_entries.append(";".join(mapped_proteins))
+        return mapped_proteins_entries
+
     def _collect_leading_protein_entries(self, df: pd.DataFrame) -> list[list[str]]:
         """Generates a list of leading protein entries.
 
@@ -995,6 +1080,9 @@ class FragPipeReader(ResultReader):
             A list of the same length as the input dataframe. Each position contains a
             list of leading protein entries, which a minimum of one entry.
         """
+        if self._sil:  # No "Indistinguishable Proteins" columns in 'SIL' data
+            return [[p] for p in df["Protein"]]
+
         leading_protein_entries = []
         for protein_entry, indist_protein_entry in zip(
             df["Protein"], df["Indistinguishable Proteins"].fillna("").astype(str)

{msreport-0.0.29.dist-info → msreport-0.0.30.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.29
+Version: 0.0.30
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License-Expression: Apache-2.0
@@ -29,7 +29,7 @@ Requires-Dist: seaborn>=0.12.0
 Requires-Dist: statsmodels>=0.13.2
 Requires-Dist: typing_extensions>=4
 Provides-Extra: r
-Requires-Dist: rpy2!=3.5.13,>=3.5.3; extra == "r"
+Requires-Dist: rpy2<3.5.13,>=3.5.3; extra == "r"
 Provides-Extra: dev
 Requires-Dist: mypy>=1.15.0; extra == "dev"
 Requires-Dist: pytest>=8.3.5; extra == "dev"
@@ -40,6 +40,7 @@ Dynamic: license-file
 # MsReport
 
 [![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)
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15309090.svg)](https://doi.org/10.5281/zenodo.15309090)
 ![Python Version from PEP 621 TOML](https://img.shields.io/python/required-version-toml?tomlFilePath=https%3A%2F%2Fraw.githubusercontent.com%2Fhollenstein%2Fmsreport%2Fmain%2Fpyproject.toml)
 [![Run tests](https://github.com/hollenstein/msreport/actions/workflows/run-tests.yml/badge.svg)](https://github.com/hollenstein/msreport/actions/workflows/run-tests.yml)
 
@@ -55,6 +56,7 @@ bottom-up mass spectrometry experiments.
     - [Additional requirements](#additional-requirements)
     - [Optional Dependencies](#optional-dependencies)
 - [Development status](#development-status)
+- [How to cite](#how-to-cite)
 
 ## What is MsReport?
 
@@ -134,3 +136,9 @@ For example, the R home directory might look like this on Windows: `C:\Program F
 ## Development status
 
 MsReport is a stable and reliable library that has been used on a daily basis for over two years in the Mass Spectrometry Facility at the Max Perutz Labs and the Mass Spectrometry Facility of IMP/IMBA/GMI. While the current interface of MsReport is stable, the library is still under active development, with new features being added regularly. Please note that a major rewrite is planned, which may introduce changes to the API in the future.
+
+## How to cite
+
+If you use MsReport for your research or publications, please include the following citation and consider giving the project a star on GitHub.
+
+> Hollenstein, D. M., & Hartl, M. (2025). hollenstein/msreport: v0.0.29 (0.0.29). Zenodo. https://doi.org/10.5281/zenodo.15309090

{msreport-0.0.29.dist-info → msreport-0.0.30.dist-info}/RECORD

@@ -1,4 +1,4 @@
-msreport/__init__.py,sha256=mwpJ3VkH0wctK3CzSQwaywF-mkOC8revi1Ra82apJ3U,339
+msreport/__init__.py,sha256=ajNIgBNRP06cDKDl6tsTeDhWSlJQw922QAxoJFd8Mhs,339
 msreport/analyze.py,sha256=I1sfxvXy02AjFcfLRlvC-F_bg0J8ePKoSIU8yDWxLs0,31313
 msreport/errors.py,sha256=X9yFxMiIOCWQdxuqBGr8L7O3vRV2KElXdX1uHbFcZMk,421
 msreport/export.py,sha256=YvY3Nly5JC2CUM-JY1gydU1g2eqnennzToZfQQ5phO0,20156
@@ -7,8 +7,8 @@ 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=Dqm3Ii9RKiQ61RNATXIqWzD8eOfQyPQQ7lddl-thLQA,112075
+msreport/qtable.py,sha256=4bJaWac1ePDZB1q7ssINWPdciqx4BIc6tiYUx5xrCsY,27265
+msreport/reader.py,sha256=ozw6QJ22aC0B3kSeb_frIIjkzGLx2yIV-1ZI9w8WffI,115638
 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
@@ -21,7 +21,7 @@ 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/distribution.py,sha256=QNFL5vG9p-vqhwEk5WcCSXa2B8u5QgySZlAQIPys0-0,10248
 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
@@ -31,8 +31,8 @@ msreport/rinterface/__init__.py,sha256=Zs6STvbDqaVZVPRM6iU0kKjq0TWz_2p2ChvNAveRd
 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-0.0.29.dist-info/licenses/LICENSE.txt,sha256=Pd-b5cKP4n2tFDpdx27qJSIq0d1ok0oEcGTlbtL6QMU,11560
-msreport-0.0.29.dist-info/METADATA,sha256=pI4CU6ol8LHTgkVEAGs-5HrCNefD52o-VdrZakKtwE4,8008
-msreport-0.0.29.dist-info/WHEEL,sha256=ooBFpIzZCPdw3uqIQsOo4qqbA4ZRPxHnOH7peeONza0,91
-msreport-0.0.29.dist-info/top_level.txt,sha256=Drl8mCckJHFIw-Ovh5AnyjKnqvLJltDOBUr1JAcHAlI,9
-msreport-0.0.29.dist-info/RECORD,,
+msreport-0.0.30.dist-info/licenses/LICENSE.txt,sha256=Pd-b5cKP4n2tFDpdx27qJSIq0d1ok0oEcGTlbtL6QMU,11560
+msreport-0.0.30.dist-info/METADATA,sha256=FO20yj_zTnw7F6pcWrWDbLLFwo_0Bz8Qm8djt1eOcWs,8444
+msreport-0.0.30.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+msreport-0.0.30.dist-info/top_level.txt,sha256=Drl8mCckJHFIw-Ovh5AnyjKnqvLJltDOBUr1JAcHAlI,9
+msreport-0.0.30.dist-info/RECORD,,

{msreport-0.0.29.dist-info → msreport-0.0.30.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.0.1)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any