FragPipe PG Reader

alphabase/constants/const_files/pg_reader.yaml

@@ -87,3 +87,34 @@ spectronaut:
     # At the beginning (^) of the string, match open square bracket "\\[", any number of digits "[0-9]+", closed square bracket "\\]"
     # Square brackets are special characters -> need to be escaped with "\[". The backslash itself needs to be escaped -> "\\["
     "default": "^\\[[0-9]+\\]"
+
+
+# https://fragpipe.nesvilab.org/docs/tutorial_fragpipe_outputs.html#proteintsv
+fragpipe:
+  reader_type: "fragpipe"
+  column_mapping:
+    "proteins": "Entry Name"
+    "uniprot_ids": "Protein ID"
+    "genes": "Gene Names"
+    "description": "Description"
+  measurement_regex:
+    "raw": "Intensity$"
+    "razor": "Razor Intensity$"
+    "unique": "Unique Intensity$"
+    "total": "Total Intensity$"
+    "lfq": "MaxLFQ Intensity$"
+    "lfq_unique": "MaxLFQ Unique Intensity$"
+    "lfq_total": "MaxLFQ Total Intensity$"
+
+
+# mzTab
+# version 2.0.0 (2019-03)
+mztab:
+  reader_type: "mztab"
+  column_mapping:
+    "uniprot_ids": "accession"
+    "description": "description"
+    "source_db": "database"
+  measurement_regex:
+    "assay": "^protein_abundance_assay\\[[0-9]+\\]" # The protein's abundance as measured in the given assay through whatever technique was employed
+    "study_variable": "^protein_abundance_study_variable\\[[0-9]+\\]" # The protein's abundance as measured in the given study variable (condition) through whatever technique was employed

alphabase/pg_reader/__init__.py

@@ -1,7 +1,9 @@
 from .alphadia_pg_reader import AlphaDiaPGReader
 from .alphapept_pg_reader import AlphaPeptPGReader
 from .diann_pg_reader import DiannPGReader
+from .fragpipe_pg_reader import FragPipePGReader
 from .maxquant_pg_reader import MaxQuantPGReader
+from .mztab_pg_reader import MZTabPGReader
 from .pg_reader import pg_reader_provider
 from .spectronaut_reader import SpectronautPGReader
 
@@ -12,4 +14,6 @@
     "AlphaPeptPGReader",
     "MaxQuantPGReader",
     "SpectronautPGReader",
+    "FragPipePGReader",
+    "MZTabPGReader",
 ]

alphabase/pg_reader/fragpipe_pg_reader.py

@@ -0,0 +1,47 @@
+"""FragPipe protein group reader."""
+
+from typing import Literal, Optional, Union
+
+from .pg_reader import PGReaderBase, pg_reader_provider
+
+
+class FragPipePGReader(PGReaderBase):
+    """Reader for `protein.tsv` reports from FragPipe.
+
+    Example:
+    -------
+    Per default, the reader will return the raw intensities from the `razor` method. Additional protein features are stored
+    in the dataframe index, samples are stored as columns.
+
+    .. code-block:: python
+
+        # Get raw intensities
+        reader = FragPipePGReader()
+        results = reader.import_file(download_path)
+
+
+    References:
+    ----------
+    - FragPipe Documentation https://fragpipe.nesvilab.org/docs/tutorial_fragpipe_outputs.html#proteintsv
+
+    """
+
+    _reader_type: str = "fragpipe"
+
+    def __init__(  # noqa: D107 inherited from base class
+        self,
+        *,
+        column_mapping: Optional[dict[str, str]] = None,
+        measurement_regex: Union[
+            Literal[
+                "raw", "razor", "unique", "total", "lfq", "lfq_unique", "lfq_total"
+            ],
+            None,
+        ] = "razor",
+    ):
+        super().__init__(
+            column_mapping=column_mapping, measurement_regex=measurement_regex
+        )
+
+
+pg_reader_provider.register_reader("fragpipe", reader_class=FragPipePGReader)

alphabase/pg_reader/mztab_pg_reader.py

@@ -0,0 +1,116 @@
+"""FragPipe protein group reader."""
+
+from pathlib import Path
+from typing import Literal, Optional, Union
+
+import pandas as pd
+
+from .pg_reader import PGReaderBase, pg_reader_provider
+
+
+class MZTabPGReader(PGReaderBase):
+    """Reader for MZTab search engine output.
+
+    MZTab is a standardized tab-delimited format for reporting proteomics and metabolomics results.
+    The format organizes data into distinct sections: metadata (MTD), protein groups (PRH/PRT),
+    peptides (PEH/PEP), PSMs (PSH/PSM), and small molecules (SMH/SML), with each section identified
+    by specific three-letter prefixes. This reader extracts protein-level quantification data from
+    the PRT lines, which contain protein abundances across samples or study variables.
+
+    Example:
+    -------
+    Per default, the reader will return the raw intensities from the `razor` method. Additional protein features are stored
+    in the dataframe index, samples are stored as columns.
+
+    .. code-block:: python
+
+        from alphabase.pg_reader import MZTabPGReader
+
+        # Get raw intensities
+        reader = MZTabPGReader()
+        results = reader.import_file(path)
+
+
+    References:
+    ----------
+    - Griss, J. et al. The mzTab Data Exchange Format: Communicating Mass-spectrometry-based Proteomics and Metabolomics Experimental Results to a Wider Audience*. Molecular & Cellular Proteomics 13, 2765-2775 (2014).
+    - Official MZTab Repository: https://github.com/HUPO-PSI/mzTab.git
+    - Official documentation: https://hupo-psi.github.io/mzTab/
+
+    """
+
+    _reader_type: str = "mztab"
+
+    _PROTEIN_ROW_INDICATOR: str = "PRT"
+    _PROTEIN_HEADER_INDICATOR: str = "PRH"
+    _SEPARATOR: str = "\t"
+
+    def __init__(  # noqa: D107 inherited from base class
+        self,
+        *,
+        column_mapping: Optional[dict[str, str]] = None,
+        measurement_regex: Union[
+            str, Literal["assay", "study_variable"], None  # noqa: PYI051 raw and lfq are special cases and not equivalent to string
+        ] = "assay",
+    ):
+        super().__init__(
+            column_mapping=column_mapping, measurement_regex=measurement_regex
+        )
+
+    def _load_file(self, file_path: str) -> pd.DataFrame:
+        """Load MZTab file and extract protein data section.
+
+        Parameters
+        ----------
+        file_path : str
+            Path to MZTab file
+
+        Returns
+        -------
+        pd.DataFrame
+            DataFrame containing protein data from MZTab file
+
+        Notes
+        -----
+        Protein lines are indicated with a leading `PRT`. The protein metadata header is
+        indicated with a leading `PRH`. The file is tab separated.
+
+        Raises
+        ------
+        ValueError
+            If no protein data or metadata is found in the file
+
+        """
+        file_path = Path(file_path)
+        protein_header = None
+        protein_rows = []
+
+        with file_path.open() as f:
+            for line in f:
+                line_stripped = line.strip()
+
+                if line_stripped.startswith(self._PROTEIN_HEADER_INDICATOR):
+                    # Protein header line - remove 'PRH' prefix and parse columns
+                    header_content = line_stripped[3:].strip()
+                    protein_header = header_content.split(self._SEPARATOR)
+
+                elif line_stripped.startswith(self._PROTEIN_ROW_INDICATOR):
+                    # Protein data line - remove 'PRT' prefix and parse data
+                    row_content = line_stripped[3:].strip()
+                    protein_rows.append(row_content.split(self._SEPARATOR))
+
+        # Validate that we found protein data
+        if protein_header is None:
+            raise ValueError(
+                f"No protein header ({self._PROTEIN_HEADER_INDICATOR}) found in MZTab file"
+            )
+
+        if not protein_rows:
+            raise ValueError(
+                f"No protein data rows ({self._PROTEIN_ROW_INDICATOR}) found in MZTab file"
+            )
+
+        return pd.DataFrame(protein_rows, columns=protein_header)
+
+
+pg_reader_provider.register_reader("mztab", reader_class=MZTabPGReader)

docs/api.rst

@@ -36,6 +36,7 @@ Reader
    :maxdepth: 2
 
    modules_psm_reader
+   modules_pg_reader
 
 
 I/O

docs/modules_pg_reader.rst

@@ -0,0 +1,17 @@
+alphabase.pg_reader
+===========================
+
+All pg_readers can be accessed by
+:obj:`pg_reader_provider <alphabase.pg_reader.pg_reader.pg_reader_provider>`.
+
+.. toctree::
+   :maxdepth: 1
+
+   pg_reader/pg_base
+   pg_reader/alphadia_pg_reader
+   pg_reader/alphapept_pg_reader
+   pg_reader/diann_pg_reader
+   pg_reader/fragpipe_pg_reader
+   pg_reader/maxquant_pg_reader
+   pg_reader/mztab_pg_reader
+   pg_reader/spectronaut_pg_reader

docs/pg_reader/alphadia_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.alphadia_pg_reader
+======================================
+
+.. automodule:: alphabase.pg_reader.alphadia_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/alphapept_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.alphapept_pg_reader
+=======================================
+
+.. automodule:: alphabase.pg_reader.alphapept_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/diann_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.diann_pg_reader
+===================================
+
+.. automodule:: alphabase.pg_reader.diann_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/fragpipe_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.fragpipe_pg_reader
+======================================
+
+.. automodule:: alphabase.pg_reader.fragpipe_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/maxquant_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.maxquant_pg_reader
+======================================
+
+.. automodule:: alphabase.pg_reader.maxquant_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/mztab_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.mztab_pg_reader
+======================================
+
+.. automodule:: alphabase.pg_reader.mztab_pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/pg_base.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.base
+========================
+
+.. automodule:: alphabase.pg_reader.pg_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/pg_reader/spectronaut_pg_reader.rst

@@ -0,0 +1,7 @@
+alphabase.pg_reader.spectronaut_reader
+======================================
+
+.. automodule:: alphabase.pg_reader.spectronaut_reader
+   :members:
+   :undoc-members:
+   :show-inheritance:

tests/integration/conftest.py

@@ -193,3 +193,57 @@ def example_spectronaut_parquet(tmp_path) -> Path:
     REF_URL = "https://datashare.biochem.mpg.de/s/nhxU8NZXQt35BWw"
 
     return get_remote_data_with_ref(url=URL, ref_url=REF_URL, directory=tmp_path)
+
+
+@pytest.fixture(scope="function")
+def example_fragpipe_tsv(tmp_path) -> Path:
+    """Get and parse real FragPipe protein group report matrix (protein.tsv)."""
+    TEST_FILE_NAME = "pg_fragpipe"
+    TEST_DATA = """Protein Group	SubGroup	Protein	Protein ID	Entry Name	Gene Names	Protein Length	Coverage	Organism	Protein Existence	Description	Protein Probability	Top Peptide Probability	Unique Stripped Peptides	Summarized Total Spectral Count	Summarized Unique Spectral Count	S1 Razor Intensity	S2 Razor Intensity	S3 Razor Intensity	S4 Razor Intensity	S5 Razor Intensity	S6 Razor Intensity	S7 Razor Intensity	S8 Razor Intensity	S9 Razor Intensity	S10 Razor Intensity	S11 Razor Intensity	S12 Razor Intensity	S13 Razor Intensity	S14 Razor Intensity	S15 Razor Intensity	S16 Razor Intensity	S17 Razor Intensity	S18 Razor Intensity	S19 Razor Intensity	S20 Razor Intensity
+679	a	sp|P02790|HEMO_HUMAN	P02790	HEMO_HUMAN	HPX	462	82.9	Homo sapiens OX=9606	1:Experimental evidence at protein level	Hemopexin	1.0	0.9990000000000001	95	25026	25025	2216637.5	2295583.8	1240315.4	106460.28	1019385.2	2596973.0	3091005.2	2327599.5	2323380.0	3109355.8	2113776.8	2301295.2	2451093.5	142603.97	946154.75	3126271.8	2970801.5	2399545.8	3020956.8	3691187.2
+680	a	sp|P02792|FRIL_HUMAN	P02792	FRIL_HUMAN	FTL	175	40.6	Homo sapiens OX=9606	1:Experimental evidence at protein level	Ferritin light chain	1.0	0.9990000000000001	18	69	67	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
+681	a	sp|P02794|FRIH_HUMAN	P02794	FRIH_HUMAN	FTH1	183	53.6	Homo sapiens OX=9606	1:Experimental evidence at protein level	Ferritin heavy chain	1.0	0.9990000000000001	15	15	15	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
+682	a	sp|P03951|FA11_HUMAN	P03951	FA11_HUMAN	F11	625	20.2	Homo sapiens OX=9606	1:Experimental evidence at protein level	Coagulation factor XI	1.0	0.9990000000000001	11	18	18	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
+683	a	sp|P03952|KLKB1_HUMAN	P03952	KLKB1_HUMAN	KLKB1	638	41.7	Homo sapiens OX=9606	1:Experimental evidence at protein level	Plasma kallikrein	1.0	0.9990000000000001	23	1022	1022	0.0	85066.71	0.0	0.0	74640.38	118894.164	111398.06	59677.086	45627.31200000001	36386.727	38690.133	70755.9	70384.055	102087.5	106722.82	102985.125	99397.76	45197.56	54068.883	45319.242
+684	a	sp|P04003|C4BPA_HUMAN	P04003	C4BPA_HUMAN	C4BPA	597	40.2	Homo sapiens OX=9606	1:Experimental evidence at protein level	C4b-binding protein alpha chain	1.0	0.9990000000000001	26	1645	1645	0.0	0.0	0.0	0.0	0.0	112257.234	30634.523	112197.33	107021.34	95892.05	100655.766	77396.234	78481.19	0.0	0.0	0.0	55184.43	25498.191000000006	43999.35	32183.307
+685	a	sp|P04004|VTNC_HUMAN	P04004	VTNC_HUMAN	VTN	478	51.0	Homo sapiens OX=9606	1:Experimental evidence at protein level	Vitronectin	1.0	0.9990000000000001	41	10829	10812	426109.1	531158.4	280231.38	972440.7	925719.9	1446606.2	841194.25	850832.94	911400.2	461015.6	349032.28	877507.94	1113970.9	980389.94	1374961.0	1188514.5	870155.6	1299377.1	1360895.5	614073.56
+686	a	sp|P04040|CATA_HUMAN	P04040	CATA_HUMAN	CAT	527	43.8	Homo sapiens	1:Experimental evidence at protein level	Catalase	1.0	0.9990000000000001	18	23	23	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
+687	a	sp|P04070|PROC_HUMAN	P04070	PROC_HUMAN	PROC	461	43.4	Homo sapiens OX=9606	1:Experimental evidence at protein level	Vitamin K-dependent protein C	1.0	0.9990000000000001	15	65	65	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	39016.97	0.0	0.0	0.0
+688	a	sp|P04114|APOB_HUMAN	P04114	APOB_HUMAN	APOB	4563	75.5	Homo sapiens OX=9606	1:Experimental evidence at protein level	Apolipoprotein B-100	1.0	0.9990000000000001	573	103725	103716	603013.44	923688.06	591751.25	491850.03	397211.94	506224.94	319749.8	263752.28	390402.94	443494.1	498007.12	230024.48	265819.75	687710.9	762252.1	422017.75	1020169.75	196046.12	318726.28	480642.72
+"""
+
+    file_path = write_test_data(
+        data=TEST_DATA, directory=tmp_path, test_case_name=TEST_FILE_NAME
+    )
+    reference = get_local_reference_data(test_case_name=TEST_FILE_NAME)
+
+    return file_path, reference
+
+
+@pytest.fixture(scope="function")
+def example_mztab(tmp_path) -> Path:
+    """Get and parse real MZTab report"""
+    URL = "https://datashare.biochem.mpg.de/s/ayieQHU9zjY89cl"
+    REF_URL = "https://datashare.biochem.mpg.de/s/o7K2FEAmpmLUglS"
+
+    return get_remote_data_with_ref(url=URL, ref_url=REF_URL, directory=tmp_path)
+
+
+@pytest.fixture(scope="function")
+def example_mztab_minimal(tmp_path) -> Path:
+    """Get and parse minimal MZTab report for local testing"""
+    TEST_FILE_NAME = "pg_mztab_minimal"
+    TEST_DATA = """COM	Only variable modifications can be reported when the original source is a PRIDE XML file
+
+PRH	accession	description	taxid	species	database	database_version	search_engine	best_search_engine_score[1]	search_engine_score[1]_ms_run[1]	num_psms_ms_run[1]	num_peptides_distinct_ms_run[1]	num_peptides_unique_ms_run[1]	ambiguity_members	modifications	protein_coverage	protein_abundance_assay[1]	protein_abundance_assay[2]	protein_abundance_assay[3]	protein_abundance_assay[4]
+PRT	223462890	Spna2 protein [Mus musculus]	10090	Mus musculus (Mouse)	NCBInr_2010_10	nr_101020.fasta	[MS, MS:1001207, Mascot, ]	6539.67	6539.67	157	92	null	null	null	0	1	0.853	0.864	0.791
+PRT	19855078	RecName: Full=Sodium/potassium-transporting ATPase subunit alpha-3; Short=Na(+)/K(+) ATPase alpha-3 subunit; AltName: Full=Na(+)/K(+) ATPase alpha(III) subunit; AltName: Full=Sodium pump subunit alpha-3	10090	Mus musculus (Mouse)	NCBInr_2010_10	nr_101020.fasta	[MS, MS:1001207, Mascot, ]	6331.91	6331.91	144	49	null	null	32-MOD:00425,525-MOD:00425,606-MOD:00425,725-MOD:00425,739-MOD:00425,940-MOD:00425	0	null	null	null	null
+PRT	21450277	sodium/potassium-transporting ATPase subunit alpha-1 precursor [Mus musculus]	10090	Mus musculus (Mouse)	NCBInr_2010_10	nr_101020.fasta	[MS, MS:1001207, Mascot, ]	4577.11	4577.11	112	39	null	null	42-MOD:00425,616-MOD:00425,749-MOD:00425,950-MOD:00425	0	1	0.776	0.819	0.687
+PRT	6978545	sodium/potassium-transporting ATPase subunit alpha-2 precursor [Rattus norvegicus]	10090	Mus musculus (Mouse)	NCBInr_2010_10	nr_101020.fasta	[MS, MS:1001207, Mascot, ]	4342.81	4342.81	108	42	null	null	40-MOD:00425,613-MOD:00425,746-MOD:00425,947-MOD:00425	0	1	0.784	0.848	0.693
+    """
+    file_path = write_test_data(
+        data=TEST_DATA, directory=tmp_path, test_case_name=TEST_FILE_NAME
+    )
+    reference = get_local_reference_data(test_case_name=TEST_FILE_NAME)
+
+    return file_path, reference

tests/integration/test_pg_reader_provider.py

@@ -4,7 +4,9 @@
     AlphaDiaPGReader,
     AlphaPeptPGReader,
     DiannPGReader,
+    FragPipePGReader,
     MaxQuantPGReader,
+    MZTabPGReader,
     SpectronautPGReader,
     pg_reader_provider,
 )
@@ -48,3 +50,19 @@ def test_reader_provider(self) -> None:
         reader = pg_reader_provider.get_reader("spectronaut")
 
         assert isinstance(reader, SpectronautPGReader)
+
+
+class TestFragPipePGReaderProvider:
+    def test_reader_provider(self) -> None:
+        """Test whether reader provider initializes FragPipe protein group reader correctly."""
+        reader = pg_reader_provider.get_reader("fragpipe")
+
+        assert isinstance(reader, FragPipePGReader)
+
+
+class TestMZTabPGReaderProvider:
+    def test_reader_provider(self) -> None:
+        """Test whether reader provider initializes MZTab protein group reader correctly."""
+        reader = pg_reader_provider.get_reader("mztab")
+
+        assert isinstance(reader, MZTabPGReader)