flippr 0.1.1__tar.gz

flippr-0.1.1/.gitignore

@@ -0,0 +1,15 @@
+.DS_Store
+flippr/.DS_Store
+
+__pycache__
+flippr/__pycache__
+
+/**/.*
+/**/.*/
+/**/data/
+/**/*.log
+/**/*.txt
+/**/*.ipynb
+/**/*.xlsx
+/**/__pycache__
+!/.gitignore

flippr-0.1.1/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.3
+Name: flippr
+Version: 0.1.1
+Summary: FragPipe Limited-Proteolysis Processor (FLiPPR) is modular, fast, and easy-to-use data processing tool for LiP-MS & LFQ-based experiments analyzed in FragPipe
+Project-URL: Documentation, https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor#readme
+Project-URL: Issues, https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processorissues
+Project-URL: Source, https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor
+Author-email: Edgar Manriquez-Sandoval <emanriq1@jhu.edu>
+Maintainer-email: "FriedLab@JHU" <friedlab.jhu@gmail.com>, "Stephen D. Fried" <sdfried@jhu.edu>, Edgar Manriquez-Sandoval <emanriq1@jhu.edu>
+License-File: LICENSE
+Keywords: bottom-up proteomics,computational mass spectrometry,differential analysis,flippr,fragpipe,fragpipe analysis,label-free,label-free quantification,lfq,limited proteolysis,lip-ms,proteomics
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.10
+Requires-Dist: biopython
+Requires-Dist: h2
+Requires-Dist: httpx
+Requires-Dist: matplotlib
+Requires-Dist: nest-asyncio
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: polars
+Requires-Dist: pyarrow
+Requires-Dist: requests
+Requires-Dist: scipy
+Requires-Dist: seaborn
+Requires-Dist: xlsx2csv
+Requires-Dist: xlsxwriter
+Description-Content-Type: text/markdown
+
+![FLiPPR Logo](/assets/images/flippr_long_logo.png)
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Support](#support)
+- [Installation](#installation)
+- [Usage](#usage)
+- [License](#license)
+- [Citation](#citation)
+
+## Overview
+
+FLiPPR (**F**ragPipe **Li**mited-**P**roteolysis **Pr**ocessor) is modular, fast, and easy-to-use data processing tool for LiP-MS & LFQ-based experiments analyzed in FragPipe.
+
+FLiPPR is:
+* **Super Fast**: FLiPPR utilizes [Polars](https://pola.rs/) in the back-end to ensure all CPU cores contribute to your data processing.
+* **Convinent to Use**: [FragPipe](https://fragpipe.nesvilab.org/) produces standarized outputs, FLiPPR takes full advantage of this feat and integrates seemlessly with any FragPipe LFQ-MBR anaylsis.
+* **Flexible and Expandable**: Experiments introduce unique and novel variables, FLiPPR ensures capatibility with all experimental setups and gives you full control of the data processing pipeline.
+
+## Support
+FLiPPR has been tested with Python 3.10 – 3.12
+To learn more about how FLiPPR can help you analyze your LiP-MS or LFQ data, head over to the [FLiPPR docs](https://flippr.readthedocs.io)
+
+## Installation
+
+To get started with FLiPPR, follow these steps:
+
+```bash
+    # 1. Clone the repository:
+    git clone https://https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor.git
+    
+    # 2. Navigate to the project directory:
+    cd FragPipe-Limited-Proteolysis-Processor
+    
+    # 3. Install FLiPPR:
+    python -m pip install .
+```
+
+## Usage
+
+1. Start a `Study`
+
+```python
+import flippr as fp
+from flippr import Study
+
+# Pass the FragPipe output directory path from your LiP-MS experiment
+study = Study(lip = "path/to/lip")
+
+# Include protein normalization factors from a Trypsin-only experiment
+study = Study(lip = "path/to/lip", trp = "path/to/trp")
+
+# Including the protein FASTA file will add metadata and remove contaminants
+study = Study(lip = "path/to/lip", trp = "path/to/trp", fasta = "UP000000625_83333.fasta")
+```
+
+2. View the experimental sample annotations
+
+```python
+print(study.samples)
+# >>> { 'LiP': {'Native', 'Refolded_001_min', 'Refolded_005_min', 'Refolded_120_min'}, 'TrP': {'Refolded', 'Native'}}
+```
+
+3. Add an experimental process
+
+```python
+# Process without normalization
+study.add_process(1, "Native", "Refolded_001_min", 3)
+
+# Process with normalizations (only when `trp` is included in the study)
+study.add_process(5, "Native", "Refolded_005_min", 3, "Native", "Refolded", 3)
+
+# Multiple processes within one study
+study.add_process(1, "Native", "Refolded_001_min", 3, "Native", "Refolded", 3)
+study.add_process(5, "Native", "Refolded_005_min", 3, "Native", "Refolded", 3)
+study.add_process(120, "Native", "Refolded_120_min", 3, "Native", "Refolded", 3)
+```
+
+4. Run your study
+
+```python
+# Running a study returns results and populates the `Study().results` dictionary
+results = study.run()
+# >>> {1: <flippr.Results>, 5: <flippr.Results>, 120: <flippr.Results>}
+
+# Change analysis parameters within `fp.rcParams` before running for more control
+fp.rcParams["protein.fc_sig_thresh"] = 2.0
+results = study.run()
+```
+
+5. View or save your results as Polars DataFrames
+
+```python
+# 1 min time point results
+results_1_min = results[1]
+
+# View all ions included in the 1 min experimental process
+results_1_min.ion
+
+# View higher-order results
+results_1_min.modified_peptide
+results_1_min.peptide
+results_1_min.cut_site
+
+# View protein-level summary of all data
+results_1_min.protein_summary
+```
+
+| Protein ID | Protein                     | Entry Name  | Gene   | ... | No. of Valid Cut Sites | No. of Significant Cut Sites | No. of Significant Cut Sites |
+|------------|-----------------------------|-------------|--------|-----|------------------------|------------------------------|------------------------------|
+| P00350     | sp\|P00350\|6PGD_ECOLI      | 6PGD_ECOLI  | gnd    | ... | 111                    | 40                           | 50                           |
+| P00363     | sp\|P00363\|FRDA_ECOLI      | FRDA_ECOLI  | frdA   | ... | 15                     | 2                            | 2                            |
+| Q57261     | sp\|Q57261\|TRUD_ECOLI      | TRUD_ECOLI  | truD   | ... | 24                     | 7                            | 8                            |
+| Q59385     | sp\|Q59385\|COPA_ECOLI      | COPA_ECOLI  | copA   | ... |13                      | 2                            | 1                            |
+| Q7DFV3     | sp\|Q7DFV3\|YMGG_ECOLI      | YMGG_ECOLI  | ymgG   | ... | 4                      | 2                            | 4                            |
+| Q93K97     | sp\|Q93K97\|ADPP_ECOLI      | ADPP_ECOLI  | nudF   | ... | 9                      | 4                            | 5                            |
+
+## License
+
+This project is licensed under the CC BY-NC-ND 4.0 License. Feel free to use the code according to the terms specified in the license.
+This project is licensed under the CC BY-NC-ND 4.0 License. Feel free to use the code according to the terms specified in the license.
+
+Thank you for your interest in FLiPPR!
+If you encounter any issues or have suggestions, please open an issue.
+We appreciate your feedback!
+
+## Citation
+If you found this work helpful in your research, please cite us!  
+ 
+**FLiPPR: A Processor for Limited Proteolysis (LiP) Mass Spectrometry Data Sets Built on FragPipe**  
+Edgar Manriquez-Sandoval, Joy Brewer, Gabriela Lule, Samanta Lopez, and Stephen D. Fried  
+*Journal of Proteome Research*  
+DOI: ***10.1021/acs.jproteome.3c00887***

flippr-0.1.1/README.md

@@ -0,0 +1,134 @@
+![FLiPPR Logo](/assets/images/flippr_long_logo.png)
+
+## Table of Contents
+
+- [Overview](#overview)
+- [Support](#support)
+- [Installation](#installation)
+- [Usage](#usage)
+- [License](#license)
+- [Citation](#citation)
+
+## Overview
+
+FLiPPR (**F**ragPipe **Li**mited-**P**roteolysis **Pr**ocessor) is modular, fast, and easy-to-use data processing tool for LiP-MS & LFQ-based experiments analyzed in FragPipe.
+
+FLiPPR is:
+* **Super Fast**: FLiPPR utilizes [Polars](https://pola.rs/) in the back-end to ensure all CPU cores contribute to your data processing.
+* **Convinent to Use**: [FragPipe](https://fragpipe.nesvilab.org/) produces standarized outputs, FLiPPR takes full advantage of this feat and integrates seemlessly with any FragPipe LFQ-MBR anaylsis.
+* **Flexible and Expandable**: Experiments introduce unique and novel variables, FLiPPR ensures capatibility with all experimental setups and gives you full control of the data processing pipeline.
+
+## Support
+FLiPPR has been tested with Python 3.10 – 3.12
+To learn more about how FLiPPR can help you analyze your LiP-MS or LFQ data, head over to the [FLiPPR docs](https://flippr.readthedocs.io)
+
+## Installation
+
+To get started with FLiPPR, follow these steps:
+
+```bash
+    # 1. Clone the repository:
+    git clone https://https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor.git
+    
+    # 2. Navigate to the project directory:
+    cd FragPipe-Limited-Proteolysis-Processor
+    
+    # 3. Install FLiPPR:
+    python -m pip install .
+```
+
+## Usage
+
+1. Start a `Study`
+
+```python
+import flippr as fp
+from flippr import Study
+
+# Pass the FragPipe output directory path from your LiP-MS experiment
+study = Study(lip = "path/to/lip")
+
+# Include protein normalization factors from a Trypsin-only experiment
+study = Study(lip = "path/to/lip", trp = "path/to/trp")
+
+# Including the protein FASTA file will add metadata and remove contaminants
+study = Study(lip = "path/to/lip", trp = "path/to/trp", fasta = "UP000000625_83333.fasta")
+```
+
+2. View the experimental sample annotations
+
+```python
+print(study.samples)
+# >>> { 'LiP': {'Native', 'Refolded_001_min', 'Refolded_005_min', 'Refolded_120_min'}, 'TrP': {'Refolded', 'Native'}}
+```
+
+3. Add an experimental process
+
+```python
+# Process without normalization
+study.add_process(1, "Native", "Refolded_001_min", 3)
+
+# Process with normalizations (only when `trp` is included in the study)
+study.add_process(5, "Native", "Refolded_005_min", 3, "Native", "Refolded", 3)
+
+# Multiple processes within one study
+study.add_process(1, "Native", "Refolded_001_min", 3, "Native", "Refolded", 3)
+study.add_process(5, "Native", "Refolded_005_min", 3, "Native", "Refolded", 3)
+study.add_process(120, "Native", "Refolded_120_min", 3, "Native", "Refolded", 3)
+```
+
+4. Run your study
+
+```python
+# Running a study returns results and populates the `Study().results` dictionary
+results = study.run()
+# >>> {1: <flippr.Results>, 5: <flippr.Results>, 120: <flippr.Results>}
+
+# Change analysis parameters within `fp.rcParams` before running for more control
+fp.rcParams["protein.fc_sig_thresh"] = 2.0
+results = study.run()
+```
+
+5. View or save your results as Polars DataFrames
+
+```python
+# 1 min time point results
+results_1_min = results[1]
+
+# View all ions included in the 1 min experimental process
+results_1_min.ion
+
+# View higher-order results
+results_1_min.modified_peptide
+results_1_min.peptide
+results_1_min.cut_site
+
+# View protein-level summary of all data
+results_1_min.protein_summary
+```
+
+| Protein ID | Protein                     | Entry Name  | Gene   | ... | No. of Valid Cut Sites | No. of Significant Cut Sites | No. of Significant Cut Sites |
+|------------|-----------------------------|-------------|--------|-----|------------------------|------------------------------|------------------------------|
+| P00350     | sp\|P00350\|6PGD_ECOLI      | 6PGD_ECOLI  | gnd    | ... | 111                    | 40                           | 50                           |
+| P00363     | sp\|P00363\|FRDA_ECOLI      | FRDA_ECOLI  | frdA   | ... | 15                     | 2                            | 2                            |
+| Q57261     | sp\|Q57261\|TRUD_ECOLI      | TRUD_ECOLI  | truD   | ... | 24                     | 7                            | 8                            |
+| Q59385     | sp\|Q59385\|COPA_ECOLI      | COPA_ECOLI  | copA   | ... |13                      | 2                            | 1                            |
+| Q7DFV3     | sp\|Q7DFV3\|YMGG_ECOLI      | YMGG_ECOLI  | ymgG   | ... | 4                      | 2                            | 4                            |
+| Q93K97     | sp\|Q93K97\|ADPP_ECOLI      | ADPP_ECOLI  | nudF   | ... | 9                      | 4                            | 5                            |
+
+## License
+
+This project is licensed under the CC BY-NC-ND 4.0 License. Feel free to use the code according to the terms specified in the license.
+This project is licensed under the CC BY-NC-ND 4.0 License. Feel free to use the code according to the terms specified in the license.
+
+Thank you for your interest in FLiPPR!
+If you encounter any issues or have suggestions, please open an issue.
+We appreciate your feedback!
+
+## Citation
+If you found this work helpful in your research, please cite us!  
+ 
+**FLiPPR: A Processor for Limited Proteolysis (LiP) Mass Spectrometry Data Sets Built on FragPipe**  
+Edgar Manriquez-Sandoval, Joy Brewer, Gabriela Lule, Samanta Lopez, and Stephen D. Fried  
+*Journal of Proteome Research*  
+DOI: ***10.1021/acs.jproteome.3c00887***

flippr-0.1.1/pyproject.toml

@@ -0,0 +1,114 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "flippr"
+dynamic = ["version"]
+description = "FragPipe Limited-Proteolysis Processor (FLiPPR) is modular, fast, and easy-to-use data processing tool for LiP-MS & LFQ-based experiments analyzed in FragPipe"
+readme = "README.md"
+requires-python = ">=3.10"
+keywords = [
+  "bottom-up proteomics",
+  "computational mass spectrometry",
+  "fragpipe",
+  "fragpipe analysis",
+  "limited proteolysis",
+  "lip-ms",
+  "lfq",
+  "label-free",
+  "label-free quantification",
+  "differential analysis",
+  "proteomics",
+  "flippr",
+  "fragpipe"
+]
+authors = [
+  { name = "Edgar Manriquez-Sandoval", email = "emanriq1@jhu.edu"},
+]
+maintainers = [
+  {name = "FriedLab@JHU", email = "friedlab.jhu@gmail.com"},
+  {name = "Stephen D. Fried", email = "sdfried@jhu.edu"},
+  {name = "Edgar Manriquez-Sandoval", email = "emanriq1@jhu.edu"},
+]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: Implementation :: PyPy",
+]
+dependencies = [
+  "biopython",
+  "h2",
+  "httpx",
+  "matplotlib",
+  "nest_asyncio",
+  "numpy",
+  "pandas",
+  "polars",
+  "pyarrow",
+  "requests",
+  "scipy",
+  "seaborn",
+  "xlsx2csv",
+  "xlsxwriter"
+]
+
+[project.urls]
+Documentation = "https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor#readme"
+Issues = "https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processorissues"
+Source = "https://github.com/FriedLabJHU/FragPipe-Limited-Proteolysis-Processor"
+
+[tool.hatch.version]
+path = "src/flippr/__about__.py"
+
+[tool.hatch.envs.default]
+dependencies = [
+  "coverage[toml]>=6.5",
+  "pytest",
+]
+[tool.hatch.envs.default.scripts]
+test = "pytest {args:tests}"
+test-cov = "coverage run -m pytest {args:tests}"
+cov-report = [
+  "- coverage combine",
+  "coverage report",
+]
+cov = [
+  "test-cov",
+  "cov-report",
+]
+
+[tool.setuptools.package-data]
+"flippr" = ["py.typed"]
+
+[[tool.hatch.envs.all.matrix]]
+python = ["3.10", "3.11", "3.12"]
+
+[tool.hatch.envs.types]
+dependencies = [
+  "mypy>=1.0.0",
+]
+[tool.hatch.envs.types.scripts]
+check = "mypy --install-types --non-interactive {args:src/flippr tests}"
+
+[tool.coverage.run]
+source_pkgs = ["flippr", "tests"]
+branch = true
+parallel = true
+omit = [
+  "src/flippr/__about__.py",
+]
+
+[tool.coverage.paths]
+flippr = ["src/flippr", "*/flippr/src/flippr"]
+tests = ["tests", "*/flippr/tests"]
+
+[tool.coverage.report]
+exclude_lines = [
+  "no cov",
+  "if __name__ == .__main__.:",
+  "if TYPE_CHECKING:",
+]

flippr-0.1.1/src/flippr/__about__.py

@@ -0,0 +1 @@
+__version__ = "0.1.1"

flippr-0.1.1/src/flippr/__init__.py

@@ -0,0 +1,172 @@
+from functools import cached_property
+from pathlib import Path
+
+import polars as pl
+
+from . import spr as _spr
+from . import validate as _validate
+from .parameters import rcParams
+from .uniprot import fasta as _fasta
+
+
+class Study:
+    """
+    A FLiPPR Study is used to coordinate Limited Proteolysis (LiP) data processing for a single experiment analyzed with FragPipe.
+    Studies can contain LiP data alone or LiP and TrP data; with the inclusion of a FASTA file for automatic metadata generation.
+    TrP data should result from the same experimental conditions as the LiP data, but without including a broad-spectrum protease like Proteinase K (PK).
+
+    Args:
+        lip (str | Path): Directory or path to the FragPipe LFQ output data for Limited Proteolysis (LiP) experiment data.
+        trp (str | Path, optional): Directory or path to the FragPipe LFQ output data for Trypsin Only (TrP) experiment data. Defaults to None.
+        fasta (str | Path, optional): Path to the FASTA file containing the same protein sequences used in the LiP/TrP experiments. Defaults to None.
+        method (str): Method used to quantify ion intensities in FragPipe. `lfq` - Label-Free Quantification, `silac` - Stable Isotope Labelling (currently not incorporated). Defaults to `lfq`.
+
+    Examples:
+        Analysis of a single dataset
+        >>> flippr.Study(lip = "PXD025926/FragPipe/LiP_LFQ")
+
+        Analysis of a single dataset with metadata integration
+        >>> flippr.Study(lip = "PXD025926/FragPipe/LiP_LFQ", fasta = "UP000000625.fasta")
+
+        Including protein-level normalization from trypsin-only data
+        >>> flippr.Study(lip = "PXD025926/FragPipe/LiP_LFQ", trp = "PXD025926/FragPipe/TrP_LFQ")
+
+    """
+
+    def __init__(self, lip: str | Path, trp: str | Path | None = None, fasta: str | Path | None = None, method: str = "lfq") -> None:
+
+        _lip, _trp, _fasta_path, _method = _validate._validate_study(lip, trp, fasta, method)
+
+        self.lip: Path = _lip
+        self.trp: Path | None = _trp
+        self._fasta_path: Path | None = _fasta_path
+        self.method: str = _method
+
+        self._pid: int = 0
+        self.processes: dict = dict()
+        self.results: dict = dict()
+
+    @property
+    def samples(self) -> dict:
+        """
+        Returns the names of the samples or experimental annotations found in the FragPipe outputs for LiP and TrP (if include) datasets.
+
+        Examples:
+            Including only LiP data
+            >>> e_coli_refolding = flippr.Study(lip = "PXD025926/FragPipe/LiP_LFQ")
+            >>> print(e_coli_refolding.samples)
+            {"LiP": ("Native", "Refolded_01_min", "Refolded_05_min", "Refolded_30_min")}
+
+            Including LiP and TrP data
+            >>> e_coli_refolding = flippr.Study(lip = "PXD025926/FragPipe/LiP_LFQ", trp = "PXD025926/FragPipe/TrP_LFQ")
+            >>> print(e_coli_refolding.samples)
+            {"LiP": ("Native", "Refolded_01_min", "Refolded_05_min", "Refolded_30_min"),
+             "TrP": ("Native", "Refolded")}
+
+        """
+
+        if self.trp is not None:
+            return {"LiP": self.lip_samples, "TrP": self.trp_samples}
+
+        return {"LiP": self.lip_samples}
+
+    @property
+    def lip_samples(self) -> set:
+        """
+        Returns the names of the samples or experimental annotations found in the FragPipe outputs for LiP datasets.
+
+        """
+
+        return self.__read_annotation(self.lip)
+
+    @property
+    def trp_samples(self) -> set:
+        """
+        Returns the names of the samples or experimental annotations found in the FragPipe outputs for TrP datasets.
+
+        """
+
+        return self.__read_annotation(self.trp)
+
+    @cached_property
+    def fasta(self) -> pl.DataFrame | None:
+        """
+        Returns a three column dataframe containing Protein IDs, Sequences, and Valid ID if the Protein ID is interpretable as an official Uniprot ID.
+
+        """
+        if self._fasta_path is not None:
+            return _fasta._read_fasta(self._fasta_path)
+
+        return None
+
+    def add_process(
+        self, pid: object | None, lip_ctrl: str, lip_test: str, n_rep: int, trp_ctrl: str | None = None, trp_test: str | None = None, trp_n_rep: int | None = None) -> None:
+        """
+        Adding a process to calculate the fold-change between test and control conditions.
+        Normalization is optional and must include a TrP experiment in the `Study` set-up.
+
+        Args:
+            pid (Any): Process ID used to index the `Study().results` dictionary after running `Study().run()`.
+            lip_ctrl (str): Control condition sample name from the LiP experiment.
+            lip_test (str): Test condition sample name from the LiP experiment.
+            n_rep (int): Number of replicates in the LiP experiment.
+            trp_ctrl (str, optional): Control condition sample name from the TrP experiment.
+            trp_test (str, optional): Test condition sample name from the TrP experiment.
+            trp_n_rep (int, optional): Number of replicates in the TrP experiment.
+
+        Examples:
+            Simple fold-change calculation between two conditions
+            >>> study.add_process("sample", "WT", "Drug", 3)
+
+            Fold-change calculation with normalization
+            >>> study.add_process("sample", "WT", "Drug", 3, "WT_TrP", "DMSO_TrP", 3)
+
+            Add multiple processes to the same study
+            >>> study.add_process("cond_1", "WT", "Cond1", 5)
+            >>> study.add_process("cond_2", "WT", "Cond2", 5, "WT_TrP", "DMSO_TrP", 5)
+        """
+
+        if pid is None:
+            pid = self._pid
+            self._pid += 1
+
+        self.processes.update(
+            {
+                pid: _spr.Process(
+                    self.fasta,
+                    self.lip,
+                    self.trp,
+                    pid,
+                    lip_ctrl,
+                    lip_test,
+                    n_rep,
+                    trp_ctrl,
+                    trp_test,
+                    trp_n_rep,
+                )
+            }
+        )
+
+    def run(self) -> dict[object: _spr.Result]:
+        """
+        Run the processes added to the study.
+        Study parameters can be changed by editing the `flippr.rcParams` dictionary.
+        """
+
+        self.results = {pid: proc.run(rcParams) for pid, proc in self.processes.items()}
+
+        return self.results
+
+    def __read_annotation(self, liptrp: Path) -> set:
+        def __strip_fragpipe_repilicate(sample: str) -> str:
+            return "_".join([_ for _ in sample.split("_")[:-1]])
+
+        annotation = liptrp.joinpath("experiment_annotation.tsv")
+
+        annotation_df = pl.read_csv(annotation, separator="\t")
+
+        annotation_dict = annotation_df.select(pl.col("sample")).to_dict(
+            as_series=False
+        )
+
+        return set(__strip_fragpipe_repilicate(sample) for sample in annotation_dict["sample"])