peak-performance 0.7.0__py3-none-any.whl → 0.7.1__py3-none-any.whl

peak_performance/models.py

@@ -1,19 +1,20 @@
-"""
-PeakPerformance
-Copyright (C) 2023 Forschungszentrum Jülich GmbH
+# PeakPerformance
+# Copyright (C) 2023 Forschungszentrum Jülich GmbH
 
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU Affero General Public License as published
-by the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
 
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU Affero General Public License for more details.
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
 
-You should have received a copy of the GNU Affero General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+This module contains functions for creating various kinds of peak models and to make initial guesses for their parameters.
 """
 
 from enum import Enum
@@ -28,12 +29,19 @@ import scipy.stats as st
 
 
 class ModelType(str, Enum):
-    """Class containing all implemented model types."""
+    """Enum of default model types."""
 
     Normal = "normal"
+    """Shape of a Gaussian Normal PDF."""
+
     SkewNormal = "skew_normal"
+    """Shape of a skewed Normal PDF."""
+
     DoubleNormal = "double_normal"
+    """Superposition of two ``Normal`` peaks."""
+
     DoubleSkewNormal = "double_skew_normal"
+    """Superposition of two ``SkewedNormal`` peaks."""
 
 
 def guess_noise(intensity):
@@ -392,10 +400,9 @@ def std_skew_calculation(scale, alpha):
         Skewness parameter of the skew normal distribution.
 
     Returns
-    ----------
+    -------
     std
         Standard deviation of a skew normal distribution.
-    -------
     """
     return np.sqrt(scale**2 * (1 - (2 * alpha**2) / ((alpha**2 + 1) * np.pi)))
 
@@ -414,7 +421,7 @@ def mean_skew_calculation(loc, scale, alpha):
         Skewness parameter of the skew normal distribution.
 
     Returns
-    ----------
+    -------
     mean
         Arithmetic mean of a skew normal distribution.
     """
@@ -488,7 +495,7 @@ def height_calculation(area, loc, scale, alpha, mode_skew):
         Mode of the skew normal distribution.
 
     Returns
-    ----------
+    -------
     mean
         Arithmetic mean of a skew normal distribution.
     """

peak_performance/pipeline.py

@@ -1,19 +1,20 @@
-"""
-PeakPerformance
-Copyright (C) 2023 Forschungszentrum Jülich GmbH
+# PeakPerformance
+# Copyright (C) 2023 Forschungszentrum Jülich GmbH
 
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU Affero General Public License as published
-by the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
 
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU Affero General Public License for more details.
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
 
-You should have received a copy of the GNU Affero General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+Defines steps for a pipeline to process LC-MS-MS data.
 """
 
 import importlib
@@ -1186,7 +1187,7 @@ def pipeline(
         Data format (suffix) of the raw data, default is '.npy'.
 
     Returns
-    ----------
+    -------
     path_results
         Path variable pointing to the newly created folder for this batch.
     """
@@ -1223,7 +1224,7 @@ def pipeline_restart(
         Path variable pointing to the directory of the broken PeakPerformance batch
 
     Returns
-    ----------
+    -------
     path_results_new
         Path variable pointing to the newly created folder for the restarted batch.
     """
@@ -1322,7 +1323,7 @@ def parse_files_for_model_selection(signals: pandas.DataFrame) -> Dict[str, str]
         DataFrame containing the signals tab of Template.xlsx.
 
     Returns
-    ----------
+    -------
     files_for_selection
         Dict with file names as keys and unique identifiers as values.
     """
@@ -1429,7 +1430,7 @@ def model_selection_check(
         to be accepted.
 
     Returns
-    ----------
+    -------
     selected_model
         Name of the selected model type.
     """
@@ -1472,7 +1473,7 @@ def selection_loop(
         "waic": widely applicable information criterion)
 
     Returns
-    ----------
+    -------
     result_df
         DataFrame containing the ranking and scores of the model selection.
     model_dict
@@ -1564,7 +1565,7 @@ def model_selection(path_raw_data: Union[str, os.PathLike], *, ic: str = "loo"):
         "waic": widely applicable information criterion)
 
     Returns
-    ----------
+    -------
     comparison_results
         DataFrame containing all rankings from model selection.
     model_dict

peak_performance/plots.py

@@ -1,19 +1,20 @@
-"""
-PeakPerformance
-Copyright (C) 2023 Forschungszentrum Jülich GmbH
+# PeakPerformance
+# Copyright (C) 2023 Forschungszentrum Jülich GmbH
 
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU Affero General Public License as published
-by the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published
+# by the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
 
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU Affero General Public License for more details.
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
 
-You should have received a copy of the GNU Affero General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+Functions for preparing diagnostic and QC plots.
 """
 
 import os

peak_performance-0.7.1.dist-info/METADATA

@@ -0,0 +1,48 @@
+Metadata-Version: 2.1
+Name: peak-performance
+Version: 0.7.1
+Summary: A Python toolbox to fit chromatography peaks with uncertainty.
+Author-email: Jochen Nießer <j.niesser@fz-juelich.de>, Michael Osthege <m.osthege@fz-juelich.de>
+License: AGPLv3
+Project-URL: homepage, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
+Project-URL: documentation, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
+Project-URL: repository, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
+Keywords: hplc,mass-spectrometry,uncertainty quantification
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: License :: OSI Approved :: GNU Affero General Public License v3
+Classifier: Intended Audience :: Science/Research
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.md
+Requires-Dist: arviz
+Requires-Dist: matplotlib
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pymc>=5.9.1
+Requires-Dist: pytensor
+Requires-Dist: scipy
+Requires-Dist: openpyxl
+
+[![PyPI version](https://img.shields.io/pypi/v/peak-performance)](https://pypi.org/project/peak-performance/)
+[![pipeline](https://github.com/jubiotech/peak-performance/workflows/pipeline/badge.svg)](https://github.com/JuBiotech/peak-performance/actions)
+[![coverage](https://codecov.io/gh/jubiotech/peak-performance/branch/main/graph/badge.svg)](https://app.codecov.io/gh/JuBiotech/peak-performance)
+[![documentation](https://readthedocs.org/projects/peak-performance/badge/?version=latest)](https://peak-performance.readthedocs.io/en/latest)
+[![DOI](https://zenodo.org/badge/713469041.svg)](https://zenodo.org/doi/10.5281/zenodo.10255543)
+
+# About PeakPerformance
+PeakPerformance employs Bayesian modeling for chromatographic peak data fitting.
+This has the innate advantage of providing uncertainty quantification while jointly estimating all peak parameters united in a single peak model.
+As Markov Chain Monte Carlo (MCMC) methods are utilized to infer the posterior probability distribution, convergence checks and the aformentioned uncertainty quantification are applied as novel quality metrics for a robust peak recognition.
+
+# First steps
+Be sure to check out our thorough [documentation](https://peak-performance.readthedocs.io/en/latest). It contains not only information on how to install PeakPerformance and prepare raw data for its application but also detailed treatises about the implemented model structures, validation with both synthetic and experimental data against a commercially available vendor software, exemplary usage of diagnostic plots and investigation of various effects.
+Furthermore, you will find example notebooks and data sets showcasing different aspects of PeakPerformance.
+
+# How to contribute
+If you encounter bugs while using PeakPerformance, please bring them to our attention by opening an issue. When doing so, describe the problem in detail and add screenshots/code snippets and whatever other helpful material you can provide.
+When contributing code, create a local clone of PeakPerformance, create a new branch, and open a pull request (PR).
+
+# How to cite
+Head over to Zenodo to [generate a BibTeX citation](https://doi.org/10.5281/zenodo.10255543) for the latest release.
+A publication has just been submitted to a scientific journal. Once published, this section will be updated.

peak_performance-0.7.1.dist-info/RECORD

@@ -0,0 +1,13 @@
+peak_performance/__init__.py,sha256=yTq4THYewbWRnrs2Qkv4nCd-7MyvDlu_t0fPeWeKxQc,261
+peak_performance/models.py,sha256=m32qCkEW00E3WV5d8xDlcMVHvdmcLH0fRnziPLsgDMk,27755
+peak_performance/pipeline.py,sha256=O38AtmtGTA4fFYj78S836TgcFa1nuyf6npsbIM7DGec,64456
+peak_performance/plots.py,sha256=JToIsNxGF-uh09t8IJvN9cWRTsL3opjDE8DMqGocYJQ,9528
+peak_performance/test_main.py,sha256=xQiLDjhldxZzY5sp3RyIJUTtXxX46auWY9Qy7nuifxw,97
+peak_performance/test_models.py,sha256=r6kqAVBtAbycf4IoRaXcSCZp6Lras3afK6o9qcLZbH8,11592
+peak_performance/test_pipeline.py,sha256=gTZAxcJEVwJ0XW4IewmIWGLmx1n7KaK8egrovKHsCFI,22961
+peak_performance/test_plots.py,sha256=lGwPWzezAhzEnyu_NMx2lFtyzzb1wxy-jnRMtOaaniY,4100
+peak_performance-0.7.1.dist-info/LICENSE.md,sha256=zj-4LZ7oChyw5Uj5sFYOrVI3juK06Cb9lFm0rPcHXYk,32387
+peak_performance-0.7.1.dist-info/METADATA,sha256=62R5sa4j-zdBzwVQRBaUD9cfS6pXvfPqUBpEUx0rVmk,3388
+peak_performance-0.7.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+peak_performance-0.7.1.dist-info/top_level.txt,sha256=-lZSmgn2fZA-xPVmddLwaRt2hQeeWj7TYVefOk7_T58,17
+peak_performance-0.7.1.dist-info/RECORD,,

{peak_performance-0.7.0.dist-info → peak_performance-0.7.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: bdist_wheel (0.44.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

peak_performance-0.7.0.dist-info/METADATA

@@ -1,68 +0,0 @@
-Metadata-Version: 2.1
-Name: peak-performance
-Version: 0.7.0
-Summary: A Python toolbox to fit chromatography peaks with uncertainty.
-Author-email: Jochen Nießer <j.niesser@fz-juelich.de>, Michael Osthege <m.osthege@fz-juelich.de>
-License: AGPLv3
-Project-URL: homepage, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
-Project-URL: documentation, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
-Project-URL: repository, https://jugit.fz-juelich.de/IBG-1/micropro/peak-performance
-Keywords: hplc,mass-spectrometry,uncertainty quantification
-Classifier: Programming Language :: Python :: 3
-Classifier: Operating System :: OS Independent
-Classifier: License :: OSI Approved :: GNU Affero General Public License v3
-Classifier: Intended Audience :: Science/Research
-Requires-Python: >=3.9
-Description-Content-Type: text/markdown
-License-File: LICENSE.md
-Requires-Dist: arviz
-Requires-Dist: matplotlib
-Requires-Dist: numpy
-Requires-Dist: pandas
-Requires-Dist: pymc >=5.9.1
-Requires-Dist: pytensor
-Requires-Dist: scipy
-Requires-Dist: openpyxl
-Requires-Dist: numpy <1.26.0
-
-[![PyPI version](https://img.shields.io/pypi/v/peak-performance)](https://pypi.org/project/peak-performance/)
-[![pipeline](https://github.com/jubiotech/peak-performance/workflows/pipeline/badge.svg)](https://github.com/JuBiotech/peak-performance/actions)
-[![coverage](https://codecov.io/gh/jubiotech/peak-performance/branch/main/graph/badge.svg)](https://app.codecov.io/gh/JuBiotech/peak-performance)
-[![documentation](https://readthedocs.org/projects/peak-performance/badge/?version=latest)](https://peak-performance.readthedocs.io/en/latest)
-[![DOI](https://zenodo.org/badge/713469041.svg)](https://zenodo.org/doi/10.5281/zenodo.10255543)
-
-# How to use PeakPerformance
-For installation instructions, see `Installation.md`.
-For instructions regarding the use of PeakPerformance, check out the example notebook(s) under `notebooks`, the complementary example data under `example`, and the following introductory explanations.
-
-## Preparing raw data
-This step is crucial when using PeakPerformance. Raw data has to be supplied as time series meaning for each signal you want to analyze, save a NumPy array consisting of time in the first dimension and intensity in the second dimension (compare example data). Both time and intensity should also be NumPy arrays. If you e.g. have time and intensity of a singal as lists, you can use the following code to convert, format, and save them in the correct manner:
-
-```python
-import numpy as np
-from pathlib import Path
-
-time_series = np.array([np.array(time), np.array(intensity)])
-np.save(Path(r"example_path/time_series.npy"), time_series)
-```
-
-The naming convention of raw data files is `<acquisition name>_<precursor ion m/z or experiment number>_<product ion m/z start>_<product ion m/z end>.npy`. There should be no underscores within the named sections such as `acquisition name`. Essentially, the raw data names include the acquisition and mass trace, thus yielding a recognizable and unique name for each isotopomer/fragment/metabolite/sample.
-
-## Model selection
-When it comes to selecting models, PeakPerformance has a function performing an automated selection process by analyzing one acquisiton per mass trace with all implemented models. Subsequently, all models are ranked based on an information criterion (either pareto-smoothed importance sampling leave-one-out cross-validation or widely applicable information criterion). For this process to work as intended, you need to specify acquisitions with representative peaks for each mass trace (see example notebook 1). If e.g. most peaks of an analyte show a skewed shape, then select an acquisition where this is the case. For double peaks, select an acquision where the peaks are as distinct and comparable in height as possible.
-Since model selection is a computationally demanding and time consuming process, it is suggested to state the model type as the user (see example notebook 1) if possible.
-
-## Troubleshooting
-### A batch run broke and I want to restart it.
-If an error occured in the middle of a batch run, then you can use the `pipeline_restart` function in the `pipeline` module to create a new batch which will analyze only those samples, which have not been analyzed previously.
-
-### The model parameters don't converge and/or the fit does not describe the raw data well.
-Check the separate file `How to adapt PeakPerformance to your data`.
-
-# How to contribute
-If you encounter bugs while using PeakPerformance, please bring them to our attention by opening an issue. When doing so, describe the problem in detail and add screenshots/code snippets and whatever other helpful material you can provide.
-When contributing code, create a local clone of PeakPerformance, create a new branch, and open a pull request (PR).
-
-# How to cite
-Head over to Zenodo to [generate a BibTeX citation](https://doi.org/10.5281/zenodo.10255543) for the latest release.
-A publication has just been submitted to a scientific journal. Once published, this section will be updated.

peak_performance-0.7.0.dist-info/RECORD

@@ -1,13 +0,0 @@
-peak_performance/__init__.py,sha256=yTq4THYewbWRnrs2Qkv4nCd-7MyvDlu_t0fPeWeKxQc,261
-peak_performance/models.py,sha256=HpJzjf9Eq1ZXUxKlX6GZDj21icL4s_G0naJrCgWntcM,27457
-peak_performance/pipeline.py,sha256=8yy2-hTNozBJeLE_dulQJCzCBWv2CoRRdXSHDN2UwD8,64395
-peak_performance/plots.py,sha256=5F-s7ZcFgZuN5xGIWRSJ5-_Pl99-vqbcr3F8dYnBFQc,9455
-peak_performance/test_main.py,sha256=xQiLDjhldxZzY5sp3RyIJUTtXxX46auWY9Qy7nuifxw,97
-peak_performance/test_models.py,sha256=r6kqAVBtAbycf4IoRaXcSCZp6Lras3afK6o9qcLZbH8,11592
-peak_performance/test_pipeline.py,sha256=gTZAxcJEVwJ0XW4IewmIWGLmx1n7KaK8egrovKHsCFI,22961
-peak_performance/test_plots.py,sha256=lGwPWzezAhzEnyu_NMx2lFtyzzb1wxy-jnRMtOaaniY,4100
-peak_performance-0.7.0.dist-info/LICENSE.md,sha256=zj-4LZ7oChyw5Uj5sFYOrVI3juK06Cb9lFm0rPcHXYk,32387
-peak_performance-0.7.0.dist-info/METADATA,sha256=uAz1t9qggYqguLgLPJ611PjUOYKM8CWJQLXbH3u8RsY,5076
-peak_performance-0.7.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-peak_performance-0.7.0.dist-info/top_level.txt,sha256=-lZSmgn2fZA-xPVmddLwaRt2hQeeWj7TYVefOk7_T58,17
-peak_performance-0.7.0.dist-info/RECORD,,