mmm4microbiome 0.1.0__tar.gz

mmm4microbiome-0.1.0/.gitignore

@@ -0,0 +1,16 @@
+# local case studies (data + caches) -- never committed
+example/
+
+# environments and builds
+.venv/
+dist/
+build/
+*.egg-info/
+
+# caches
+__pycache__/
+*.py[cod]
+.pytest_cache/
+__marimo__/
+.ipynb_checkpoints/
+.DS_Store

mmm4microbiome-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 peiyang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

mmm4microbiome-0.1.0/PKG-INFO

@@ -0,0 +1,111 @@
+Metadata-Version: 2.5
+Name: mmm4microbiome
+Version: 0.1.0
+Summary: Read a StripeSankey sweep of mixed-membership models as microbiome: microbial components (MC), their taxa, and the samples behind them
+Project-URL: Homepage, https://gitlab.kuleuven.be/aida-lab/public/mmm4microbiome
+Project-URL: Repository, https://gitlab.kuleuven.be/aida-lab/public/mmm4microbiome.git
+Author-email: Peiyang Huo <peiyang.huo@kuleuven.be>
+Maintainer-email: Peiyang Huo <peiyang.huo@kuleuven.be>
+License: MIT License
+        
+        Copyright (c) 2025 peiyang
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Keywords: LDA,NMF,anywidget,microbiome,mixed-membership,stripesankey,topic-modeling,visualization
+Classifier: Development Status :: 3 - Alpha
+Classifier: Framework :: Jupyter
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Classifier: Topic :: Scientific/Engineering :: Visualization
+Requires-Python: >=3.9
+Requires-Dist: anywidget>=0.9.0
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: plotly>=5.0.0
+Requires-Dist: scipy>=1.7.0
+Requires-Dist: stripesankey>=0.4.1
+Requires-Dist: traitlets>=5.0.0
+Provides-Extra: daa
+Requires-Dist: scikit-bio>=0.7.0; extra == 'daa'
+Requires-Dist: statsmodels>=0.14.0; extra == 'daa'
+Provides-Extra: static
+Requires-Dist: kaleido>=1.0.0; extra == 'static'
+Description-Content-Type: text/markdown
+
+# mmm4microbiome
+
+mmm4microbiome is the microbiome layer on top of
+[stripesankey](https://pypi.org/project/stripesankey/) (>= 0.4.1). *mmm4microbiome* reads the output of *stripesankey* and makes interpretation plots for microbiome data analysis.
+
+## Install
+
+```bash
+pip install mmm4microbiome # with pip
+uv add mmm4microbiome # with uv
+```
+
+## Input: a stripesankey base folder
+
+Everything takes a `base` folder written by *stripesankey*:
+
+```python
+import stripesankey as ss
+
+ss.prepare(base, counts, feature_annotation, metadata, level="Genus")
+ss.sweep(base, k_range=range(2, 11))
+```
+
+## Use
+
+```python
+import mmm4microbiome as mmm
+
+# the sweep, with captions like "MC3 · Prevotella"
+mmm.stripesankey_mb(base, metadata_df=meta, hover_field="METADATA_COLUMN")
+mmm.metasankey_mb(base, metadata_df=meta, hover_field="METADATA_COLUMN")
+
+# one k, sample by sample
+mmm.heatmap_sample(base, 5, metadata_df=meta, include=["METADATA_COLUMN"])
+mmm.bar_sample(base, 5, metadata_df=meta, sort="METADATA_COLUMN")
+
+# what the MCs are made of
+mmm.heatmap_mc(base, 5, feature_level="Family")
+
+# everything in one self-contained HTML page: base/visualization/onestop_app.html
+mmm.onestop(base, meta)
+```
+
+### Taxonomic levels
+
+The **fit level** is what `prepare(level=)` collapsed the counts to. The
+**display level** (`feature_level=`) is what a figure names. By default it is
+the fit level, except that an ASV (or Species) fit is shown at Genus. A coarser
+level sums the probabilities of its child taxa; a level finer than the fit
+cannot be recovered and falls back to the fit level with a warning.
+
+## License
+
+MIT

mmm4microbiome-0.1.0/README.md

@@ -0,0 +1,54 @@
+# mmm4microbiome
+
+mmm4microbiome is the microbiome layer on top of
+[stripesankey](https://pypi.org/project/stripesankey/) (>= 0.4.1). *mmm4microbiome* reads the output of *stripesankey* and makes interpretation plots for microbiome data analysis.
+
+## Install
+
+```bash
+pip install mmm4microbiome # with pip
+uv add mmm4microbiome # with uv
+```
+
+## Input: a stripesankey base folder
+
+Everything takes a `base` folder written by *stripesankey*:
+
+```python
+import stripesankey as ss
+
+ss.prepare(base, counts, feature_annotation, metadata, level="Genus")
+ss.sweep(base, k_range=range(2, 11))
+```
+
+## Use
+
+```python
+import mmm4microbiome as mmm
+
+# the sweep, with captions like "MC3 · Prevotella"
+mmm.stripesankey_mb(base, metadata_df=meta, hover_field="METADATA_COLUMN")
+mmm.metasankey_mb(base, metadata_df=meta, hover_field="METADATA_COLUMN")
+
+# one k, sample by sample
+mmm.heatmap_sample(base, 5, metadata_df=meta, include=["METADATA_COLUMN"])
+mmm.bar_sample(base, 5, metadata_df=meta, sort="METADATA_COLUMN")
+
+# what the MCs are made of
+mmm.heatmap_mc(base, 5, feature_level="Family")
+
+# everything in one self-contained HTML page: base/visualization/onestop_app.html
+mmm.onestop(base, meta)
+```
+
+### Taxonomic levels
+
+The **fit level** is what `prepare(level=)` collapsed the counts to. The
+**display level** (`feature_level=`) is what a figure names. By default it is
+the fit level, except that an ASV (or Species) fit is shown at Genus. A coarser
+level sums the probabilities of its child taxa; a level finer than the fit
+cannot be recovered and falls back to the fit level with a warning.
+
+## License
+
+MIT

mmm4microbiome-0.1.0/pyproject.toml

@@ -0,0 +1,90 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "mmm4microbiome"
+dynamic = ["version"]
+description = "Read a StripeSankey sweep of mixed-membership models as microbiome: microbial components (MC), their taxa, and the samples behind them"
+readme = "README.md"
+license = {file = "LICENSE"}
+authors = [
+    {name = "Peiyang Huo", email = "peiyang.huo@kuleuven.be"}
+]
+maintainers = [
+    {name = "Peiyang Huo", email = "peiyang.huo@kuleuven.be"}
+]
+keywords = [
+    "microbiome",
+    "mixed-membership",
+    "topic-modeling",
+    "LDA",
+    "NMF",
+    "stripesankey",
+    "anywidget",
+    "visualization",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Topic :: Scientific/Engineering :: Bio-Informatics",
+    "Topic :: Scientific/Engineering :: Visualization",
+    "Framework :: Jupyter",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+requires-python = ">=3.9"
+dependencies = [
+    # the upstream: prepare / sweep / consensus write the base folder this
+    # package reads, and its widget draws the Sankey (>= 0.4.1 for the
+    # per-component annotation interface).
+    "stripesankey>=0.4.1",
+    "numpy>=1.20.0",
+    "pandas>=1.3.0",
+    "scipy>=1.7.0",
+    "anywidget>=0.9.0",
+    "traitlets>=5.0.0",
+    "plotly>=5.0.0",
+]
+
+[project.optional-dependencies]
+# compare_groups(): differential abundance (ANCOM-BC, Dirichlet-multinomial,
+# Wilcoxon on CLR) and PERMANOVA. Imported only when compare_groups runs.
+daa = [
+    "scikit-bio>=0.7.0",
+    "statsmodels>=0.14.0",
+]
+# .svg / .png output of the plotly figures (heatmap_mc, mc_profile, da_barplot).
+static = [
+    "kaleido>=1.0.0",
+]
+
+[dependency-groups]
+dev = [
+    "pytest>=7.0",
+]
+
+[project.urls]
+Homepage = "https://gitlab.kuleuven.be/aida-lab/public/mmm4microbiome"
+Repository = "https://gitlab.kuleuven.be/aida-lab/public/mmm4microbiome.git"
+
+[tool.hatch.version]
+path = "src/mmm4microbiome/__init__.py"
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "src/mmm4microbiome",
+    "tests",
+    "README.md",
+    "LICENSE",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/mmm4microbiome"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

mmm4microbiome-0.1.0/src/mmm4microbiome/__init__.py

@@ -0,0 +1,47 @@
+"""
+mmm4microbiome: read a mixed-membership sweep as microbiome.
+
+Downstream of ``stripesankey`` (>= 0.4.1): ``stripesankey.prepare`` and
+``stripesankey.sweep`` write a base folder, and everything here reads it. A
+component is called **MC** (microbial component), and its H row is mapped to
+taxa through ``feature_annotation.csv``. Fitting, consensus and the Sankey
+widget itself stay in stripesankey::
+
+    import stripesankey as ss
+    import mmm4microbiome as mmm
+
+    ss.prepare(base, counts, feature_annotation, metadata, level="Genus")
+    ss.sweep(base, k_range=range(2, 11))
+
+    mmm.stripesankey_mb(base, metadata_df=meta, hover_field="Country")
+    mmm.heatmap_mc(base, 5)
+    mmm.compare_groups(base, "K5MC2", "K5MC0")
+    mmm.onestop(base, meta)
+"""
+
+__version__ = "0.1.0"
+
+from ._base import (dominant_samples, fit_level, k_values, load_clusters, load_counts,
+                    load_mc, mc_feature_table, parse_mc, taxonomy_for_features)
+from .sankey import stripesankey_mb, metasankey_mb
+from .sample import SampleHeatmapInline, heatmap_sample, bar_sample
+from .features import heatmap_mc, mc_profile
+from .da_barplot import da_barplot
+from .compare import compare_groups, CompareReport, DAA_METHODS
+from .onestop import onestop
+
+__all__ = [
+    # the base folder
+    "k_values", "fit_level", "load_mc", "load_clusters", "load_counts",
+    "mc_feature_table", "taxonomy_for_features", "parse_mc", "dominant_samples",
+    # the sweep
+    "stripesankey_mb", "metasankey_mb",
+    # one k, sample by sample
+    "SampleHeatmapInline", "heatmap_sample", "bar_sample",
+    # what the MCs are made of
+    "heatmap_mc", "mc_profile",
+    # two groups compared
+    "compare_groups", "CompareReport", "DAA_METHODS", "da_barplot",
+    # everything in one page
+    "onestop",
+]