documentation (formatting)

theislab · Aug 17, 2024 · cc7e67f · cc7e67f
1 parent 4ba78b2
commit cc7e67f
Show file tree

Hide file tree

Showing 10 changed files with 63 additions and 39 deletions.
diff --git a/docs/index.rst b/docs/index.rst
@@ -1,7 +1,7 @@
 MuBind - Learning sequence associations with single-cell transitions
 ================================================
 
-`muBind` (short for ***multibind***) is a neural network architecture designed to learn sequence associations with genomics data through the leveraging of sample-sample relationships as sparse graphs. The model architecture is suitable for the analysis of both single-cell as well as bulk genomics data.
+`muBind` (short for **multibind**) is a neural network architecture designed to learn sequence associations with genomics data through the leveraging of sample-sample relationships as sparse graphs. The model architecture is suitable for the analysis of both single-cell as well as bulk genomics data.
 
 .. image:: https://raw.githubusercontent.com/theislab/mubind/development/docs/_static/logo.png
     :alt: Mubind figure title

diff --git a/docs/installation.md b/docs/installation.md
@@ -1,6 +1,8 @@
 Installation
 ============
-`mubind` has been tested with Python version greater than 3.8.
+`mubind` main tests have been tested with Python versions greater than >=3.9, and is available via PyPI
+https://pypi.org/project/mubind/
+
 
 PyPI
 ----
@@ -11,3 +13,8 @@ Development version
 -------------------
 
     pip install git+https://github.com/theislab/mubind.git@main
+
+Pytest
+----
+
+    python -m pytest tests
diff --git a/docs/notebooks/batch/01_CTCF_two_batches.ipynb b/docs/notebooks/batch/01_CTCF_two_batches.ipynb
@@ -6,7 +6,7 @@
    "id": "28547fd9",
    "metadata": {},
    "source": [
-    "## Modeling HT-SELEX data [Jolma et al. 2013]"
+    "## CTCF HT-SELEX (Jolma et al. 2013) | Model training"
    ]
   },
   {

diff --git a/docs/notebooks/single_cell/02_2_1_scatac_multiome_pancreas_priors_train.ipynb b/docs/notebooks/single_cell/02_2_1_scatac_multiome_pancreas_priors_train.ipynb
@@ -5,7 +5,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Modeling scATAC-seq using sequence features and a custom kNN graph\n",
+    "## Mouse pancreatic endocrinogenesis (scATAC-seq) | Training with a RNA-dynamics kNN-graph"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "\n",
     "In this tutorial we demonstrate the applicability of mubind in a case where an arbitrarily complex graph is provided.\n",
     "The dataset is mouse pancreatic endocrinogenesis multiome [Klein et al 2023]\n"

diff --git a/docs/notebooks/single_cell/02_2_1_scrna_dentategyrus_priors_evaluate.ipynb b/docs/notebooks/single_cell/02_2_1_scrna_dentategyrus_priors_evaluate.ipynb
@@ -4,7 +4,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Model assessment\n",
+    "## Dentate gyrus (scRNA-seq) | Model evaluation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "Here we compared the weights learned by several model iterations, to highlight\n",
     "- Performance user parameter combinations\n",
     "- Interpretation based on TF regulators\n",
@@ -1622,7 +1628,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
+    "### Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
     "\n",
     "Load information from archetypes DB (Vierstra et al 2020)"
    ]
@@ -2391,9 +2397,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Observe general scores per case"
+    "### Observe general scores per case"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": 94,
@@ -6175,7 +6188,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Filter activities versus graph activities"
+    "### Filter activities versus graph activities"
    ]
   },
   {

diff --git a/docs/notebooks/single_cell/02_2_1_scrna_dentategyrus_train.ipynb b/docs/notebooks/single_cell/02_2_1_scrna_dentategyrus_train.ipynb
@@ -5,10 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Modeling scRNA-seq using sequence features and a custom kNN graph\n",
-    "\n",
-    "In this tutorial we demonstrate the applicability of mubind in a case where an arbitrarily complex graph is provided.\n",
-    "The dataset is mouse pancreatic endocrinogenesis multiome [Klein et al 2023]\n"
+    "## Dentate gyrus (scRNA-seq) | Training with a RNA-dynamics kNN-graph"
    ]
   },
   {

diff --git a/docs/notebooks/single_cell/02_2_1_scrna_noack_priors_evaluate.ipynb b/docs/notebooks/single_cell/02_2_1_scrna_noack_priors_evaluate.ipynb
@@ -4,7 +4,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Model assessment\n",
+    "## Mouse neurogenesis scRNA-seq (Noack et al. 2022) | Model evaluation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "Here we compared the weights learned by several model iterations, to highlight\n",
     "- Performance user parameter combinations\n",
     "- Interpretation based on TF regulators\n",
@@ -1481,7 +1487,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
+    "### Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
     "\n",
     "Load information from archetypes DB (Vierstra et al 2020)"
    ]
@@ -1965,7 +1971,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Observe general scores per case"
+    "### Observe general scores per case"
    ]
   },
   {
@@ -6230,7 +6236,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Filter activities versus graph activities"
+    "### Filter activities versus graph activities"
    ]
   },
   {

diff --git a/docs/notebooks/single_cell/02_2_1_scrna_noack_priors_train.ipynb b/docs/notebooks/single_cell/02_2_1_scrna_noack_priors_train.ipynb
@@ -5,10 +5,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Modeling scRNA-seq using sequence features and a custom kNN graph\n",
-    "\n",
-    "In this tutorial we demonstrate the applicability of mubind in a case where an arbitrarily complex graph is provided.\n",
-    "The dataset is mouse pancreatic endocrinogenesis multiome [Klein et al 2023]\n"
+    "## Mouse neurogenesis scRNA-seq (Noack et al. 2022) | Training with a RNA-dynamics kNN-graph\n"
    ]
   },
   {

diff --git a/docs/notebooks/single_cell/02_2_2_scatac_multiome_pancreas_priors_evaluate.ipynb b/docs/notebooks/single_cell/02_2_2_scatac_multiome_pancreas_priors_evaluate.ipynb
@@ -1,5 +1,12 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Mouse pancreatic endocrinogenesis (scATAC-seq) | Model evaluation"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -1485,7 +1492,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
+    "### Study the asssociations betweeen obtained weights and cluster-specific transcription factors\n",
     "\n",
     "Load information from archetypes DB (Vierstra et al 2020)"
    ]
@@ -1955,7 +1962,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Observe general scores per case"
+    "### Observe general scores per binding layer filter"
    ]
   },
   {
@@ -5862,7 +5869,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Filter activities versus graph activities"
+    "### Filter activities versus graph activities"
    ]
   },
   {

diff --git a/docs/tutorials.rst b/docs/tutorials.rst
@@ -1,28 +1,17 @@
-# Tutorials
-
 Tutorials
 =========
 
-**Note** Code is pre-release and outputs are provisory. Changes will occur in upcoming versions.
-
-The first half of tutorials ire focused on single-cell genomics. For general applications in genomics data (HT-SELEX, ChIP-seq, etc.), please refer to the second list of tutorials.
-
-To test library installation and dependencies, please check general pytests. In case of bugs, please submit a GitHub issue.
-https://github.com/theislab/mubind/issues
-
-Testing
-----
-    pytest tests
+The first section is focused on single-cell genomics. For general applications in genomics data (HT-SELEX, ChIP-seq, etc.), please refer to the second section (bulk).
 
 Single-cell genomics analysis using :mod:`mubind`
 -------------------------------------------------
 .. toctree::
     :maxdepth: 1
 
-    notebooks/single_cell/02_2_1_scrna_dentategyrus_priors_train
+    notebooks/single_cell/02_2_1_scrna_dentategyrus_train
     notebooks/single_cell/02_2_1_scrna_dentategyrus_priors_evaluate
     notebooks/single_cell/02_2_1_scatac_multiome_pancreas_priors_train
-    notebooks/single_cell/02_2_1_scatac_multiome_pancreas_priors_evaluate
+    notebooks/single_cell/02_2_2_scatac_multiome_pancreas_priors_evaluate
     notebooks/single_cell/02_2_1_scrna_noack_priors_train
     notebooks/single_cell/02_2_1_scrna_noack_priors_evaluate
 
@@ -33,7 +22,9 @@ Bulk data analysis using :mod:`mubind`
 
     notebooks/batch/01_CTCF_two_batches
 
-Missing tutorials
+Troubleshooting
 -------------------------------------------------
 
-If you wish to suggest a public dataset for a tutorial, please submit an [issue](https://github.com/theislab/mubind/issues).
+**Note** Notebooks outputs are provisory while release documentation is updated. 
+
+If you find issues while executing the tutorials, or wish to suggest a dataset for a tutorial, please reach out and/or submit an issue at https://github.com/theislab/mubind/issues