docs: change readthedocs template

Novartis · Jun 21, 2022 · 421e52f · 421e52f
1 parent 1f8f668
commit 421e52f
Show file tree

Hide file tree

Showing 18 changed files with 139 additions and 136 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 
 <p align="left">
-  <img src="docs/img/scAR_logo_white.png" width="250" title="scAR">
+  <img src="docs/_static/scAR_logo_white.png" width="250" title="scAR">
 </p>
 
 

diff --git a/docs/Installation.ipynb b/docs/Installation.ipynb
diff --git a/docs/Installation.rst b/docs/Installation.rst
@@ -0,0 +1,62 @@
+Installation
+================
+
+To use ``scAR``, first install it using conda install or Git+pip.
+
+Conda install
+-------------------------------
+
+1, Install `conda <https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html>`_
+
+2, Create conda environment::
+    
+    conda create -n scar
+
+3, Activate conda environment::
+    
+    conda activate scar
+    
+4, Install scar::
+
+    conda install -c bioconda scar
+    
+5, Activate the scar conda environment::
+
+    conda activate scar
+    
+Git + pip
+-------------------------------------------
+
+1, Clone scar repository::
+
+    git clone https://github.com/Novartis/scAR.git
+    
+2, Enter the cloned directory::
+
+    cd scAR
+    
+3, Create a conda environment
+
+.. tabs::
+
+   .. tab:: GPU version
+
+      .. code-block::
+         :caption: Please use ``scar-gpu`` if you have an nvidia graphics card and the corresponging driver installed
+            
+            conda env create -f scar-gpu.yml
+
+   .. tab:: CPU version
+
+      .. code-block:: 
+         :caption: Please use ``scar-cpu`` if you don't have a graphics card availalble
+            
+            conda env create -f scar-cpu.yml
+    
+4, Activate the scar conda environment::
+
+    conda activate scar
+
+
+
+
diff --git a/docs/Introduction.rst b/docs/Introduction.rst
@@ -4,21 +4,21 @@ Introduction
 What is ambient signal?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. image:: img/ambient_signal_hypothesis.png
+.. image:: _static/ambient_signal_hypothesis.png
    :width: 500
    :align: center
 
-During the preparation of the single-cell solution, RNA or protein counts are released upon cell lysis and consequently encapsulated by droplets. These exogenous molecules are mixed with native ones and barcoded by the same 10x bead, resulting in overestimated count data.
+During the preparation of the single-cell solution, RNA or protein counts are released upon cell lysis and consequently encapsulated by droplets. These exogenous molecules are mixed with native ones and barcoded by the same 10x beads, resulting in overestimated count data. The ambient signal harms the downstream analysis and even introduces significant bias in some cases (e.g. scCRISPR-seq and Cell multiplexing).
 
 The design of scAR
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. image:: img/overview_scAR.png
+.. image:: _static/overview_scAR.png
    :width: 600
    :align: center
 
 scAR uses a latent variable model to represent the biological and technical components in the observed count data. scAR is built under ambient signal hypothesis, in which the probability of occurrence of each ambient transcript can be empirically estimated from cell-free droplets. There are two hidden variables, contamination level per cell and the probability of occurrence of native transcript. With these three parameters, we are able to reconstruct the noisy observations. To learn the hidden variables, we train neural networks (the variational autoencoder) to minimize the differences between the reconstructions and original noisy observations. Once converging, the contamination levels and native expression are inferred and downstream analysis can be performed using these values. See our manuscript [Sheng2022]_ for details.
 
 What types of data that scAR can process?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-We applied scAR to scRNAseq data for denoising mRNA, scCRISPRseq data for sgRNA assignment, and CITE-seq data for denoising protein counts (ADT). In theory, any droplet-based single-cell omics technology has the ambient signal contamination issue, and scAR can be a good consideration.
+We validated scAR on scRNAseq for denoising mRNA, scCRISPR-seq for sgRNA assignment, cell multiplexing for tag assignment and CITE-seq for denoising protein counts (ADT). It recovers great number (33% ~ 50%) of cells in scCRISPR-seq and cell multiplexing experiments and significantly improves data quality in scRNAseq and CITE-seq. In theory, any droplet-based single-cell omics technology may have the ambient contamination issue, especially for the complex experiments. scAR can also be a reasonable solution in these cases.
diff --git a/docs/img/ambient_signal_hypothesis.png → docs/_static/ambient_signal_hypothesis.png b/docs/img/ambient_signal_hypothesis.png → docs/_static/ambient_signal_hypothesis.png
diff --git a/docs/img/overview_scAR.png → docs/_static/overview_scAR.png b/docs/img/overview_scAR.png → docs/_static/overview_scAR.png
diff --git a/docs/_static/scAR_favicon.png b/docs/_static/scAR_favicon.png
diff --git a/docs/img/scAR_logo_black.png → docs/_static/scAR_logo_black.png b/docs/img/scAR_logo_black.png → docs/_static/scAR_logo_black.png
diff --git a/docs/img/scAR_logo_transparent.png → docs/_static/scAR_logo_transparent.png b/docs/img/scAR_logo_transparent.png → docs/_static/scAR_logo_transparent.png
diff --git a/docs/img/scAR_logo_white.png → docs/_static/scAR_logo_white.png b/docs/img/scAR_logo_white.png → docs/_static/scAR_logo_white.png
diff --git a/docs/_static/scar-styles.css b/docs/_static/scar-styles.css
@@ -0,0 +1,4 @@
+body {
+    margin: 0;
+    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, "Helvetica Neue", Arial, "Noto Sans", "Liberation Sans", sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji";
+}
diff --git a/docs/_templates/layout.html b/docs/_templates/layout.html
@@ -0,0 +1,5 @@
+{# Import the theme's layout. #}
+{% extends "!layout.html" %}
+
+{# Custom CSS overrides #}
+{% set bootswatch_css_custom = ['_static/scar-styles.css'] %}
diff --git a/docs/conf.py b/docs/conf.py
@@ -9,23 +9,18 @@
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
-#
+
 import os
 import sys
 
 sys.path.insert(0, os.path.abspath("."))
 sys.path.insert(0, os.path.abspath(".."))
-# sys.path.insert(0, os.path.abspath('tutorials'))
 from scar.main.__version__ import __version__, _copyright
 
 # -- Project information -----------------------------------------------------
-
-
 project = "scAR"
 copyright = _copyright
 author = "Caibin Sheng"
-
-# The full version, including alpha/beta/rc tags
 release = __version__
 
 
@@ -46,20 +41,20 @@
     "sphinx.ext.napoleon",
     "autodocsumm",
     "matplotlib.sphinxext.plot_directive",
+    "sphinx_design",
+    "sphinx_tabs.tabs",
 ]
 
 nbsphinx_execute = "never"
 nbsphinx_allow_errors = True
 autosummary_generate = True
 # Add type of source files
 
-# source_suffix = ['.rst', '.md'] #, '.ipynb'
 nb_custom_formats = {
     ".md": ["jupytext.reads", {"fmt": "mystnb"}],
 }
 
 # Add any paths that contain templates here, relative to this directory.
-# templates_path = ["tutorials"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -74,16 +69,50 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_rtd_theme"
+html_theme = "pydata_sphinx_theme"
+templates_path = ["_templates"]
+html_static_path = ["_static"]
+html_css_files = ["scar-styles.css"]
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_logo = "img/scAR_logo_transparent.png"
+html_logo = "_static/scAR_logo_transparent.png"
 html_theme_options = {
-    "logo_only": True,
-    "display_version": True,
+    "logo": {
+        "image_light": "scAR_logo_white.png",
+        "image_dark": "scAR_logo_black.png",
+    },
+    "pygment_light_style": "tango",
+    "pygment_dark_style": "native",
+    "icon_links": [
+        {
+            "name": "GitHub",
+            "url": "https://github.com/Novartis/scar",
+            "icon": "fab fa-github-square",
+            "type": "fontawesome",
+        }
+    ],
+    "use_edit_page_button": True,
+    "favicons": [
+        {
+            "rel": "icon",
+            "sizes": "32x32",
+            "href": "scAR_favicon.png",
+        }
+    ],
+}
+html_context = {
+    "github_user": "Novartis",
+    "github_repo": "scar",
+    "github_version": "develop",
+    "doc_path": "docs",
 }
+
+# html_sidebars = {
+#     "**": ["search-field.html", "sidebar-nav-bs.html", "sidebar-ethical-ads.html"]
+# }
+
 autodoc_mock_imports = ["django"]
 autodoc_default_options = {
     "autosummary": True,

diff --git a/docs/index.rst b/docs/index.rst
@@ -7,7 +7,7 @@
 scAR
 ================================
 
-**scAR** (single-cell Ambient Remover) is a tool for denoising the ambient signals in droplet-based single cell omics. It can be used for multiple tasks, such as, **sgRNA assignment** for scCRISPRseq, **identity barcode assignment** for cell indexing, **protein denoising** for CITE-seq, **mRNA denoising** for scRNAseq, and etc..
+**scAR** (single-cell Ambient Remover) is an explainable machine learning model for denoising the ambient signals in droplet-based single cell omics. It can be used for multiple tasks, such as, **sgRNA assignment** for scCRISPR-seq, **identity barcode assignment** for cell multiplexing, **protein denoising** for CITE-seq, **mRNA denoising** for scRNAseq, and etc..
 
 It is developed by Oncology Data Science, Novartis Institute for BioMedical Research.
 
@@ -20,10 +20,8 @@ It is developed by Oncology Data Science, Novartis Institute for BioMedical Rese
    Introduction
    Installation
    usages/index
-   usages/Command_Line_Interface
    tutorials/Tutorials
    Release_notes
    Reference
    License
-   Contacts
-   GitHub <https://github.com/Novartis/scAR>
+   Contacts
diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -10,4 +10,6 @@ ipykernel
 protobuf==3.20.*
 anndata
 scanpy
+sphinx-design
+pydata-sphinx-theme
 git+https://github.com/Novartis/scAR.git
diff --git a/docs/usages/Command_Line_Interface.rst b/docs/usages/Command_Line_Interface.rst