Update contributing, testing and add documentation intro. (#88)

* Update docs

* Add cit

* Add cleanup

CONTRIBUTING.md

@@ -23,21 +23,27 @@ To help us integrate your changes, please follow our standard process:
     - Document your code as you go.
     - Add unit and integration tests for your code.
 6. Run tests.
-    - Run unit tests: `pytest --cov chemicalx/tests/unit`
-    - Run integration tests: `pytest --cov chemicalx/tests/integration`
-    - Make sure that your contributions have test coverage.
-7. Update the documentation with your changes.
+    - Run unit tests: `tox -e py`
+    - Make sure that your contributions have (near) complete test coverage.
+7. Ensure that you comply with the formatting requirements:
+    - Check code quality: `tox -e flake8`
+    - Check typing: `tox -e mypy`
+9. Update the documentation with your changes.
     - Documentation is located in docs/.
     - Add new classes or modules to API documents.
     - Add new/changed functionality to the tutorials or quickstart.
     - Add code snippets (these are tested when docs are built so make them small and quick to run).
-8. When finished, push your branch and make a Pull Request (PR).
+10. Ensure the documentation quality.
+    - Lint the documentation: `tox -e doc8`
+    - Check the documentation coverage `tox -e docstr-coverage`
+    - Check the documentation build: `tox -e docs`
+11. When finished, push your branch and make a Pull Request (PR).
     - `git push origin <your branch name>` to push the branch
     - Go to https://github.com/AstraZeneca/chemicalx/pulls and use our PR template located at: ./pull_request_template.md.
       to open a PR from <your branch name>.
     - Describe changes and clearly highlight any major or breaking changes.
     - If any errors occur on the test builds, please fix them.
     - You are responsible for getting your PR merged so please chase down your reviewers.
-9. Adjust your PR based on any feedback
+12. Adjust your PR based on any feedback
     - We use the [DO, TRY, CONSIDER](https://jackiebo.medium.com/do-try-consider-how-we-give-product-feedback-at-asana-db9bc754cc4a) framework to give constructive feedback.
-10. After approval, you are responsible for completing your PR .
+13. After approval, you are responsible for completing your PR .

README.md

@@ -19,8 +19,9 @@
 [![Docs Status][docs-image]][docs-url]
 [![Code Coverage][coverage-image]][coverage-url]
 [![Build Status][build-image]][build-url]
+[![Arxiv](https://img.shields.io/badge/ArXiv-2202.05240-orange.svg)](https://arxiv.org/abs/2202.05240)
 
-**[Documentation](https://chemicalx.readthedocs.io)** | **[External Resources](https://chemicalx.readthedocs.io/en/latest/notes/resources.html)** | **[Datasets](https://chemicalx.readthedocs.io/en/latest/notes/introduction.html#datasets)** | **[Examples](https://github.com/AstraZeneca/chemicalx/tree/main/examples)**
+**[Documentation](https://chemicalx.readthedocs.io)** | **[External Resources](https://chemicalx.readthedocs.io/en/latest/notes/resources.html)** | **[Datasets](https://chemicalx.readthedocs.io/en/latest/notes/introduction.html#datasets)** | **[Examples](https://github.com/AstraZeneca/chemicalx/tree/main/examples)** 
 
 *ChemicalX* is a deep learning library for drug-drug interaction, polypharmacy side effect, and synergy prediction. The library consists of data loaders and integrated benchmark datasets. It also includes state-of-the-art deep neural network architectures that solve the [drug pair scoring task](https://arxiv.org/pdf/2111.02916v4.pdf). Implemented methods cover traditional SMILES string based techniques and neural message passing based models.
 
@@ -167,7 +168,7 @@ where `${CUDA}` should be replaced by either `cpu`, `cu102`, or `cu111` dependin
 **Running tests**
 
 ```
-$ python setup.py test
+$ tox -e py
 ```
 --------------------------------------------------------------------------------
 

docs/source/index.rst

@@ -3,7 +3,23 @@
 ChemicalX Documentation
 =======================
 
-
+ChemicalX is a deep learning library for drug-drug interaction, polypharmacy
+side effect, and synergy prediction. The library consists of data loaders
+and integrated benchmark datasets. It also includes state-of-the-art deep
+neural network architectures that solve the drug pair scoring task.
+Implemented methods cover traditional SMILES string based techniques
+and neural message passing based models.
+
+.. code-block:: latex
+
+     >@article{chemicalx,
+               arxivId = {2202.05240},
+               author = {Rozemberczki, Benedek and Hoyt, Charles Tapley and Gogleva, Anna and Grabowski, Piotr and Karis, Klas and Lamov, Andrej and Nikolov, Andriy and Nilsson, Sebastian and Ughetto, Michael and Wang, Yu and Derr, Tyler and Gyori, Benjamin M},
+               month = {feb},
+               title = {{ChemicalX: A Deep Learning Library for Drug Pair Scoring}},
+               url = {http://arxiv.org/abs/2202.05240},
+               year = {2022}
+     }
 
 .. toctree::
    :glob:
@@ -22,6 +38,7 @@ ChemicalX Documentation
 
    notes/installation
    notes/introduction
+   notes/tutorial
    notes/data_processing
    notes/resources
 

docs/source/notes/introduction.rst

@@ -1,6 +1,25 @@
-Introduction by example
+Introduction
 =======================
 
+ChemicalX is a deep learning library for drug-drug interaction, polypharmacy
+side effect, and synergy prediction. The library consists of data loaders
+and integrated benchmark datasets. It also includes state-of-the-art deep
+neural network architectures that solve the drug pair scoring task.
+Implemented methods cover traditional SMILES string based techniques
+and neural message passing based models.
+
+.. code-block:: latex
+
+     >@article{chemicalx,
+               arxivId = {2202.05240},
+               author = {Rozemberczki, Benedek and Hoyt, Charles Tapley and Gogleva, Anna and Grabowski, Piotr and Karis, Klas and Lamov, Andrej and Nikolov, Andriy and Nilsson, Sebastian and Ughetto, Michael and Wang, Yu and Derr, Tyler and Gyori, Benjamin M},
+               month = {feb},
+               title = {{ChemicalX: A Deep Learning Library for Drug Pair Scoring}},
+               url = {http://arxiv.org/abs/2202.05240},
+               year = {2022}
+     }
+
+
 Overview
 ========
 We shortly overview the fundamental concepts and features of **ChemicalX**
@@ -9,5 +28,38 @@ through simple examples. These are the following:
 .. contents::
     :local:
 
-Design philosophy
+Design Philosophy
 -----------------
+
+Drug Feature Set
+-----------------
+
+Context Feature Set
+--------------------
+
+
+Labeled Triples
+-----------------
+
+
+Drug Pair Batches
+-----------------
+
+
+Data Generators
+-----------------
+
+
+Model Layers
+-----------------
+
+
+
+Pipelines
+-----------------
+
+
+
+
+
+

docs/source/notes/tutorial.rst

@@ -0,0 +1,17 @@
+Tutorial
+========
+.. contents:: Contents
+    :local:
+
+Data Loading and Model Definition
+---------------------------------
+
+
+Model Training
+--------------
+
+
+Model Scoring
+-------------
+
+