volkamerlab · dominiquesydow · Sep 9, 2021 · Dec 15, 2020 · Dec 15, 2020 · Dec 15, 2020
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -72,7 +72,11 @@ jobs:
         shell: bash -l {0}
         run: |
           PYTEST_ARGS="--nbval-lax --current-env --dist loadscope --numprocesses 2"
-          pytest $PYTEST_ARGS teachopencadd/talktorials/T*/talktorial.ipynb
+          if [ "$RUNNER_OS" != "Windows" ]; then
+            pytest $PYTEST_ARGS teachopencadd/talktorials/T*/talktorial.ipynb
+          else
+            pytest $PYTEST_ARGS teachopencadd/talktorials/ --ignore-glob=teachopencadd/talktorials/T019*
+          fi
 
   format:
     name: Black

diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -66,7 +66,14 @@ jobs:
             --exclude "*.txt" \
             --exclude "https://onlinelibrary.wiley.com/doi/full/10.1002/cmdc.200700139" \
             --exclude "https://onlinelibrary.wiley.com/doi/10.1002/9783527806539.*" \
-            --exclude "http://doi.org/10.6019/CHEMBL.database.27"
+            --exclude "https://towardsdatascience.com" \
+            --exclude "https://medium.com" \
+            --exclude "https://*.medium.com" \
+            --exclude "http[s]://quora.com" \
+            --exclude "http[s]://doi.org" \
+            --exclude "ftp://*" \
+            --exclude "http://localhost:8000"
+
 
       - name: Check 404s (README)
         uses: gaurav-nelson/github-action-markdown-link-check@v1

diff --git a/.gitignore b/.gitignore
@@ -144,3 +144,10 @@ cython_debug/
 
 # MACOS
 .DS_Store/
+
+# temporary data notebooks will download
+_tmp/
+
+# npm
+yarn.lock
+node_modules/
diff --git a/README.md b/README.md
@@ -1,19 +1,26 @@
 # TeachOpenCADD
+A teaching platform for computer-aided drug design (CADD) using open source packages and data.
 
 [![DOI](https://img.shields.io/badge/DOI-10.1186%2Fs13321--019--0351--x-blue.svg)](https://doi.org/10.1186/s13321-019-0351-x)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.2600909.svg)](https://doi.org/10.5281/zenodo.2600909)
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/volkamerlab/TeachOpenCADD/master)
+
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
+![GitHub tag (latest by date)](https://img.shields.io/github/v/tag/volkamerlab/teachopencadd)
 [![GH Actions CI ](https://github.com/volkamerlab/teachopencadd/workflows/CI/badge.svg)](https://github.com/volkamerlab/teachopencadd/actions?query=branch%3Amaster+workflow%3ACI)
 [![GH Actions Docs](https://github.com/volkamerlab/teachopencadd/workflows/Docs/badge.svg)](https://projects.volkamerlab.org/teachopencadd/)
 
-> 🌟 You are looking at a new release of the TeachOpenCADD repository with [major changes](https://github.com/volkamerlab/teachopencadd/pull/29).
+![GitHub closed pr](https://img.shields.io/github/issues-pr-closed-raw/volkamerlab/teachopencadd) ![GitHub open pr](https://img.shields.io/github/issues-pr-raw/volkamerlab/teachopencadd) ![GitHub closed issues](https://img.shields.io/github/issues-closed-raw/volkamerlab/teachopencadd) ![GitHub open issues](https://img.shields.io/github/issues/volkamerlab/teachopencadd)  
+![TOC](https://img.shields.io/badge/Project-TeachOpenCADD-pink)
+
+
+> 🌟 You are looking at a new release of the TeachOpenCADD repository with [major changes](https://github.com/volkamerlab/teachopencadd/pull/29) and a lot of [new talktorials](https://github.com/volkamerlab/teachopencadd/pull/74).
 >
 > - We applied a new folder structure to the repository allowing us to offer for the first time a `teachopencadd` conda package! You can find all talktorials under `teachopencadd/talktorials`. Each directory contains a `talktorial.ipynb` notebook ready to be run!
-> - We refactored all published notebooks (T001-T010) to apply best practices to our code!
+> - We refactored all published talktorials (T001-T010) to apply best practices to our code!
+> - We doubled the amount of TeachOpenCADD talktorials, extending our collection by topics from structure-based drug design, database queries, 3D visualization, and deep learning.
 > - We proudly present our brand new [TeachOpenCADD website](https://projects.volkamerlab.org/teachopencadd/)!
->
-> We are adding new notebooks to the repository soon -
-> subscribe to the repository releases (top-right menu: `Watch` > `Releases`) to stay tuned!
+
 >
 > If you would like to continue working with the old repository structure, please refer to release [`1.3.0`](https://github.com/volkamerlab/teachopencadd/tree/v1.3.0). Downloadable [here](https://github.com/volkamerlab/teachopencadd/releases/tag/v1.3.0).
 
@@ -63,11 +70,11 @@ If you prefer to work in the context of a graphical interface, talktorials T001-
 
 ### Python programming introduction
 
-The TeachOpenCADD platform is not a Python programming course from scratch but teaches how to solve tasks in cheminformatics and structural bioinformatics programmatically. 
+The TeachOpenCADD platform is not a Python programming course from scratch but teaches how to solve tasks in cheminformatics and structural bioinformatics programmatically.
 If you wish to get started first with a Python programming introduction before diving into the TeachOpenCADD material, here are a few great resources to do so:
 
-- [AI in Medicine course](https://github.com/volkamerlab/ai_in_medicine) by the [Volkamer Lab](https://volkamerlab.org/) and [Ritter Lab](https://psychiatrie-psychotherapie.charite.de/en/research/neuroimaging_and_neurotechnology/machine_learning/) at the Charité: Introduction to Python basics, Jupyter Notebook, and important data science packages such as Pandas, Matplotlib and Scikit-learn
-- [Python for Chemists course](https://github.com/GDChCICTeam/python-for-chemists) by the [GDCh/CIC](https://en.gdch.de/main-navi/network-structures/divisions/computers-in-chemistry.html) team: Crash-course introduction to Python for natural scientists
+- [AI in Medicine course](https://github.com/volkamerlab/ai_in_medicine) by the [Volkamer Lab](https://volkamerlab.org/) and [Ritter Lab](https://psychiatrie-psychotherapie.charite.de/metas/person/person/address_detail/ritter-7/) at the Charité: Introduction to Python basics, Jupyter Notebook, and important data science packages such as Pandas, Matplotlib and Scikit-learn
+- [Python for Chemists course](https://github.com/GDChCICTeam/python-for-chemists) by the [GDCh/CIC](https://en.gdch.de/network-structures/divisions/computers-in-chemistry-cic.html) team: Crash-course introduction to Python for natural scientists
 - [MolSSI Education Resources](http://education.molssi.org/resources.html) by [The Molecular Sciences Software Institute](https://molssi.org/): Collection of tutorials on Python programming basics and data analysis but also more advanced material on software development and computational molecular science
 - [Core lessons](https://software-carpentry.org/lessons/) by the [Software Carpentry](https://software-carpentry.org/): Introduction to Python, Git, command line interfaces and more
 
@@ -141,20 +148,39 @@ It will help measure the impact of the TeachOpenCADD platform and future funding
   [`mdanalysis`](https://www.mdanalysis.org/),
   [`biopython`](https://biopython.org/),
   [`biopandas`](http://rasbt.github.io/biopandas/),
-  [`opencadd`](https://opencadd.readthedocs.io/en/latest/)
+  [`opencadd`](https://opencadd.readthedocs.io/en/latest/),
+  [`plip`](https://github.com/pharmai/plip),
+  [`openff`](https://github.com/openforcefield/openff-toolkit),
+  [`openff-toolkit`](https://github.com/openforcefield/openff-toolkit),
+  [`openmmforcefields`](https://github.com/openmm/openmmforcefields),
+  [`pdbfixer`](https://github.com/openmm/pdbfixer),
+  [`mdanalysis`](https://www.mdanalysis.org/),
+  [`biotite`](https://www.biotite-python.org/)
 - Data science (PyData stack):
   [`numpy`](https://numpy.org/),
   [`pandas`](https://pandas.pydata.org/),
   [`scikit-learn`](https://scikit-learn.org/),
+  [`tensorflow`](https://www.tensorflow.org/),
   [`jupyter`](https://jupyter.org/),
   [`ipywidgets`](https://ipywidgets.readthedocs.io)
 - Data visualization:
   [`matplotlib`](https://matplotlib.org/), 
+  [`mpl_toolkits`](https://matplotlib.org/stable/api/toolkits/index.html),
+  [`matplotlib_venn`](https://github.com/konstantint/matplotlib-venn),
   [`seaborn`](https://seaborn.pydata.org/),
   [`nglview`](http://nglviewer.org/nglview/latest/)
 - Web services clients:
   [`pypdb`](https://github.com/williamgilpin/pypdb),
-  [`chembl_webresource_client`](https://github.com/chembl/chembl_webresource_client)
+  [`chembl_webresource_client`](https://github.com/chembl/chembl_webresource_client),
+  [`requests`](https://docs.python-requests.org/en/master/),
+  [`bravado`](https://bravado.readthedocs.io/en/stable/),
+  [`beautifulsoup4`](https://www.crummy.com/software/BeautifulSoup/bs4/doc/)
+- Utilities:
+  [`tqdm`](https://tqdm.github.io/),
+  [`requests_cache`](https://requests-cache.readthedocs.io),
+  [`redo`](https://github.com/mozilla-releng/redo),
+  [`google-colab`](https://pypi.org/project/google-colab/),
+  [`condacolab`](https://pypi.org/project/condacolab/)
 - Continuous integration:
   [`pytest`](https://docs.pytest.org),
   [`nbval`](https://nbval.readthedocs.io)

diff --git a/devtools/conda-recipe/meta.yaml b/devtools/conda-recipe/meta.yaml
@@ -43,8 +43,9 @@ requirements:
     - redo
     - requests-cache
     - suds-community
+    - smina
     # note there are some pip dependencies not available in conda yet!
-    # check /environment.yml for details
+    # check devtools/conda_envs/test_env.yml for details
 
 test:
   requires:

diff --git a/devtools/other-conda-envs/users_env.yml b/devtools/other-conda-envs/users_env.yml
@@ -23,12 +23,20 @@ dependencies:
   - ipywidgets>=7.5
   - nglview>=3
   - biotite
-  - mdanalysis
+  - mdanalysis>=1.0.0
   - plip
   - biopython<=1.77
+  - mdtraj
+  - openmm
+  # depends on openff-toolkit->ambertools -> not available on Windows yet!
+  # - openmmforcefields
+  - pdbfixer
   - redo
   - requests-cache
   - suds-community
+  - tensorflow>=2.0
+  - smina
+  - matplotlib-venn
   ## CI tests
   # Workaround for https://github.com/computationalmodelling/nbval/issues/153
   - pytest 5.*
@@ -48,6 +56,6 @@ dependencies:
       - black-nb
       - nbsphinx-link
       - https://github.com/jaimergp/autodocktools-prepare-py3k/archive/master.zip
-      - https://github.com/volkamerlab/opencadd/archive/b6d9c511f89ff200c45532e614f1abffa35e2ab7.zip
+      - https://github.com/volkamerlab/opencadd/archive/c860671ae88eb84afdd6ef599a4ecea9587c123c.zip
       # the package itself (teachopencadd)
       - https://github.com/volkamerlab/teachopencadd/archive/master.tar.gz
diff --git a/devtools/test_env.yml b/devtools/test_env.yml
@@ -23,12 +23,20 @@ dependencies:
   - ipywidgets>=7.5
   - nglview>=3
   - biotite
-  - mdanalysis
+  - mdanalysis>=1.0.0
   - plip
   - biopython<=1.77
+  - mdtraj
+  - openmm
+  # depends on openff-toolkit->ambertools -> not available on Windows yet!
+  # - openmmforcefields
+  - pdbfixer
   - redo
   - requests-cache
   - suds-community
+  - tensorflow>=2.0
+  - smina
+  - matplotlib-venn
   ## CI tests
   # Workaround for https://github.com/computationalmodelling/nbval/issues/153
   - pytest 5.*
@@ -48,6 +56,6 @@ dependencies:
       - black-nb
       - nbsphinx-link
       - https://github.com/jaimergp/autodocktools-prepare-py3k/archive/master.zip
-      - https://github.com/volkamerlab/opencadd/archive/b6d9c511f89ff200c45532e614f1abffa35e2ab7.zip
+      - https://github.com/volkamerlab/opencadd/archive/c860671ae88eb84afdd6ef599a4ecea9587c123c.zip
       # TeachOpenCADD itself
-      - ../
+      - ../
diff --git a/docs/_static/images/TeachOpenCADD_topics.svg b/docs/_static/images/TeachOpenCADD_topics.svg
diff --git a/docs/all_talktorials.rst b/docs/all_talktorials.rst
@@ -16,3 +16,14 @@ This is the complete list of talktorials available for online reading. Take into
    talktorials/T008_query_pdb.nblink
    talktorials/T009_compound_ensemble_pharmacophores.nblink
    talktorials/T010_binding_site_comparison.nblink
+   talktorials/T011_query_online_api_webservices.nblink
+   talktorials/T012_query_klifs.nblink
+   talktorials/T013_query_pubchem.nblink
+   talktorials/T014_binding_site_detection.nblink
+   talktorials/T015_protein_ligand_docking.nblink
+   talktorials/T016_protein_ligand_interactions.nblink
+   talktorials/T017_advanced_nglview_usage.nblink
+   talktorials/T019_md_simulation.nblink
+   talktorials/T020_md_analysis.nblink
+   talktorials/T021_one_hot_encoding.nblink
+   talktorials/T022_ligand_based_screening_neural_network.nblink
diff --git a/docs/external_resources.rst b/docs/external_resources.rst
@@ -4,8 +4,8 @@ Python programming introduction
 The TeachOpenCADD platform is not a Python programming course from scratch but teaches how to solve tasks in cheminformatics and structural bioinformatics programmatically.
 If you wish to get started first with a Python programming introduction before diving into the TeachOpenCADD material, here are a few great resources to do so:
 
-- `AI in Medicine course <https://github.com/volkamerlab/ai_in_medicine>`_ by the `Volkamer Lab <https://volkamerlab.org/>`_ and `Ritter Lab <https://psychiatrie-psychotherapie.charite.de/en/research/neuroimaging_and_neurotechnology/machine_learning/>`_ at the Charité: Introduction to Python basics, Jupyter Notebook, and important data science packages such as Pandas, Matplotlib and Scikit-learn
-- `Python for Chemists course <https://github.com/GDChCICTeam/python-for-chemists>`_ by the `GDCh/CIC <https://en.gdch.de/main-navi/network-structures/divisions/computers-in-chemistry.html>`_ team: Crash-course introduction to Python for natural scientists
+- `AI in Medicine course <https://github.com/volkamerlab/ai_in_medicine>`_ by the `Volkamer Lab <https://volkamerlab.org/>`_ and `Ritter Lab <https://psychiatrie-psychotherapie.charite.de/metas/person/person/address_detail/ritter-7/>`_ at the Charité: Introduction to Python basics, Jupyter Notebook, and important data science packages such as Pandas, Matplotlib and Scikit-learn
+- `Python for Chemists course <https://github.com/GDChCICTeam/python-for-chemists>`_ by the `GDCh/CIC <https://en.gdch.de/network-structures/divisions/computers-in-chemistry-cic.html>`_ team: Crash-course introduction to Python for natural scientists
 - `MolSSI Education Resources <http://education.molssi.org/resources.html>`_ by `The Molecular Sciences Software Institute <https://molssi.org/>`_: Collection of tutorials on Python programming basics and data analysis but also more advanced material on software development and computational molecular science
 - `Core lessons <https://software-carpentry.org/lessons/>`_ by the `Software Carpentry <https://software-carpentry.org/>`_: Introduction to Python, Git, command line interfaces and more
 - `Best practices for Python, Git and Jupyter <https://zenodo.org/record/4630714>`_, a slide deck used in the introduction of our CADD Block course 2021, part of the Master's degree in Bioinformatics curriculum at the Freie Universität (FU) Berlin.

diff --git a/docs/talktorials.rst b/docs/talktorials.rst
@@ -36,6 +36,10 @@ Ligand-based cheminformatics
    talktorials/T005_compound_clustering.nblink
    talktorials/T006_compound_maximum_common_substructures.nblink
    talktorials/T007_compound_activity_machine_learning.nblink
+   talktorials/T012_query_klifs.nblink
+   talktorials/T013_query_pubchem.nblink
+   talktorials/T021_one_hot_encoding.nblink
+   talktorials/T022_ligand_based_screening_neural_network.nblink
 
 Structural biology
 ------------------
@@ -46,4 +50,26 @@ Structural biology
 
    talktorials/T008_query_pdb.nblink
    talktorials/T009_compound_ensemble_pharmacophores.nblink
-   talktorials/T010_binding_site_comparison.nblink
+   talktorials/T010_binding_site_comparison.nblink
+   talktorials/T012_query_klifs.nblink
+   talktorials/T014_binding_site_detection.nblink
+   talktorials/T015_protein_ligand_docking.nblink
+   talktorials/T016_protein_ligand_interactions.nblink
+   talktorials/T017_advanced_nglview_usage.nblink
+   talktorials/T019_md_simulation.nblink
+   talktorials/T020_md_analysis.nblink
+
+
+Online APIs/servers
+-------------------
+
+.. nbgallery::
+   :name: onlineapi
+   :caption: Online API/servers for structural bioinformatics and cheminformatics
+
+   talktorials/T001_query_chembl.nblink
+   talktorials/T008_query_pdb.nblink
+   talktorials/T011_query_online_api_webservices.nblink
+   talktorials/T012_query_klifs.nblink
+   talktorials/T013_query_pubchem.nblink
+
diff --git a/docs/talktorials/T011_query_online_api_webservices.nblink b/docs/talktorials/T011_query_online_api_webservices.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T011_query_online_api_webservices/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T011_query_online_api_webservices/images"]}
diff --git a/docs/talktorials/T012_query_klifs.nblink b/docs/talktorials/T012_query_klifs.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T012_query_klifs/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T012_query_klifs/images"]}
diff --git a/docs/talktorials/T013_query_pubchem.nblink b/docs/talktorials/T013_query_pubchem.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T013_query_pubchem/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T013_query_pubchem/images"]}
diff --git a/docs/talktorials/T014_binding_site_detection.nblink b/docs/talktorials/T014_binding_site_detection.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T014_binding_site_detection/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T014_binding_site_detection/images"]}
diff --git a/docs/talktorials/T015_protein_ligand_docking.nblink b/docs/talktorials/T015_protein_ligand_docking.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T015_protein_ligand_docking/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T015_protein_ligand_docking/images"]}
diff --git a/docs/talktorials/T016_protein_ligand_interactions.nblink b/docs/talktorials/T016_protein_ligand_interactions.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T016_protein_ligand_interactions/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T016_protein_ligand_interactions/images"]}
diff --git a/docs/talktorials/T017_advanced_nglview_usage.nblink b/docs/talktorials/T017_advanced_nglview_usage.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T017_advanced_nglview_usage/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T017_advanced_nglview_usage/images"]}
diff --git a/docs/talktorials/T019_md_simulation.nblink b/docs/talktorials/T019_md_simulation.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T019_md_simulation/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T019_md_simulation/images"]}
diff --git a/docs/talktorials/T020_md_analysis.nblink b/docs/talktorials/T020_md_analysis.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T020_md_analysis/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T020_md_analysis/images"]}
diff --git a/docs/talktorials/T021_one_hot_encoding.nblink b/docs/talktorials/T021_one_hot_encoding.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T021_one_hot_encoding/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T021_one_hot_encoding/images"]}
diff --git a/docs/talktorials/T022_ligand_based_screening_neural_network.nblink b/docs/talktorials/T022_ligand_based_screening_neural_network.nblink
@@ -0,0 +1 @@
+{"path": "../../teachopencadd/talktorials/T022_ligand_based_screening_neural_network/talktorial.ipynb", "extra-media": ["../../teachopencadd/talktorials/T022_ligand_based_screening_neural_network/images"]}