[DL Edition] T037: E(3)-invariant graph neural networks - Githubissues

volkamerlab / teachopencadd

TeachOpenCADD: a teaching platform for computer-aided drug design (CADD) using open source packages and data

https://projects.volkamerlab.org/teachopencadd

Creative Commons Attribution 4.0 International

757 stars 202 forks source link

[DL Edition] T037: E(3)-invariant graph neural networks #326

Closed joschka-gross closed 1 year ago

joschka-gross commented 1 year ago

Details

Talktorial ID: 037
Title: [DL Edition] T037: E(3)-invariant graph neural networks
Original authors: Joschka Groß
Reviewer(s): XXX
Date of review: DD-MM-YYYY

Content

One line summary: Introduction to E(3) In-/Equivariant Graph Neural Networks
Potential labels or categories (e.g. machine learning, small molecules, online APIs): Machine learning, small molecules, graph neural networks, point clouds, 3D information
Time it took to execute (approx.):
[x] I have used the talktorial template and followed the content and formatting suggestions there
[ ] Packages must be open-sourced and should be installable from conda-forge. If you are adding new packages to the TeachOpenCADD environment, please check if already installed packages can perform the same functionality and if not leave a sentence explaining why the new addition is needed. If the new package is not on conda-forge, please list them and their intended usage here.
- numpy, matplotlib: Already in TeachOpenCADD
- pytorch 1.12.1, pytorch-cluster 1.6.0, pytorch-scatter 2.1.0, pytorch-sparse 0.6.15, pyg 2.2.0 (conda-forge): pyg (torch_geometric) includes graph neural network and the QM9 dataset we use for the practical part, everzthing else is a dependency of torch_geometric, however we also use pytorch-scatter explicitly in our EGNN implementation
[x] Data must be publicly available, preferably accessible via a webserver or downloadable via a URL. Please list the data resources that you use and how to access them:
- QM9 dataset: Access via (torch-geometric)

Content style

[x] Talktorial includes cross-references to other talktorials if applicable
[x] The table of contents reflects the talktorial story-line; order of #, ##, ### headers is correct
[x] URLs are linked with meaningful words, instead of pasting the URL directly or linking words like here.
[x] I have spell-checked the notebook
[x] Images have enough resolution to be rendered with quality, without being too heavy.
[x] All figures have a description
[x] Markdown cell content is still in-line with code cell output (whenever results are discussed)
[x] I have checked that cell outputs are not incredibly long (this applies also to DataFrames) - is 100 lines okay?
[ ] Formatting looks correctly on the Sphinx render (bold, italics, figure placing)

Code style

[x] Variable and function names follow snake case rules (e.g. a_variable_name vs aVariableName)
[x] Spacing follows PEP8 (run Black on the code cells if needed)
[x] Code line are under 99 characters each (run black-nb -l 99)
[x] Comments are useful and well placed
[x] There are no unpythonic idioms like for i in range(len(list)) (see slides)
[x] All 3rd party dependencies are listed at the top of the notebook
[x] I have marked all code cell with output referenced in markdown cells with the label # NBVAL_CHECK_OUTPUT
[ ] I have identified potential candidates for a code refactor / useful functions
[x] All import ... lines are at the top (practice part) cell, ordered by standard library / 3rd party packages / our own (teachopencadd.*)
[x] I have used absolute paths instead of relative paths
```
HERE = Path(_dh[-1])
DATA = HERE / "data"
```

Website

We present our talktorials on our TeachOpenCADD website (https://projects.volkamerlab.org/teachopencadd/), so we have to check as well if the Jupyter notebook renders nicely there.

[ ] If this PR adds a new talktorial, please follow these steps:
- [ ] Add your talktorial to the complete list of talktorials here (at the end).
- [ ] Add your talktorial to one or multiple of the collections here. Or propose a new collection section in your PR.
- [ ] Add your talktorial's nblink file by running python generate_nblinks.py from within the directory teachopencadd/docs/talktorials.
- [ ] Please complile the website following the instructions here.
[ ] Check the rendering of the talktorial of this PR.
[ ] Is your talktorial listed in the talktorial list?
[ ] Is your talktorial listed in the talktorial collections?
- [ ] Add a picture for your talktorial in the collection view by following these instructions.

Status

[ ] Ready to go

review-notebook-app[bot] commented 1 year ago

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB