Colab with cytopus - #7
Merged
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
This PR updates the project’s user-facing onboarding materials by adding a new Google Colab notebook demonstrating pretrained Compocyte usage (including Cytopus-based hierarchy queries) and by refreshing the README’s Colab tutorial links.
Changes:
- Adds a new Colab notebook:
02_pretrained_classifiers.ipynb(Compocyte + Cytopus hierarchical workflow). - Updates README to include a citation link and replaces old Colab “Drive” links with GitHub-backed Colab badge links.
Reviewed changes
Copilot reviewed 2 out of 5 changed files in this pull request and generated 4 comments.
| File | Description |
|---|---|
| README.md | Adds a preprint citation callout and updates Colab tutorial links to GitHub-hosted notebooks. |
| colab_tutorials/02_pretrained_classifiers.ipynb | Introduces a new interactive tutorial notebook for pretrained classifiers + Cytopus hierarchy querying. |
Comments suppressed due to low confidence (2)
colab_tutorials/02_pretrained_classifiers.ipynb:61
- Installing dependencies directly from GitHub without pinning a tag/commit makes the tutorial non-reproducible (and increases supply-chain risk if upstream changes). Prefer a released version (PyPI/conda) or pin to a specific tag/commit SHA.
"!pip install --quiet git+https://github.com/WALL-E-Lab/Compocyte.git"
colab_tutorials/02_pretrained_classifiers.ipynb:71
- Same reproducibility concern here:
cytopusis installed from GitHub without a pinned tag/commit. Pinning to a known-good ref keeps the tutorial stable over time.
"!pip install --quiet git+https://github.com/wallet-maker/cytopus.git"
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+59
to
+61
| Learn how to label your data using pretrained models [](https://colab.research.google.com/github/WALL-E-Lab/Compocyte/blob/colab_with_cytopus/colab_tutorials/02_pretrained_classifiers.ipynb) | ||
|
|
||
| Learn how to train a Compocyte classifier [](https://colab.research.google.com/github/WALL-E-Lab/Compocyte/blob/colab_with_cytopus/colab_tutorials/01_training_PBMC_classifier.ipynb) |
Comment on lines
+32
to
+36
| "source": [ | ||
| "#Cytopus dependencies\n", | ||
| "!apt install libgraphviz-dev\n", | ||
| "!pip install pygraphviz" | ||
| ] |
Comment on lines
+614
to
+625
| { | ||
| "cell_type": "markdown", | ||
| "id": "4abe410a", | ||
| "metadata": {}, | ||
| "source": [ | ||
| "'''\n", | ||
| "alternatively you can also retrieve the most granular annotations from the hierachy \n", | ||
| "starting on top of the hierarchy we can find the most granular label for each cell. Here, we start from the root node 'all-cells' so that all cells will be annotated.\n", | ||
| "'''\n", | ||
| "H.query_ancestors(query_node='all-cells', adata=hc.adata, obs_key='hierarchical_query')" | ||
| ] | ||
| }, |
Comment on lines
+49
to
+53
| "outputs": [ | ||
| { | ||
| "name": "stdout", | ||
| "output_type": "stream", | ||
| "text": [ |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Updated interactive tutorial to include hierarchical queries