search

theislab / cpa

The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.
BSD 3-Clause "New" or "Revised" License
83 stars 17 forks source link

Maintenance: Fixing bugs, typos, version conflicts, etc. #26

Closed ArianAmani closed 1 year ago

ArianAmani commented 1 year ago

  1. combosciplex.ipynb changes:

    • Version conflicts fixed for Colab (now works smoothly in Colab)
    • Data Loading fixed (The previous code didn't work properly)

  2. Installation docs Updated to contain the correct version of prerequisites to install and also added a code block for installing in Colab (fixes #20).

  3. combosciplex_Rdkit_embeddings.ipynb changes:

    • Version conflicts fixed for Colab (now works smoothly in Colab)
    • Data Loading fixed (The previous code didn't work properly)

  4. Kang.ipynb changes:

    • Version conflicts fixed for Colab (now works smoothly in Colab)
    • Data Loading fixed (The previous code didn't work properly)

  5. _model.py changes:

    • Code was using smiles_key although it is optional, fixed to if smiles_key is not None:

  6. Norman.ipynb changes:

    • Version conflicts fixed for Colab (now works smoothly in Colab)
    • Data Loading fixed (The previous code didn't work properly)
    • obs keys changed to match the linked dataset
    • pathway needs to be added to the linked dataset. Currently unavailable.

  7. pyproject.toml changes:

    • Resolved some of the version conflicts.
    • scanpy is not getting installed using pip install cpa-tools. Needs to be resolved.
review-notebook-app[bot] commented 1 year ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB