Harreman tutorials

[ori-kron-wis]

Formatting

• My tutorial has only one top-level (#) header

Reproducibility

• My tutorial works on Google Colab
• My tutorial sets scvi.settings.seed = 0 at the beginning of the notebook
• My tutorial has been run and includes outputs (e.g. plots, tables)

Other

• Counts and normalized data should co-exist in the datasets, see the API overview for an example
• For scRNA-seq data, normalization should be counts per median library size and then log1p transformed -- if not, a reason should be given

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[chatgpt-codex-connector]

💡 Codex Review

https://github.com/scverse/scvi-tutorials/blob/eafe52736d4a4a38ac837d3c6b827e2f116e7255/spatial/Visium_colon_Harreman_pipeline.ipynb#L1304
Load KEGG signatures from a portable path

This hard-codes a private /home/projects/... location for KEGG_metab_m.json; in the notebook execution workflows that were updated to include this tutorial, that path is not created and the JSON is not committed anywhere in the repo, so a fresh nbconvert --execute run will fail with FileNotFoundError before the enrichment section can run. Please fetch the signature data or store it under a repository-relative/cache path.

---

https://github.com/scverse/scvi-tutorials/blob/eafe52736d4a4a38ac837d3c6b827e2f116e7255/spatial/Visium_colon_Harreman_pipeline.ipynb#L93
Import plotnine before building ggplot figures

The notebook later constructs figures with ggplot, aes, geom_violin, theme_classic, etc., but the only plotnine import is commented out here. In a fresh kernel this reaches the plotting cell and raises NameError: name 'ggplot' is not defined (the committed output already records that failure), so the tutorial cannot execute end-to-end until the needed plotnine symbols are imported or the plots are rewritten.

---

https://github.com/scverse/scvi-tutorials/blob/eafe52736d4a4a38ac837d3c6b827e2f116e7255/spatial/DestVI_tutorial.ipynb#L113
Import destvi_utils before calling its helpers

This change comments out the only destvi_utils import, but the notebook still calls destvi_utils.automatic_proportion_threshold, explore_gamma_space, and DE helpers later. Installing the package in the earlier cell does not bind the module name in a fresh kernel, including the workflow nbconvert --execute path, so the first helper call will fail with NameError unless the import is restored.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".