This release introduces changes listed below:
Big changes to code:
- [x] Updates for compatibility with scvi-tools>=0.16.0
- [x] Deleting pymc3 code
- [x] Revised tutorial (including per cell type expression prediction
- [x] Amortised NN using AutoGuideMessenger and option to use hierarchical guide
Changes to defaults:
- [x] Changing our default `detection_alpha` because within-slide tech effects seem to be more prevalent than their absence (detection_alpha=20) and recommend to run both detection_alpha=20 and detection_alpha=200 in the tutorial.
Changes to docs
- [x] Template issue: bug (version, are you following scvi-tools tutorial)
- [x] Template issue: usage question (version, are you following scvi-tools tutorial, which technology was used to generate reference data / spatial data, how many cell types, how many batches, how many genes, how many spatial locations)
- [x] Update tutorial to match scvi-tools tutorial
- [x] Update tutorial according to this feedback https://github.com/BayraktarLab/cell2location/discussions/65#discussioncomment-1725332
- [x] Delete pymc3 tutorials from documentation website (reorder the rest to make it easier to understand that pymc3 should not be used)
- [x] Fix documentation website for various classes including user-facing `Cell2location` class (automodule->autoclass)
- [x] Update readme - shorten what's possible
- [x] Update readme - future work
- [x] Update readme - add link to Nat Biotech paper
- [x] Update acknowledgements
- [x] Update copyright date
- [x] Revise colab version of the notebook (less posterior samples)
- [x] Add this line to tutorial: "The values are stored in adata.uns[f"mod_coloc_n_fact{n_fact}"] in a similar output format main cell2location results."