Notebook to explore using normal cell references to annotate tumor cell states in Ewing sarcoma samples

### If you are filing this issue based on a specific GitHub Discussion, please link to the relevant Discussion.

#696

### Describe the goals of the changes to the analysis module.

We should explore using a normal cell reference to annotate tumor cell clusters in the Ewing samples. In particular, Ewing sarcoma cells are hypothesized to originate from either mesenchymal stem cells (MSC) or neural crest cells. There is also literature showing that Ewing cells show varying levels of an MSC-like signature. It could be helpful to use a reference atlas that contains MSC cells and the MSC lineage and see where tumor cells match up.

### What will your pull request contain?

The goal is to create a notebook that looks at using label transfer to annotate tumor cell clusters in 1-2 samples from SCPCP000015. Part of this notebook will include identifying a reference that may be useful in doing this. From #696, here are some possible references we might be able to use:

- [MSCscDB](http://mscsdb.jflab.ac.cn:18088/index/)
- [Single-cell transcriptome atlas of human mesenchymal stem cells exploring cellular heterogeneity](https://onlinelibrary.wiley.com/doi/10.1002/ctm2.650)
- [Fetal organ atlas](https://www.science.org/doi/10.1126/science.aba7721)
- [A human embryonic limb cell atlas resolved in space and time](https://www.nature.com/articles/s41586-023-06806-x)
- [Single‐cell study of neural stem cells derived from human iPSCs reveals distinct progenitor populations with neurogenic and gliogenic potential](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6916357/)

I think we will want to do this in 2 steps. The first PR will perform any prep on the reference and write some code to actually do the label transfer. The second PR will contain the notebook to evaluate the results.

### Will you require additional software beyond what is already in the analysis module?

Probably. I think we may want to use Azimuth for the label transfer. Alternatively, we could use scANVI since we already have a conda environment set up.

### Will you require different computational resources beyond what the analysis module already uses?

TBD

### If known, when do you expect to file the pull request?

January 2025

Start by reviewing the analysis module and Discussion #696, then compare the listed reference atlases for 1-2 SCPCP000015 samples. Investigate whether Azimuth or scANVI is suitable, prepare the reference and label-transfer code in the first PR, and use a follow-up notebook to evaluate the annotations.

Written by the indexing model from the issue text.