atarashansky

Thanks for catching this! Looks like a pandas update broke everything :'D Can you output the result of `pip list` and paste it here?

Just to confirm @xgrau and @mikepassal - you are encountering the same error when running through the tutorial notebook?

> I think I've found a workaround: removing (or commenting out) the `@njit(parallel=True)` line in the `_refine_corr_kernel` of the [`mapping.py`](https://github.com/atarashansky/SAMap/blob/main/samap/mapping.py#L1445) script avoids the use of no-python code (via `numba`), which...

Can you try installing from source with the [most recent commit](https://github.com/atarashansky/SAMap/commit/69261b39d6a0b571d2b7fa86be2ee7c3037bfd77)? I pinned the package dependencies and confirmed that it works in both linux and macbook m1. If this solves...

Alright, I'm going to have to try reproducing this error in a centOS instance... I'll keep you posted.

`keys` determines which set of labels to use to set the maximum neighborhood size for a particular cell. `neigh_keys` determines which set of labels to use to _determine_ the neighborhood...

Can you give me a sense of how large the cell type labels are? It would be great if you could show me the number of cells assigned to each...

I think SAMap can be robust to dataset size disparities, but I would encourage you to try downsampling and check if the results change. I would also encourage changing the...

Instead of using `keys` in `SAMAP(...)`, Can you try using `neigh_from_keys` in `SAMAP.run(...)`? You can pass it the same exact value as you're passing to `keys`. If you use `neigh_from_keys`,...

The mapping scores are a relative measure of the connectivity between cells across species. It's not really comparable to the connectivity strength of cells within species. As SAMap is a...