some question about clustering about sc_mixology HOT 5 CLOSED

It depends on which benchmark dataset you used. These cell lines have distinct gene expression patterns, so the single cell data can be easily clustered. This is why we have the mixture dataset, where the difference between clusters are more subtle. Also keep in mind that these dataset provide a baseline for method evaluation, which means having good performance on these dataset does not guarantee the similar performance on other more complicated data. If you want to challege your clustering methods, you can look at scRNAseq data from cells in differenciation, such as hematopietic stem cells (https://www.nature.com/articles/s41467-019-10291-0) or iPSCs (https://doi.org/10.1016/j.cell.2019.01.006). The different between different cell type/state will be more subtle, but the annotation will not be as good as our controlled experiment, due to the limited knowledge of the biological systems.

from sc_mixology.

Hi, I am experimenting with your test data as well. (Nice paper by the way, very comprehensive comparisons). However, I am having difficulties finding out the "true label" for cellmix data.

I understand that for CellLine scRNAseq data you used "cell_line_demuxlet" as your true label, and for RNAmix data you used "mix" column to store the true label info, but for cellmix data there is no such group info in "colData".

It will be great if you can help me with this issue. A bunch of thanks in advance.

from sc_mixology.

Hi, I am experimenting with your test data as well. (Nice paper by the way, very comprehensive comparisons). However, I am having difficulties finding out the "true label" for cellmix data.

I understand that for CellLine scRNAseq data you used "cell_line_demuxlet" as your true label, and for RNAmix data you used "mix" column to store the true label info, but for cellmix data there is no such group info in "colData".

It will be great if you can help me with this issue. A bunch of thanks in advance.

Yes I agree it is not very clear. The true label are the combinations of cell numbers from three cell lines, so is the RNA mixtures. but in RNA mixtures it is the combinations of RNA proportions not cell numbers. I will update the documentation.

from sc_mixology.

Hi @LuyiTian I am curious about the true labels as well. Which file(s) contains the true cluster labels? Thanks in advance.

from sc_mixology.

@sgmccalla I have updated the document. please check recent commit bba1c35.

from sc_mixology.