search

rsinghlab / SCOT

Gromov-Wasserstein based optimal transport for aligning single-cell multi-omics data
http://rsinghlab.github.io/SCOT
MIT License
66 stars 16 forks source link

Mismatch between number of cells and number of labels for Splatter simulations #16

Closed DylanMannKrzisnik closed 8 months ago

DylanMannKrzisnik commented 8 months ago

It seems there are only 4000 labels in splatter_labels.csv for 5000 cells in splatter_X.npy and splatter_Y.npy. I realize that I could recreate the simulations (splatter + random projections), but was hoping I could reuse your simulations. Thanks.

pinardemetci commented 8 months ago

Hi Dylan,

I re-uploaded the splatter_labels.csv file and double-checked that it has 5000 entries. Each row in the splatter_labels.csv correspond to the cell type of the cell on the same row of splatter_X.npy or splatter_y.npy. Just to roughly double-check they are correct, I reduce splatter_X.npy, and splatter_y.npy files to 2D via PCA and plot them with these labels, I get the following figures, which appear to be what we expect based on the figures in the publication. Let me know if you run into any issues.

splatter_y splatter_X
pinardemetci commented 8 months ago

closing this for now, if this doesn't fix the issue, feel free to re-open it or comment.