Some questions about signac

[HelloWorldLTY]

Hi, I found that most of the datasets including atac information are very large, and it takes me very long time to run the step generating chr-gene relation. Therefore, could you please offer me some suggestions about this problem? Or is it possible to run your model without this relation as an input? Thanks a lot!

[PeterZZQ]

Hello, do you mean that the script calc_gact.R runs super slow? The script basically loops through all the regions in the count matrix and finds a gene for each region. The running time depends on the number of regions you have. You can filter some regions in advance before putting the regions into the script. It shouldn't cost more than an hour in most cases if you don't filter the genes.

The relationship is required in scDART. If you wish to train without the relationship, you can remove the corresponding loss in the model. I believe it should also work, but it would be a different framework.

[HelloWorldLTY]

Ok, thanks for your help. I will reconsider my filter threshold.