Can scvelo be applied on long-read scRNA?

[WeiCSong]

Hi, thanks for the great tool! I'm wondering if scvelo could accept third generation sequencing data as input, or is this possible in the near future? Long read sequencing would provide much more information on splicing, so theoretically it would be better for scvelo. It seems that currently there is no way to generate loom file from long read data, will this be applicable? Thanks for your help!