Chris Kang

Looks like it's python's multiprocess problem, in the next version I will make a workaround

Hi Julien, could you update to 0.1.9.3 and check if the error occurs? Thank you!

Doesn't look right, could you add `mnnpy.settings.normalization='seq'` in the front (to circumvent python multiprocessing) and use the old code?

- `Sample1.h5ad` is a data file made from single-cell sequencing data using scanpy; - `load_from_file("Some HVGs.csv")` represents the general process of getting a list of HVGs. in my workflow I...

Glad you guys could work it out. I was actually developing from my mac but didn't encounter the issue. I may have installed all those deps without knowing...

log counts, regressed is better. The output should only be used for PCA/Cluster/TSNE, don't use it to do DE.

No problem, as long as the data is in log space > On Jun 26, 2018, at 15:43, wangjiawen2013 wrote: > > Excuse me, > Can I use log(CPM) instead...

No problem, as long as the data is in log space > On Jun 26, 2018, at 15:43, wangjiawen2013 wrote: > > Excuse me, > Can I use log(CPM) instead...

有可能参数不一样，https://github.com/chriscainx/mnnpy/issues/11，SCRAN改了一些参数

你复制一下网址再打开 > On Jun 26, 2018, at 15:33, wangjiawen2013 wrote: > > I have tried some different parameters and keep them the same, indeed the results are different, but the...