How to obtain more top_non_dropout_de?

snap-stanford / GEARS

GEARS is a geometric deep learning model that predicts outcomes of novel multi-gene perturbations

MIT License

189 stars 38 forks source link

Open yanwuanxin opened 5 months ago

yanwuanxin commented 5 months ago

adata.uns["top_non_dropout_de_20"] stored top20 differential gene, how to get more?

yanwuanxin commented 5 months ago

modifying script of data_utils.py to get more top_non_dropout_de, but the result of top20 and top50 are inconsistent.

modify the script as follows：

top20 result:

top50 result:

ceesu commented 2 days ago

There is an example notebook on their paper's GitHub.