the results of several runs are different in silico perturbation

[ergezhenshuai]

Hi, thanks for your previous help. I have used my own dataset to run several times, and its results are different from the picture. Do you have any better suggestions? `import warnings warnings.filterwarnings('ignore')

import dynamo as dyn import scanpy as sc dyn.dynamo_logger.main_silence()

adata = dyn.read_h5ad(r"E:\python\h5ad\a.h5ad") print(adata) dyn.pp.recipe_monocle(adata) dyn.tl.moments(adata, layers=['X_unspliced', 'X_spliced']) dyn.tl.dynamics(adata) dyn.tl.reduceDimension(adata) dyn.tl.cell_velocities(adata, basis='pca', transition_genes = adata.var.index[adata.var['use_for_dynamics']], enforce=True) dyn.vf.VectorField(adata, basis='pca', pot_curl_div=True, cores=8, M=1000) dyn.tl.cell_velocities(adata, basis='umap', transition_genes = adata.var.index[adata.var['use_for_dynamics']], enforce=True) dyn.vf.VectorField(adata, basis='umap', pot_curl_div=True, cores=8, M=1000) gene = "ACSL1" dyn.pd.perturbation(adata, gene, [-100], emb_basis="umap", basis='umap') dyn.pl.streamline_plot(adata, color=["leiden_1.2", gene], basis="umap_perturbation",save_show_or_return="show")

[github-actions[bot]]

This issue is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 14 days