search

jianhuupenn / SpaGCN

SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network
MIT License
199 stars 60 forks source link

Error running spaGCN : Could not construct partition #47

Closed archanabhardwaj closed 2 years ago

archanabhardwaj commented 2 years ago

Hello I am trying to run spatial 10X visium data in sgaGCN on spatial dataset but it gives me following error at processing step :

Search for suitable resolution

res=spg.search_res(adata, adj, l, n_clusters, start=0.7, step=0.1, tol=5e-3, lr=0.05, max_epochs=20, r_seed=r_seed, t_seed=t_seed, n_seed=n_seed) BaseException: Could not construct partition: vector::_M_default_append

Same code was working before on single and integrated datasets. But this time it gives me error for both integrated and single objects.

Please help me to fix this issue. I would appreciate all the suggestions. Thanks in advance

xiao-kong-long commented 2 years ago

I also meet this problem now.

xiao-kong-long commented 2 years ago

hello, you can try the solution closed issue #43

archanabhardwaj commented 2 years ago

It worked. Thanks alot !!