Open wangjiawen2013 opened 4 years ago
Hi @wangjiawen2013, thanks for the issue! I just resolved this, the fix is on diffxpy and batchglm dev branches so please install them from source via pip install -e .
.
And, how to integrate diffxpy with scanpy anndata object ? especially for the data (raw counts, normalized data or scaled data)
You can give adata
or adata.raw
to the data argument of diffxpy tests. If you use negative binomial noise models, you should use raw counts. Does that answer your question?
My adata stores scaled data, and adata.raw stores raw counts, could you give me an example on how to test it using negative binomial noise models ? adata.raw only contains the raw counts matrix, while the condition/batch are in adata object.
My adata stores scaled data, and adata.raw stores raw counts, could you give me an example on how to test it using negative binomial noise models ? adata.raw only contains the raw counts matrix, while the condition/batch are in adata object.
sure:
de.test.wald(
data=adata.raw,
sample_description=adata.obs,
gene_names=adata.raw.var_names,
formula_loc=...,
fac_loc_totest=...,
...
)
I will make access of raw objects easier, I will comment in this issue again once it s done! Thanks for the feedback @wangjiawen2013!
Dear, This chunk of code: sim = Simulator(num_observations=200, num_features=100) sim.generate_sample_description(num_batches=0, num_conditions=4) sim.generate_params(rand_fn_loc=lambda shape: np.random.uniform(-0.1, 0.1, shape),rand_fn_scale=lambda shape: np.random.uniform(0.1, 2, shape)) sim.generate_data() showed the error: 'Simulator' object has no attribute 'np_clip_param' what caused the problem ?
And, how to integrate diffxpy with scanpy anndata object ? especially for the data (raw counts, normalized data or scaled data)