How to setup scRNA data for scPRINT using scDataLoader

[unikill066]

Hi @jkobject, I am trying a pilot run on the 3K PBMC dataset. Could you please point me to docs/material to set up the Data object with just scanpy and anndata, without loading it into lamin-db.

Dataset;

!mkdir -p data
!curl https://cf.10xgenomics.com/samples/cell-exp/1.1.0/pbmc3k/pbmc3k_filtered_gene_bc_matrices.tar.gz -o data/pbmc3k_filtered_gene_bc_matrices.tar.gz
!cd data; tar -xzf pbmc3k_filtered_gene_bc_matrices.tar.gz

[unikill066]

Here is the notebook for reference
https://utdallas.box.com/s/evprlsbkf3hdxo8a9qn1jvu39h2soplb

[jkobject]

Hello, if you follow the example notebooks or the google collab it should tell you how an anndata is managed. as long as your genes are ensembl ids it should be fine. load this as an anndata, add the obs['organism_ontology_id'] = 'NCBITaxon:9606' and you should be good to go to get it processed by the Preprocessor() class and use it as is

[jkobject]

I will close this since there is not reply