additional datasets about scvi-tools HOT 3 CLOSED

With regard to my dataset, the raw counts are indeed already accessible through the Dataset10X class:

I could theoretically simply run something like:

cd4_t_helper = Dataset10X("cd4_t_helper", dense=False, new_n_genes=None)
regulatory_t = Dataset10X("regulatory_t", dense=False, new_n_genes=None)
naive_t = Dataset10X("naive_t", dense=False, new_n_genes=None)
memory_t = Dataset10X("memory_t", dense=False, new_n_genes=None)
cytotoxic_t = Dataset10X("cytotoxic_t", dense=False, new_n_genes=None)
naive_cytotoxic = Dataset10X("naive_cytotoxic", dense=False, new_n_genes=None)

fresh_68k_pbmc_donor_a = Dataset10X("fresh_68k_pbmc_donor_a", dense=False, new_n_genes=None)

cite_seq_pbmc = CiteSeqDataset("pbmc")

t_cells = GeneExpressionDataset.concat_datasets(cd4_t_helper,regulatory_t,naive_t,memory_t,cytotoxic_t,naive_cytotoxic)
all_concatenated_pbmcs = GeneExpressionDataset.concat_datasets(t_cells, fresh_68k_pbmc_donor_a, cite_seq_pbmc, shared_batches=False)

However, initially I would work with the .rds data coming from this repo, as well as its preprocessing scripts, which gave me additional information:

• the gene_symbols without which I can't merge the datasets with citeSeq (10X Datasets only use the ENSEMBL version for the gene names, and I didn't find any mapping yet).

• the predicted labels from the original "Massively Parallel ..." paper, which one has to compute for himself (they don't give it in an output file).

from scvi-tools.

@imyiningliu @Edouard360 Are there additional datasets we plan to keep using, that aren't wrapped by scVI, beyond what Yining added in #97 ? If not, let's close this issue.

from scvi-tools.

Let me add scmap datasets, and I'll be good

from scvi-tools.