Duplicated gene names in replogle_k562_essential

[zhan8855]

Hi, I have the following error,

pert_data = PertData('./data')
pert_data.load(data_name='replogle_k562_essential')
gene_name = pert_data.adata.var['gene_name'].tolist()

assert len(gene_name) == len(set(gene_name))
>>> AssertionError

[yhr91]

Yes, I believe there is one gene name that is repeated twice in this dataset. This doesn't impact the model because it mainly relies on gene indices during training and prediction.

[zhan8855]

But is it biologically sound?

[yhr91]

Yes, gene names are arbitrary constructs given to segments of the DNA. For example, often multiple ENSEMBL ids map to the same gene name

[zhan8855]

Thank you very much!!