Having trouble applying geneformer on my data
#544
by
tomererez
- opened
Hey guys, Having trouble applying geneformer on my data.
my goal is to extract meaningful embeddings from my dataset.
I am using the notebook: extract_and_plot_cell_embeddings, able to run it on your dataset but not mine.
my data is a csv of rna sequence gene expression levels by gene names.
so the csv columns are gene symbol names (ABCA10, ABCA11P, ABCA12... about 16k genes). each sample has the gene expression level of the gene from its rna sequence.
can you please explain to me how to convert the data to a format which allows later usage of geneformer?
Thanks for your question! Please see the example here for converting your data:
https://huggingface.co/ctheodoris/Geneformer/blob/main/examples/tokenizing_scRNAseq_data.ipynb
ctheodoris
changed discussion status to
closed