How are the onehot files generated?

[YOU-k]

Thanks for the nice work! we find this interesting. But when trying to follow the models, we find that:

There is one file loaded as data_gi_onehot_all. The dimension of it is cell x genes. I am not sure how is this matrix generated? Does the 1 means that specific gene is perturbed in a cell?

For the other file loaded as data_gi_onehot. The dimension of it is number of perturbed genes x number of all genes. Same, I find that when there are only 2 genes perturbed, there could be more than two 1 in that row, which indicates that this is not a matrix that tells the relationship between perturbed genes and all the genes used. So, how should I generate this matrix?
Cheers,
Yue

[cyclopenta]

Hi Yue, the new version of PerturbNet has been published on PyPI. You can check the tutorial notebooks to help solve your problems. The necessary data has been uploaded to Hugging Face.