Alex Velez-Arce

Oracles not satisfying public benchmarks

1

Hi @amva13 , thanks for the fix! Checking with the other oracles in that specific version, something seems to break in `deco hop`. In the first example of the documentation...

Got it. Thanks for pointing out. The best solution is to pickle these solutions with a more modern scikit (or invoke the models with a different method entirely to avoid...

scperturb issue

1

For the perturb-seq dataset, there might be some problem: from tdc.multi_pred.perturboutcome import PerturbOutcome data = PerturbOutcome(name = 'scperturb_drug_SrivatsanTrapnell2020_sciplex2') split = data.get_split() # this line has a problem print_sys("processing cell line",...

**Describe the problem** Though self.adata exists, there is no obvious getter method. also, the splits don't provide an anndata option **Describe the solution you'd like** getter method(s); also implement splits...

Chat: """ Like for example ___ can’t combine the scperturb drug datasets due to batch effects but we could if we had label projection because we’d agree on the control,...

https://github.com/kjappelbaum/awesome-chemistry-datasets

https://github.com/dsi-bdi/biokg/tree/master https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10760044/

https://github.com/mims-harvard/TDC/tree/geneformer_server

Explore embeddings storage perteval <> tdc

1

@cmvcordova