Anndatas and corresponding drug and protein embeddings

Here are the anndatas (LINCS, Sciplex3, Norman, Replogle (RPE1 and K562, too big!)), their preprocessed versions (2,000 highly variable genes) and the drug and protein embeddings The Replogle datasets (K562_essential_raw_singlecell_01 and anndatas/rpe1_raw_singlecell_01 are each ~10Gb) can be downlaoded from https://plus.figshare.com/articles/dataset/_Mapping_information-rich_genotype-phenotype_landscapes_with_genome-scale_Perturb-seq_Replogle_et_al_2022_processed_Perturb-seq_datasets/20029387