Tutorials

If you are interested in predicting the effect of a drug and its combinations, check the demo with all hyper-parameters for combo sci-plex dataset (Lotfollahi et al., 2023), check the following examples:

• Predicting combinatorial drug perturbations
• Data Loading
• Data setup
• Training CPA
• Model instantiation
• Training CPA
• Latent space UMAP visualization
• Evaluation
• Visualizing similarity between drug embeddings
• Predicting combinatorial drug perturbations using RDKit embeddings for drugs

If you are interested in predicting the effect of CRISPRi or CRISPRa perturbations (gene perturbations) and their combinations, check the demo with all hyper-parameters for (Norman et al., 2019 dataset), check:

• Predicting single-cell response to unseen combinatorial CRISPR perturbations

If you would like to perform context transfer (i.e. predict the effect of a perturbation (e.g. disease) on unseen cell types or transfer perturbation effects from one context to another) check this example for INF-B stimulated cells from (Kang et al., 2018), check:

• Predicting perturbation responses for unseen cell-types (context transfer)

If you would like to perform batch effect removal on gene expression space as well as latent space, check this example:

• Batch correction in expression space