Selected Publication


Compositional perturbation autoencoder for single-cell response modeling

Interpretable single-cell perturbation modeling using a compositional perturbation autoencoder (CPA)

We are thrilled to announce the recent publication of Mohammad Lotfollahi from Theis Lab in bioRxiv.  In this paper, the team presents the Compositional Perturbation Autoencoder (CPA), which combines the interpretability of linear models with the flexibility of deep-learning approaches for single-cell response modeling. CPA encodes and learns transcriptional drug response across different cell types, doses, and drug combinations.

Please click here to access the full publication.

Congratulations Mohammad!