Learning interpretable cellular responses to complex perturbations in high-throughput screens
Mohammad Lotfollahi, Anna Klimovskaia, Carlo De Donno et al. · bioRxiv (Cold Spring Harbor Laboratory) · 2021
Abstract Recent advances in multiplexed single-cell transcriptomics experiments are facilitating the high-throughput study of drug and genetic perturbations. However, an exhaustive exploration of the combinatorial perturbation space is experimentally unfeasible, so computational methods are needed to predict, interpret, and prioritize perturbations. Here, we present 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 responses across different cell type, dose, and drug combinations. The model produces easy-to-interpret embeddings for drugs and cell types, which enables drug similarity analysis and predictions for unseen dosage and drug combinations. We show that CPA accurately models single-cell perturbations across compounds, doses, species, and time. We further demonstrate that CPA predicts combinatorial genetic interactions of several types, implying that it captures features that distinguish different interaction programs. Finally, we demonstrate that CPA can generate in-silico 5,329 missing genetic combination perturbations (97.6% of all possibilities) with diverse genetic interactions. We envision our model will facilitate efficient experimental design and hypothesis generation by enabling in-silico response prediction at the single-cell level, and thus accelerate therapeutic applications using single-cell technologies.
Cited by 48 works. doi:10.1101/2021.04.14.439903 Open-access PDF
Authors
- Mohammad Lotfollahi
- Anna Klimovskaia
- Carlo De Donno
- Yuge Ji
- Ignacio L. Ibarra
- F. Alexander Wolf
- Nafissa Yakubova
- Fabian Joachim Theis
- David López-Paz
References
- Visualizing Data using t-SNE
- Distributed Representations of Words and Phrases and their Compositionality
- Advances in neural information processing systems 7
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- UMAP: Uniform Manifold Approximation and Projection
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- SCANPY: large-scale single-cell gene expression data analysis
- Slide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution
- Deep generative modeling for single-cell transcriptomics
- Ancient DNA and the rewriting of human history: be sparing with Occam’s razor