MultiCPA: Multimodal Compositional Perturbation Autoencoder
Inecik, K.; Uhlmann, A.; Lotfollahi, M.; Theis, F. J.
Show abstract
Single-cell multimodal profiling provides a high-resolution view of cellular information. Recently, multimodal profiling approaches have been coupled with CRISPR technologies to perform pooled screens of single or combinatorial perturbations. This opens the possibility of exploring the massive space of combinatorial perturbations and their regulatory effects computationally from the extrapolation of a few experimentally feasible combinations. Here, we propose MultiCPA, an end-to-end generative architecture to predict multimodal perturbation response at single cell level. Two mixing strategies to integrate multiple modalities are introduced and compared with existing methods. MultiCPA was also shown to accurately predict unseen combinatorial perturbation responses for multiple modalities. The code to reproduce the results is available on GitHub, theislab/multicpa.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- SwarmMAP: Swarm Learning for Decentralized Cell Type Annotation in Single Cell Sequencing Data 94%
- Synthetic lethality in large-scale integrated metabolic and regulatory network models of human cells 93%
- Network- and Enrichment-based Inference of Phenotypes and Targets from large-scale Disease Maps 93%
Similar papers in this journal
- A variational autoencoder trained with priors from canonical pathways increases the interpretability of transcriptome data 96%
- Learning Genetic Perturbation Effects with Variational Causal Inference 95%
- coupleCoC+: an information-theoretic co-clustering-basedtransfer learning framework for the integrative analysis of single-cell genomic data 95%
Similar papers in this journal
Similar papers in this journal
- Species-Agnostic Transfer Learning for Cross-species Transcriptomics Data Integration without Gene Orthology 96%
- Evaluation of out-of-distribution detection methods for data shifts in single-cell transcriptomics 96%
- Graph Contrastive Learning as a Versatile Foundation for Advanced scRNA-seq Data Analysis 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.