Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling
Celcomen leverages a mathematical causality framework to disentangle intra- and inter- cellular gene regulation programs in spatial transcriptomics and single-cell data through a generative graph neural network. It can learn gene-gene interactions, as well as generate post-perturbation counterfactual spatial transcriptomics, thereby offering access to experimentally inaccessible samples. We validated its disentanglement, identifiability, and counterfactual prediction capabilities through simulations and in clinically relevant human glioblastoma, human fetal spleen, and mouse lung cancer samples. Celcomen provides the means to model disease and therapy induced changes allowing for new insights into single-cell spatially resolved tissue responses relevant to human health.
Code (1)
Tasks
counterfactualDisentanglementGraph Neural NetworkSimilar Papers 제목 키워드 기반
CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
Predicting cellular responses to various perturbations is a critical focus in drug discovery and personalized therapeutics, with deep learning models playing a significant role in this endeavor. Single-cell datasets cont…
counterfactualCounterfactual ReasoningDisentanglementDrug DiscoveryQuerying Counterfactuals on Tissue Graphs with Supervised Disentanglement
Tissue graph counterfactuals ask how a cell's expression would change under altered spatial neighbor contexts. Such queries are central to predicting cell behavior in tissues, but lack a unified definition, with existing…
Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling
Latent variable models such as the Variational Auto-Encoder (VAE) have become a go-to tool for analyzing biological data, especially in the field of single-cell genomics. One remaining challenge is the interpretability o…
DisentanglementDomain GeneralizationTransfer LearningDisentanglement of Latent Representations via Causal Interventions
The process of generating data such as images is controlled by independent and unknown factors of variation. The retrieval of these variables has been studied extensively in the disentanglement, causal representation lea…
DisentanglementRepresentation LearningRetrievalFedDis: A Causal Disentanglement Framework for Federated Traffic Prediction
Federated learning offers a promising paradigm for privacy-preserving traffic prediction, yet its performance is often challenged by the non-identically and independently distributed (non-IID) nature of decentralized tra…
Federated LearningTraffic Prediction