Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Causal Machine Learning for Real-World Impact

Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling

Romain Lopez · NataĊĦa Tagasovska · Stephen Ra · Kyunghyun Cho · Jonathan Pritchard · Aviv Regev


Abstract:

Latent variable models have become a go-to tool for analyzing biological data, especially in the field of single-cell genomics. One remaining challenge is the identification of individual latent variables related to biological pathways, more generally conceptualized as disentanglement. Although versions of variational autoencoders that explicitly promote disentanglement were introduced and applied to single-cell genomics data, the theoretical feasibility of disentanglement from independent and identically distributed measurements has been challenged.Recent methods propose instead to leverage non-stationary data, as well as the sparse mechanism assumption in order to learn disentangled representations, with a causal semantic. Here, we explore the application of these methodological advances in the analysis of single-cell genomics data with genetic or chemical perturbations. We benchmark these methods on simulated single cell expression data to evaluate their performance regarding disentanglement, causal target identification and out-of-domain generalisation. Finally, by applying the approaches to a large-scale gene perturbation dataset, we find that the model relying on the sparse mechanism shift hypothesis surpasses contemporary methods on a transfer learning task.

Chat is not available.