The Power of Two: integrating deep diffusion models and variational autoencoders for single-cell transcriptomics analysis
Sadria, M.; Layton, A.
Show abstract
Discovering a lower-dimensional embedding of single-cell data can greatly improve downstream analysis. The embedding should encapsulate both the high-level semantics and low-level variations in order to be meaningful and interpretable. Although current generative models have been used to learn such a low-dimensional representation, they have several limitations. Here, we introduce scVAEDer, a scalable deep-learning model that combines the power of variational autoencoders and deep diffusion models to learn a meaningful representation which can capture both global semantics and local variations in the data. By using the learned embedding, we show that scVAEDer can generate novel scRNA-seq data, predict the effect of the perturbation on various cell types, identify changes in gene expression during dedifferentiation, and detect master regulators in a biological process.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- FateNet: an integration of dynamical systems and deep learning for cell fate prediction 96%
- ARTEMIS integrates autoencoders and schrodinger bridges to predict continuous dynamics of gene expression, cell population and perturbation from time-series single-cell data 96%
- scNODE: Generative Model for Temporal Single Cell Transcriptomic Data Prediction 96%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Learning the rules of cell competition without prior scientific knowledge 95%
- Inferring spatial single-cell-level interactions through interpreting cell state and niche correlations learned by self-supervised graph transformer 95%
- Gene set inference from single-cell sequencing data using a hybrid of matrix factorization and variational autoencoders 94%
"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.