Anne Condon

CellUntangler disentangles multiple biological signals in single-cell data using deep generative models, separating cell cycle from other signals like cell type and differentiation.

This study benchmarks deep learning methods for building atomic models from cryo-EM density maps, showing their superiority over traditional methods and the benefits of integrating AlphaFold.

The paper introduces scvis, a deep generative model for dimensionality reduction of single-cell RNA-seq data, preserving both local and global structures in low-dimensional representations.