Zoe Piran

The paper introduces bioIB, a framework using the Information Bottleneck method to extract compressed, signal-informative representations of scRNA-seq data, demonstrating its utility in diverse biological contexts.

moscot unifies optimal transport for temporal, spatial and spatiotemporal single-cell mapping, using multimodal cost spaces and low-rank solvers to scale to 1.7 million mouse embryo cells.

The paper introduces moslin, a method that combines lineage and gene expression data across time points to predict cell fate and decision driver genes.

This paper introduces biolord, a deep generative framework for disentangling biological factors in single-cell data, enabling prediction of cell states and responses to drug perturbations.

SiFT filters biological signals in single-cell data to uncover hidden processes, outperforming existing methods in preprocessing and revealing disease-related dynamics in COVID-19 data.