Jakub Sedzinski

StressNET infers intercellular mechanical stresses from tissue geometry using a Graph Neural Network, achieving state-of-the-art performance in zebrafish and Xenopus embryos.

The paper shows that actin cross-linking regulates basal body patterning through transitions from diffusive to confined motion in Xenopus embryos.

The paper uses morphodynamic features from live imaging to predict cell fate during Xenopus mucociliary epithelial differentiation, showing that integrated time-resolved features outperform single features.

ForSys estimates intercellular stresses and intracellular pressures from time-lapse microscopy, validated in silico and in vivo using Xenopus embryos and zebrafish.

The paper presents a standardized pre-processing pipeline for MARS-seq data using the nf-core framework, improving transparency, scalability, and RNA velocity estimation.

This study uses single-cell transcriptomics to reveal a non-hierarchical model of mucociliary epithelium development in Xenopus, identifying multipotent progenitors and distinct cell-type programs.