Lab of Computational Cell Dynamics

Computational cell dynamics

Oded is developing generative models and deep learning innovations for analysis of biomedical images

Guy is developing network-based representations to measure cell biological state transitions for intracellular and for tissue organization

Reut is developing methods to analyze fluorescence lifetime imaging microscopy (FLIM) in the context of triple negative breast cancer patient samples

Omri analyzes recurring spatial multicellular motifs to understand immune organization

Barak is using Graph Neural Networks to optimize cell type hierarchies for spatial biology

Daniel is developing a virtual staining model by utilizing deep generative models to generate high-fidelity mIF images directly from standard H&E tissue

​

Orit is mentoring students in multiple diverse projects, advising on computational and technical issues, formulating challenging research questions and keeping contact with collaborators

Yuval is investigating the interplay between cell shape and its intracellular molecular composition and organization

Lion is developing a method for visual interpretation of image-to-image transformation models and applying it to in-silico organelle localization.

Leah is investigating the brain vasculature structure in Glioblastoma (GBM) patients data

Omer is developing a method for inference of organelle alterations by combining supervised interpretable AI and in silico labeling.

Denis is developing metrics to decouple global and local signals in collective cell death dynamics

​

Noga's reseach focus on trustworthy in silico labeling, model interpretability, and cellular dynamics via live-cell imaging

Esraa is developing methods for quantitative spatiotemporal characterization of heterogeneous collective cell death

Leor is developing methods for analysis and integration of multimodal bioimaging data.

Alon is developing computational methods for data-driven early prediction of a tissue rigidity phase transition in zebrafish morphogenesis

Eitan is developing a foundation model for in silico labeling to reduce the amount of paired imaging required, to achieve robustness and generalization across different datasets and organelles

Kobe develops deep learning methods for the alignment and integration of multimodal spatial omics

​