Assaf Zaritsky
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Assaf Zaritsky has a total of 256 co-authors. Here are the top co-authors by number of shared publications:
- Gaudenz Danuser
Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center
8 shared publications - Ilan Tsarfaty
Department of Clinical Microbiology and Immunology, Sackler School of Medicine, Tel Aviv University, Tel Aviv 69978, Israel
6 shared publications - Sari Natan
Department of Clinical Microbiology and Immunology, Sackler School of Medicine, Tel Aviv University, Tel Aviv, Israel
6 shared publications Daniel S. Seidman
AIVF Ltd., Tel Aviv, Israel
4 shared publications- Maddy Parsons
Randall Centre for Cell and Molecular Biophysics, King’s College London, Guy’s Campus
4 shared publications - Oded Rotem
Ben-Gurion University of the Negev
4 shared publications
Latest Publications
- Open Access
DM4ISL: high-fidelity and uncertainty-aware in silico labeling of fluorescence images via diffusion models
In silico labeling predicts organelle-specific localizations from label-free images, potentially enabling longitudinal and multiplexed live-cell imaging. Here we present DM4ISL (Diffusion Model for In Silico Labeling), a high-fidelity and uncertainty-aware model that overcomes current limitations, such as blurry or structurally inaccurate predictions, by resolving the intrinsic entanglement of biological signal and noise that characterizes fluorescence imaging. DM4ISL leverages the iterative nature of diffusion through a step-wise self-ensemble averaging approach that marginalizes these stochastic fluctuations, preventing the overfitting to noise that typically degrades standard final-step predictions. Benchmarking across six organelles demonstrates that DM4ISL systematically outperforms state-of-the-art architectures in structural fidelity, as confirmed through both pixel-based and application-specific metrics. Furthermore, calculating the standard deviation across intermediate denoising steps generates localized uncertainty maps that automatically detect erroneous predictions at inference time. Providing high-fidelity predictions alongside built-in reliability metrics, DM4ISL offers a robust method for trustworthy, data-driven discovery in cell biology.
Open AccessDM4ISL: high-fidelity and uncertainty-aware in silico labeling of fluorescence images via diffusion models
In silico labeling predicts organelle-specific localizations from label-free images, potentially enabling longitudinal and multiplexed live-cell imaging. Here we present DM4ISL (Diffusion Model for In Silico Labeling), a high-fidelity and uncertainty-aware model that overcomes current limitations, such as blurry or structurally inaccurate predictions, by resolving the intrinsic entanglement of biological signal and noise that characterizes fluorescence imaging. DM4ISL leverages the iterative nature of diffusion through a step-wise self-ensemble averaging approach that marginalizes these stochastic fluctuations, preventing the overfitting to noise that typically degrades standard final-step predictions. Benchmarking across six organelles demonstrates that DM4ISL systematically outperforms state-of-the-art architectures in structural fidelity, as confirmed through both pixel-based and application-specific metrics. Furthermore, calculating the standard deviation across intermediate denoising steps generates localized uncertainty maps that automatically detect erroneous predictions at inference time. Providing high-fidelity predictions alongside built-in reliability metrics, DM4ISL offers a robust method for trustworthy, data-driven discovery in cell biology.
- Open Access
Trustworthy in silico labeling via semantic visual interpretability of image-to-image translation
Cross-modality image translation promises to provide multiple layers of biological information from a single image input, yet its practical application is stalled by a lack of interpretability and the inability to account for model imperfections. In silico labeling, the inference of organelle localization from label-free images, is a primary example where this black-box nature limits adoption. We present Mask Interpreter, a generalized method for semantic visual interpretability of image-to-image translation models. By uncovering organelle-specific “explanation signatures”, Mask Interpreter validates that models rely on authentic biological structures rather than spurious artifacts. Beyond biological validation, it outperforms traditional explainable AI (xAI) approaches, identifies batch effects and localizes prediction errors when ground-truth fluorescence is unavailable. Semantic confidence modeling further provides fine-grained reliability assessment at single-cell resolution, enabling the automated exclusion of artifacts from downstream analyses. By bridging the gap between computational inference and meaningful biological features, Mask Interpreter transforms in silico labeling into a reliable tool for scientific discovery across diverse biomedical imaging modalities.
Open AccessTrustworthy in silico labeling via semantic visual interpretability of image-to-image translation
Cross-modality image translation promises to provide multiple layers of biological information from a single image input, yet its practical application is stalled by a lack of interpretability and the inability to account for model imperfections. In silico labeling, the inference of organelle localization from label-free images, is a primary example where this black-box nature limits adoption. We present Mask Interpreter, a generalized method for semantic visual interpretability of image-to-image translation models. By uncovering organelle-specific “explanation signatures”, Mask Interpreter validates that models rely on authentic biological structures rather than spurious artifacts. Beyond biological validation, it outperforms traditional explainable AI (xAI) approaches, identifies batch effects and localizes prediction errors when ground-truth fluorescence is unavailable. Semantic confidence modeling further provides fine-grained reliability assessment at single-cell resolution, enabling the automated exclusion of artifacts from downstream analyses. By bridging the gap between computational inference and meaningful biological features, Mask Interpreter transforms in silico labeling into a reliable tool for scientific discovery across diverse biomedical imaging modalities.
- 27 July 2026
- Published by EMBL-EBI
DM4ISL: Prediction Error Annotation and Uncertainty Benchmark Dataset
BioStudies – one package for all the data supporting a study
- 27 July 2026
- Published by EMBL-EBI
DM4ISL: Prediction Error Annotation and Uncertainty Benchmark Dataset
BioStudies – one package for all the data supporting a study
- Open Access
- 15 May 2026
- Published by Elsevier in Cell Reports Methods
- Vol. 6 (7) , 101463
Data modeling the interplay between single-cell shape, single-cell protein expression, and tissue state
- 15 May 2026
- Published by Elsevier in Cell Reports Methods
- Vol. 6 (7) , 101463
Open AccessData modeling the interplay between single-cell shape, single-cell protein expression, and tissue state
- Open Access
- 19 December 2025
- Published by Springer Nature in Nature Methods
- Vol. 23 (2) , 405-416
Cell context-dependent in silico organelle localization in label-free microscopy images
The in silico labeling prediction of organelle fluorescence from label-free microscopy images has the potential to revolutionize our understanding of cells as integrated complex systems. However, out-of-distribution data caused by changes in the intracellular organization across cell types, cellular processes or perturbations can lead to altered label-free images and impaired in silico labeling. Here we demonstrate that incorporating biological meaningful cell contexts, via a context-dependent model that we call CELTIC, enhanced in silico labeling prediction and enabled the downstream analysis of out-of-distribution data such as cells undergoing mitosis and cells located at the edge of the colony. These results suggest a link between cell context and intracellular organization. Using CELTIC to generate single-cell images transitioning between different contexts enabled us to overcome intercell variability toward the integrated characterization of organelles’ alterations in cellular organization. The explicit inclusion of context has the potential to harmonize multiple datasets, paving the way for generalized in silico labeling foundation models.
- 19 December 2025
- Published by Springer Nature in Nature Methods
- Vol. 23 (2) , 405-416
Open AccessCell context-dependent in silico organelle localization in label-free microscopy images
The in silico labeling prediction of organelle fluorescence from label-free microscopy images has the potential to revolutionize our understanding of cells as integrated complex systems. However, out-of-distribution data caused by changes in the intracellular organization across cell types, cellular processes or perturbations can lead to altered label-free images and impaired in silico labeling. Here we demonstrate that incorporating biological meaningful cell contexts, via a context-dependent model that we call CELTIC, enhanced in silico labeling prediction and enabled the downstream analysis of out-of-distribution data such as cells undergoing mitosis and cells located at the edge of the colony. These results suggest a link between cell context and intracellular organization. Using CELTIC to generate single-cell images transitioning between different contexts enabled us to overcome intercell variability toward the integrated characterization of organelles’ alterations in cellular organization. The explicit inclusion of context has the potential to harmonize multiple datasets, paving the way for generalized in silico labeling foundation models.
- Open Access
Spatially distinct chromatin compaction states predict neoadjuvant chemotherapy resistance in Triple Negative Breast Cancer
Organisation and dynamics of chromatin play a key role in regulation of cell state and function. In cancer, chromatin plasticity is known to be important in control of drug resistance, but the relationship between chromatin compaction and chemotherapy response within complex tissue settings remains unclear. Here, we measured single nuclei chromatin compaction using fluorescence lifetime imaging microscopy (FLIM) in situ in whole biopsies from 53 pre treatment and 14 post surgery tissue samples of human triple-negative breast cancer (TNBC) patients to determine whether single nuclei spatial chromatin compaction state can predict resistance to neoadjuvant chemotherapy (NACT). Bulk chromatin compaction across 53 pre-treatment core biopsies did not predict patient outcome. However, machine learning analysis revealed that a subset of patients exhibited distinct distributions of single nuclei with more open chromatin states, which was predictive of NACT-resistance. Graph neural network analysis established that the spatial arrangement of chromatin compaction contributed to prediction of NACT resistance and that chromatin compaction signatures were preserved in tissue state transitions from pre- to 14 post-NACT samples. Our findings shed new light on spatial control of chromatin structure and relationship to therapeutic resistance and establish a foundation for further molecular analysis of chromatin states in complex biological tissues.
Open AccessSpatially distinct chromatin compaction states predict neoadjuvant chemotherapy resistance in Triple Negative Breast Cancer
Organisation and dynamics of chromatin play a key role in regulation of cell state and function. In cancer, chromatin plasticity is known to be important in control of drug resistance, but the relationship between chromatin compaction and chemotherapy response within complex tissue settings remains unclear. Here, we measured single nuclei chromatin compaction using fluorescence lifetime imaging microscopy (FLIM) in situ in whole biopsies from 53 pre treatment and 14 post surgery tissue samples of human triple-negative breast cancer (TNBC) patients to determine whether single nuclei spatial chromatin compaction state can predict resistance to neoadjuvant chemotherapy (NACT). Bulk chromatin compaction across 53 pre-treatment core biopsies did not predict patient outcome. However, machine learning analysis revealed that a subset of patients exhibited distinct distributions of single nuclei with more open chromatin states, which was predictive of NACT-resistance. Graph neural network analysis established that the spatial arrangement of chromatin compaction contributed to prediction of NACT resistance and that chromatin compaction signatures were preserved in tissue state transitions from pre- to 14 post-NACT samples. Our findings shed new light on spatial control of chromatin structure and relationship to therapeutic resistance and establish a foundation for further molecular analysis of chromatin states in complex biological tissues.
- 4 December 2025
- Published by EMBL-EBI
Fluorescence Lifetime Imaging Microscopy (FLIM) of human triple negative breast cancer tissue samples
- 4 December 2025
- Published by EMBL-EBI
Fluorescence Lifetime Imaging Microscopy (FLIM) of human triple negative breast cancer tissue samples
- Open Access
- 29 October 2025
- Published by Elsevier in Cell Systems
- Vol. 16 (11) , 101429
Anomaly detection for high-content image-based phenotypic cell profiling
- 29 October 2025
- Published by Elsevier in Cell Systems
- Vol. 16 (11) , 101429
Open AccessAnomaly detection for high-content image-based phenotypic cell profiling
- Open Access
Context-dependent spatial multicellular network motifs for single-cell spatial biology
The clinical state of diseased tissue is caused by complex intercellular processes that go beyond pairwise cell-cell interactions and are difficult to infer due to the combinatorial explosion of such high-dimensionality. We present context-dependent identification of spatial motifs (CISM), a two-step method to identify local cell structures associated with a disease state in single cell spatial data. First, for each tissue, CISM enumerates structures of enriched reoccurring multicellular patterns that define modular ‘motifs’ in the multicellular network. Second, discriminative motifs are selected according to the context - their presence in patients at different clinical disease states. By applying CISM, we show that modular structures composed of as little as 3-5 cells and their relative spatial arrangement can encode differences in clinical disease states in cohorts of triple-negative breast cancer (TNBC) and melanoma patients. Machine learning validation indicated that discriminative motifs outperform state-of-the-art methods for disease state prediction while enabling interpretation of which interactions in what spatial context are associated with these predictions. CISM-derived discriminative motifs may define an intermediate spatial scale of abstraction and modularity in multicellular organization and function with broad applicability in the domain of spatial single cell omics and beyond.
Open AccessContext-dependent spatial multicellular network motifs for single-cell spatial biology
The clinical state of diseased tissue is caused by complex intercellular processes that go beyond pairwise cell-cell interactions and are difficult to infer due to the combinatorial explosion of such high-dimensionality. We present context-dependent identification of spatial motifs (CISM), a two-step method to identify local cell structures associated with a disease state in single cell spatial data. First, for each tissue, CISM enumerates structures of enriched reoccurring multicellular patterns that define modular ‘motifs’ in the multicellular network. Second, discriminative motifs are selected according to the context - their presence in patients at different clinical disease states. By applying CISM, we show that modular structures composed of as little as 3-5 cells and their relative spatial arrangement can encode differences in clinical disease states in cohorts of triple-negative breast cancer (TNBC) and melanoma patients. Machine learning validation indicated that discriminative motifs outperform state-of-the-art methods for disease state prediction while enabling interpretation of which interactions in what spatial context are associated with these predictions. CISM-derived discriminative motifs may define an intermediate spatial scale of abstraction and modularity in multicellular organization and function with broad applicability in the domain of spatial single cell omics and beyond.
- Open Access
- 23 December 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 6 (12)
Decoupling Implantation Prediction and Embryo Ranking in Machine Learning: The Impact of Clinical Data and Discarded Embryos
- 23 December 2024
- Published by Wiley in Advanced Intelligent Systems
- Vol. 6 (12)
Open AccessDecoupling Implantation Prediction and Embryo Ranking in Machine Learning: The Impact of Clinical Data and Discarded Embryos