Biology subjects

Pashkovskaia, N.

Publications and source records attributed to Pashkovskaia, N..

4 recordsLinked to original sources

bioRxiv2026

ViTAMIn-O: Democratizing computer vision-based machine learning for stem cell research

Deep Learning (DL) holds exciting potential in automating the prediction of organoid differentiation results. Nevertheless, current models lack adaptability, openness, and robustness in performance. Additionally, broad employments of predictive models in wet-lab settings necessitate machine learning expertise, often not readily available in biologically oriented laboratories. To offer an intuitive solution, we present ColabViTAMIn-O, a code-free platform together with ViTAMIn-O. ViTAMIn-O is a fully open organoid-specific DL model trained and tested on a total of 34 organoid categories, incorporating annotated images across transmitted light microscopy (TLM) modalities at single-organoid resolution. It is adaptable to downstream prediction tasks of varying dataset sizes and outperforms established models even with linear-probing. It performs reliably within a few-shot framework and is even extensible to human embryo TLM imaging data at single specimen level. By releasing our platform, centralized model hub, and datasets, we hope to encourage broader deployments of specialized DL models in stem-cell laboratories.

bioinformatics↗

bioRxiv2026

Human iPSC-derived CNS and retinal microvasculature-on-a-chip models recapitulate hallmarks of diabetic microvascular pathology

The central nervous system microvasculature (CNS-mv) protects neural tissue from harmful substances while supplying oxygen, nutrients, and signaling molecules. Metabolic diseases such as diabetes induce pathological changes in these microvasculatures, leading to severe outcomes including stroke and diabetic retinopathy. Blood vessels in the brain and retina share similarities and undergo comparable pathological alterations in diabetic patients. However, mechanistic understanding of CNS-mv pathogenesis remains limited due to the lack of physiologically relevant in vitro models. Here, we developed three complementary human iPSC-derived microvascular models: (1) a CNS-mv-on-a-chip for mechanistic studies, (2) scalable 3D microvasculature drops for high-throughput screening, and (3) an inner blood-retinal barrier-on-a-chip incorporating Muller glia. All platforms self-assembled into perfusable networks with high pericyte (PC) coverage and barrier function. We identified the TNF-/NF-{kappa}B pathway as the central mediator of hyperglycemia-induced vascular damage, accompanied by robust induction of inflammatory cytokines IL-1{beta} and IL-6. Importantly, cell-type-specific analysis revealed distinct inflammatory roles: endothelial cells (ECs) predominantly activated TNF-/NF-{kappa}B downstream signaling, whereas pericytes selectively upregulated IL-1{beta}, suggesting a coordinated EC-PC inflammatory crosstalk driving vascular pathology. Functionally, both hyperglycemia and TNF-/IL-1{beta} exposure induced vascular regression, reduced PC coverage, and increased ghost vessel formation, confirming these cytokines as key effectors of diabetic microvascular damage. Uniquely, Muller glia showed divergent behavior from PCs, enhancing their perivascular sheath under inflammation - indicating reactive gliosis rather than protection. Together, these in vitro platforms provide a versatile and physiologically relevant hiPSC-based system for mechanistic studies, screening anti-inflammatory therapeutics and developing glia-targeted interventions.

cell biology↗

bioRxiv2021

Aged human iPSC-RPE organoid cultures display hallmarks of drusen formation

Age-related macular degeneration (AMD) is among the most common causes of irreversible vision loss. Disease progression is strongly associated with age-related pathological changes of retinal pigment epithelial (RPE) cells, such as accumulation of intracellular lipid-containing cell debris, extracellular lipid-rich deposits (drusen) and collagen-rich basal laminar deposits. Current AMD models provide a limited understanding of the complex pathomechanisms, revealing the lack of adequate physiological human AMD models. In this study, we developed an in vitro model applicable for the exploration of AMD pathomechanisms and risk factors for AMD progression and drusen formation. Advanced 3D culturing technologies allow long-term cultivation of hiPSC-derived RPE organoids (RPEorg) for up to 360 days, which is the time frame necessary for the development of an AMD-like phenotype. Aged RPEorg exhibit hallmarks of AMD and age-related alterations such as increased autofluorescence, accumulation of lipid droplets, calcification, and the formation of extracellular clusters of the drusen-associated proteins such as apolipoprotein E (APOE) and tissue inhibitor of metalloproteinases 3 (TIMP3). Electron microscopy further reveals drusen-like extracellular deposits mimicking the signs of late drusen formation and AMD progression. In summary, our results demonstrate that hiPSC-derived 3D RPEorg provide a promising model to study age-associated RPE pathology and drusen formation. We show here that RPEorg are applicable for disease modelling studies and early stages of drug development and provide the opportunity to uncover inter-individual genetic and epigenetic factors that alter the course of the disease.

cell biology↗

bioRxiv2021

Human stem cell-based retina-on-chip as new translational model for validation of AAV retinal gene therapy vectors

Gene therapies using adeno-associated viruses (AAVs) are amongst the most promising strategies to treat or even cure hereditary and acquired retinal diseases. However, the development of new efficient AAV vectors is slow and costly, largely because of the lack of suitable non-clinical models. By faithfully recreating structure and function of human tissues, human induced pluripotent stem cell (iPSC)-derived retinal organoids could become an essential part of the test cascade addressing translational aspects. Organ-on-Chip (OoC) technology further provides the capability to recapitulate microphysiological tissue environments as well as a precise control over structural and temporal parameters. By employing our recently developed Retina-on-chip that merges organoid and OoC-technology, we analyzed the efficacy, kinetics and cell tropism of seven first and second generation AAV vectors. The presented data demonstrate the potential of iPSC-based OoC models as the next generation of screening platforms for future gene therapeutic studies.

bioengineering↗