Biology subjects

Viana, M. P.

Publications and source records attributed to Viana, M. P..

12 recordsLinked to original sources

bioRxiv2026

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.

cell biology↗

bioRxiv2026

Dynamics of ML-based Morphological Features Indicate a Shear Stress-Dependent Bifurcation of hiPSC-Derived Endothelial Cell States

Cell states are increasingly conceptualized as attractors of high-dimensional dynamical systems, yet quantitative approaches for integrating phenotypic information into this framework remain limited. Here, we take an image-based approach that combines unsupervised machine learning (ML) with timelapse imaging to extract and characterize the temporal dynamics of morphological features. Using a cell line with endogenously tagged VE-cadherin, we acquired brightfield and fluorescence timelapse images of human induced pluripotent stem cell-derived endothelial cell (hiPSC-EC) monolayers, which adopt distinct phenotypes at two different magnitudes of shear stress in terms of their morphology, behavior, and VE-cadherin organization. To quantify these phenotypic cell states without segmentation, we trained a diffusion autoencoder to predict VE-cadherin signal from brightfield images. We identified interpretable ML-based features representing cell orientation, elongation, and local density. Treating these variables as dimensions of a morphological state space, we estimated a data-driven vector field and found that the two observed phenotypic cell states correspond to stable fixed points of the inferred dynamical system. Mapping measured cell migration coherence onto this space further distinguished the states. Imaging cells across intermediate shear stresses revealed a regime of bistability in which both states coexist, indicating that the shear-stress-dependent transition between endothelial cell states occurs as a bifurcation of the inferred dynamical system. Finally, we applied this method to study an N-terminal truncation of VE-cadherin, finding that mutated cells preserve alignment and coherent migration, but exhibit altered morphology and increased migration speed. This work demonstrates the applicability of a dynamical systems approach to quantitatively characterize morphological aspects of cell state from interpretable ML-based features.

biophysics↗

bioRxiv2026

Multi-omic profiling of human antibody-secreting cells reveals diverse subsets sustain durable humoral immunity

Antibody-secreting cells (ASCs) provide humoral immunity that can mediate lifelong protection against pathogens. Current classifications cannot delineate the heterogenous functionalities, tissue residencies, and lifespans of human ASC subsets, impeding clinical translation. We applied multi-omic sequencing, spatial proteomics, and functional assays to discover and characterize human bone marrow (BM) ASC subsets. We identified two peripheral subsets (ASCp) also present in blood and three BM-resident subsets (ASCr), comprising a maturation continuum associated with increased mitochondrial networking, diminished antibody secretion, differential transcription factor motif accessibility, and preferential co-localization in homotypic niches. CD19+9+ASCr and CD19-ASCr exhibited poor recovery years after BM transplantation, indicating a strong dependence on supportive niches. Childhood vaccine antigens were recognized by long-lived ASCr subsets in adults and by immature HLA-DR+ASCp, implying ASCs can differentiate without recent antigen exposure. Our results provide new insights into ASC identity, maturation, and longevity and a generalizable framework for study and manipulation of human ASCs.

immunology↗

bioRxiv2025

Cell shapes decode molecular phenotypes in image-basedspatial proteomics

The diversity of cellular and tissue structures can arise from a few basic cell shapes, which undergo various transformations based on biophysical constraints on cytoskeletal organization. While cellular geometry has been linked with selected biological processes such as polarity, signaling or morphogenesis, the orchestration of the whole proteome in association to cell shape is still poorly understood. In this study, using more than 1 million images of single cells stained for 11,998 proteins across 10 cell lines in the Human Protein Atlas database, we performed an integrated analysis of organelle, pathway and single protein levels in association to a 2D cellular shapespace. We found that cell and nuclear shapes across cell lines exist in a shared continuum. We also found that the subcellular organelle topology varies across cell lines, but remains robust within each cell lines shapespace. At the single protein level, we found that cells of different shapes in the same cell cycle phase might be preparing for different fates, and that many non-cell cycle proteins expressed shape-based abundance variation. Using the same coordinate framework defined by shape, we could analyze the distribution shift of protein spatial localization under drug perturbation.

bioengineering↗

bioRxiv2024

A human induced pluripotent stem (hiPS) cell model for the holistic study of epithelial to mesenchymal transitions (EMTs)

The epithelial to mesenchymal transition (EMT) is a widely studied but poorly defined state change due to the variety of ways in which it has been characterized in cells. There is a need for reproducible cell model systems that enable the integration and comparison of different types of measured observations of cells across many distinct cellular contexts. We present human induced pluripotent stem (hiPS) cells as such a model system by demonstrating its utility through a comparative analysis of hiPS cell-EMT in 2D and 3D cell culture geometries. We developed live-imaging-based assays to directly compare examples of changes in cell function (via migration timing), molecular components (via expression of marker proteins), organization (via reorganization of cell junctions), and environment (via dynamics of basement membrane) in the same experimental system. The EMT-related changes we measured occurred earlier in 2D colonies than in 3D lumenoids, likely due to differences in the basement membrane environments associated with 2D vs. 3D initial hiPS cell culture geometries. We have made the 449 60-hour-long 3D time-lapse movies and the associated tools used for analysis and visualization open-source and easily accessible as a resource for future work in this field.

cell biology↗

bioRxiv2024

Interpretable representation learning for 3D multi-piece intracellular structures using point clouds

A key challenge in understanding subcellular organization is quantifying interpretable measurements of intracellular structures with complex multi-piece morphologies in an objective, robust and generalizable manner. Here we introduce a morphology-appropriate representation learning framework that uses 3D rotation invariant autoencoders and point clouds. This framework is used to learn representations of complex multi-piece morphologies that are independent of orientation, compact, and easy to interpret. We apply our framework to intracellular structures with punctate morphologies (e.g. DNA replication foci) and polymorphic morphologies (e.g. nucleoli). We systematically compare our framework to image-based autoencoders across several intracellular structure datasets, including a synthetic dataset with pre-defined rules of organization. We explore the trade-offs in the performance of different models by performing multi-metric benchmarking across efficiency, generative capability, and representation expressivity metrics. We find that our framework, which embraces the underlying morphology of multi-piece structures, facilitates the unsupervised discovery of sub-clusters for each structure. We show how our approach can also be applied to phenotypic profiling using a dataset of nucleolar images following drug perturbations. We implement and provide all representation learning models using CytoDL, a python package for flexible and configurable deep learning experiments.

cell biology↗

bioRxiv2024

Colony context and size-dependent compensation mechanisms give rise to variations in nuclear growth trajectories

To investigate the fundamental question of how cellular variations arise across spatiotemporal scales in a population of identical healthy cells, we focused on nuclear growth in hiPS cell colonies as a model system. We generated a 3D timelapse dataset of thousands of nuclei over multiple days, and developed open-source tools for image and data analysis and an interactive timelapse viewer for exploring quantitative features of nuclear size and shape. We performed a data-driven analysis of nuclear growth variations across timescales. We found that individual nuclear volume growth trajectories arise from short timescale variations attributable to their spatiotemporal context within the colony. We identified a strikingly time-invariant volume compensation relationship between nuclear growth duration and starting volume across the population. Notably, we discovered that inheritance plays a crucial role in determining these two key nuclear growth features while other growth features are determined by their spatiotemporal context and are not inherited.

cell biology↗

bioRxiv2023

Mitochondrial protein heterogeneity stems from the stochastic nature of co-translational protein targeting in cell senescence

A decline in mitochondrial function is a hallmark of aging and neurodegenerative diseases. It has been proposed that changes in mitochondrial morphology, including fragmentation of the tubular mitochondrial network, can lead to mitochondrial dysfunction, yet the mechanism of this loss of function is unclear. Most proteins contained within mitochondria are nuclear-encoded and must be properly targeted to the mitochondria. Here, we report that sustained mRNA localization and co-translational protein delivery leads to a heterogeneous protein distribution across fragmented mitochondria. We find that age-induced mitochondrial fragmentation drives a substantial increase in protein expression noise across fragments. Using a translational kinetic and molecular diffusion model, we find that protein expression noise is explained by the nature of stochastic compartmentalization and that co-translational protein delivery is the main contributor to increased heterogeneity. We observed that cells primarily reduce the variability in protein distribution by utilizing mitochondrial fission-fusion processes rather than relying on the mitophagy pathway. Furthermore, we are able to reduce the heterogeneity of the protein distribution by inhibiting co-translational protein targeting. This research lays the framework for a better understanding of the detrimental impact of mitochondrial fragmentation on the physiology of cells in aging and disease.

cell biology↗

bioRxiv2020

Robust integrated intracellular organization of the human iPS cell: where, how much, and how variable?

Despite the intimate link between cell organization and function, the principles underlying intracellular organization and the relation between organization, gene expression and phenotype are not well understood. We address this by creating a benchmark for mean cell organization and the natural range of cell-to-cell variation. This benchmark can be used for comparison to other normal or abnormal cell states. To do this, we developed a reproducible microscope imaging pipeline to generate a high-quality dataset of 3D, high-resolution images of over 200,000 live cells from 25 isogenic human induced pluripotent stem cell (hiPSC) lines from the Allen Cell Collection. Each line contains one fluorescently tagged protein, created via endogenous CRISPR/Cas9 gene editing, representing a key cellular structure or organelle. We used these images to develop a new multi-part and generalizable analysis approach of the locations, amounts, and variation of these 25 cellular structures. Taking an integrated approach, we found that both the extent to which a structures individual location varied ("stereotypy") and the extent to which the structure localized relative to all the other cellular structures ("concordance") were robust to a wide range of cell shape variation, from flatter to taller, smaller to larger, or less to more polarized cells. We also found that these cellular structures varied greatly in how their volumes scaled with cell and nuclear size. These analyses create a data-driven set of quantitative rules for the locations, amounts, and variation of 25 cellular structures within the hiPSC as a normal baseline for cell organization.

cell biology↗

bioRxiv2020

Cell states beyond transcriptomics: integrating structural organization and gene expression in hiPSC-derived cardiomyocytes

We present a quantitative co-analysis of RNA abundance and sarcomere organization in single cells and an integrated framework to predict subcellular organization states from gene expression. We used human induced pluripotent stem cell (hiPSC)-derived cardiomyocytes expressing mEGFP-tagged alpha-actinin-2 to develop quantitative image analysis tools for systematic and automated classification of subcellular organization. This captured a wide range of sarcomeric organization states within cell populations that were previously difficult to quantify. We performed RNA FISH targeting genes identified by single cell RNA sequencing to simultaneously assess the relationship between transcript abundance and structural states in single cells. Co-analysis of gene expression and sarcomeric patterns in the same cells revealed biologically meaningful correlations that could be used to predict organizational states. This study establishes a framework for multi-dimensional analysis of single cells to study the relationships between gene expression and subcellular organization and to develop a more nuanced description of cell states. Graphical AbstractTranscriptional profiling and structural classification was performed on human induced pluripotent stem cell-derived cardiomyocytes to characterize the relationship between transcript abundance and subcellular organization. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=199 SRC="FIGDIR/small/081083v1_ufig1.gif" ALT="Figure 1"> View larger version (60K): org.highwire.dtl.DTLVardef@8f89c4org.highwire.dtl.DTLVardef@19dc813org.highwire.dtl.DTLVardef@1ba7c20org.highwire.dtl.DTLVardef@2b3daa_HPS_FORMAT_FIGEXP M_FIG C_FIG

cell biology↗

bioRxiv2019

Mitochondrial volume fraction controls translation of nuclear-encoded mitochondrial proteins

Mitochondria are dynamic in their size and morphology yet must also precisely control their protein composition according to cellular energy demand. This control is particularly complicated for mitochondria, as they must coordinate gene expression from both the nuclear and mitochondrial genome. We have found that cells are able to use this dynamic morphology to post-transcriptionally coordinate protein expression with the metabolic demands of the cell through enhanced mRNA localization to the mitochondria. As yeast switch to respiratory metabolism, they increase their mitochondrial volume fraction that is, the ratio of mitochondrial volume to intracellular volume which drives the localization of nuclear-encoded mitochondrial mRNAs to the surface of the mitochondria. Through artificial tethering experiments, we show that this mitochondrial localization is sufficient to increase protein production, whereas sequestering mRNAs away from the mitochondrial surface decreases protein production, and those cells are deficient in growth in respiratory conditions. Furthermore, we find that this mRNA sensitivity to mitochondrial volume fraction is driven by the speed of translation downstream of the mitochondrial targeting sequence (MTS), as local ribosome stalling through a stretch of polyprolines in the nascent peptide can drive constitutive localization of mRNAs to the mitochondria. This points to a mechanism by which organelle volume fraction provides feedback to regulate organelle-specific gene expression through mRNA localization while potentially circumventing the need to directly coordinate with the nuclear genome.

cell biology↗

bioRxiv2018

The Allen Cell Structure Segmenter: a new open sourcetoolkit for segmenting 3D intracellular structures influorescence microscopy images

A continuing challenge in quantitative cell biology is the accurate and robust 3D segmentation of structures of interest from fluorescence microscopy images in an automated, reproducible, and widely accessible manner for subsequent interpretable data analysis. We describe the Allen Cell and Structure Segmenter (Segmenter), a Python-based open source toolkit developed for 3D segmentation of cells and intracellular structures in fluorescence microscope images. This toolkit brings together classic image segmentation and iterative deep learning workflows first to generate initial high-quality 3D intracellular structure segmentations and then to easily curate these results to generate the ground truths for building robust and accurate deep learning models. The toolkit takes advantage of the high-replicate 3D live cell image data collected at the Allen Institute for Cell Science of over 30 endogenous fluorescently tagged human induced pluripotent stem cell (hiPSC) lines. Each cell line represents a different intracellular structure with one or more distinct localization patterns within undifferentiated hiPS cells and hiPSC-derived cardiomyocytes. The Segmenter consists of two complementary elements, a classic image segmentation workflow with a restricted set of algorithms and parameters and an iterative deep learning segmentation workflow. We created a collection of 20 classic image segmentation workflows based on 20 distinct and representative intracellular structure localization patterns as a "lookup table" reference and starting point for users. The iterative deep learning workflow can take over when the classic segmentation workflow is insufficient. Two straightforward "human-in-the-loop" curation strategies convert a set of classic image segmentation workflow results into a set of 3D ground truth images for iterative model training without the need for manual painting in 3D. The deep learning model architectures used in this toolkit were designed and tested specifically for 3D fluorescence microscope images and implemented as readable scripts. The Segmenter thus leverages state of the art computer vision algorithms in an accessible way to facilitate their application by the experimental biology researcher. We include two useful applications to demonstrate how we used the classic image segmentation and iterative deep learning workflows to solve more challenging 3D segmentation tasks. First, we introduce the Training Assay approach, a new experimental-computational co-design concept to generate more biologically accurate segmentation ground truths. We combined the iterative deep learning workflow with three Training Assays to develop a robust, scalable cell and nuclear instance segmentation algorithm, which could achieve accurate target segmentation for over 98% of individual cells and over 80% of entire fields of view. Second, we demonstrate how to extend the lamin B1 segmentation model built from the iterative deep learning workflow to obtain more biologically accurate lamin B1 segmentation by utilizing multi-channel inputs and combining multiple ML models. The steps and workflows used to develop these algorithms are generalizable to other similar segmentation challenges. More information, including tutorials and code repositories, are available at allencell.org/segmenter.

cell biology↗