DynaMorph: self-supervised learning of morphodynamic states of live cells

Classification of differentially activated groups of fibroblasts using morphodynamic and motile features

Fibroblasts play essential roles in cancer progression, exhibiting activation states that can either promote or inhibit tumor growth. Understanding these differential activation states is critical for targeting the tumor microenvironment (TME) in cancer therapy. However, traditional molecular markers used to identify cancer-associated fibroblasts are limited by their co-expression across multiple fibroblast subtypes, making it difficult to distinguish specific activation states. Morphological and motility characteristics of fibroblasts reflect their underlying gene expression patterns and activation states, making these features valuable descriptors of fibroblast behavior. This study proposes an artificial intelligence-based classification framework to identify and characterize differentially activated fibroblasts by analyzing their morphodynamic and motile features. We extract these features from label-free live-cell imaging data of fibroblasts co-cultured with breast cancer cell lines using deep learning and machine learning algorithms. Our findings show that morphodynamic and motile features offer robust insights into fibroblast activation states, complementing molecular markers and overcoming their limitations. This biophysical state-based cellular classification framework provides a novel, comprehensive approach for characterizing fibroblast activation, with significant potential for advancing our understanding of the TME and informing targeted cancer therapies.

Automated prediction of fibroblast phenotypes using mathematical descriptors of cellular features

Fibrosis is caused by pathological activation of resident fibroblasts to myofibroblasts that leads to aberrant tissue stiffening and diminished function of affected organs with limited pharmacological interventions. Despite the prevalence of myofibroblasts in fibrotic tissue, existing methods to grade fibroblast phenotypes are typically subjective and qualitative, yet important for screening of new therapeutics. Here, we develop mathematical descriptors of cell morphology and intracellular structures to identify quantitative and interpretable cell features that capture the fibroblast-to-myofibroblast phenotypic transition in immunostained images. We train and validate models on features extracted from over 3000 primary heart valve interstitial cells and test their predictive performance on cells treated with the small molecule drugs 5-azacytidine and bisperoxovanadium (HOpic), which inhibited and promoted myofibroblast activation, respectively. Collectively, this work introduces an analytical framework that unveils key features associated with distinct fibroblast phenotypes via quantitative image analysis and is broadly applicable for high-throughput screening assays of candidate treatments for fibrotic diseases.

Interpretable Fine-Grained Phenotypes of Subcellular Dynamics via Unsupervised Deep Learning

Uncovering fine-grained phenotypes of live cell dynamics is pivotal for a comprehensive understanding of the heterogeneity in healthy and diseased biological processes. However, this endeavor poses significant technical challenges for unsupervised machine learning, requiring the extraction of features that not only faithfully preserve this heterogeneity but also effectively discriminate between established biological states, all while remaining interpretable. To tackle these challenges, a self-training deep learning framework designed for fine-grained and interpretable phenotyping is presented. This framework incorporates an unsupervised teacher model with interpretable features to facilitate feature learning in a student deep neural network (DNN). Significantly, an autoencoder-based regularizer is designed to encourage the student DNN to maximize the heterogeneity associated with molecular perturbations. This method enables the acquisition of features with enhanced discriminatory power, while simultaneously preserving the heterogeneity associated with molecular perturbations. This study successfully delineated fine-grained phenotypes within the heterogeneous protrusion dynamics of migrating epithelial cells, revealing specific responses to pharmacological perturbations. Remarkably, this framework adeptly captured a concise set of highly interpretable features uniquely linked to these fine-grained phenotypes, each corresponding to specific temporal intervals crucial for their manifestation. This unique capability establishes it as a valuable tool for investigating diverse cellular dynamics and their heterogeneity.

A self-supervised embedding of cell migration features for behavior discovery over cell populations

BACKGROUND AND OBJECTIVE

Recent studies point out that the dynamics and interaction of cell populations within their environment are related to several biological processes in immunology. Hence, single-cell analysis in immunology now relies on spatial omics. Moreover, recent literature suggests that immunology scenarios are hierarchically organized, including unknown cell behaviors appearing in different proportions across some observable control and therapy groups. These dynamic behaviors play a crucial role in identifying the causes of processes such as inflammation, aging, and fighting off pathogens or cancerous cells. In this work, we use a self-supervised learning approach to discover these behaviors associated with cell dynamics in an immunology scenario.

MATERIALS AND METHODS

Specifically, we study the different responses of control group and therapy groups in a scenario involving inflammation due to infarct, with a focus on neutrophil migration within blood vessels. Starting from a set of hand-crafted spatio-temporal features, we use a recurrent neural network to generate embeddings that properly describe the dynamics of the migration processes. The network is trained using a novel multi-task contrastive loss that, on the one hand, models the hierarchical structure of our scenario (groups-behaviors-samples) and, on the other, ensures temporal consistency within the embedding, enforcing that subsequent temporal samples obtained from a given cell stay close in the latent space.

RESULTS

Our experimental results demonstrate that the resulting embeddings improve the separability of cell behaviors and log-likelihood of the therapies, when compared to the hand-crafted feature extraction and recent methods from the state of the art, even with dimensionality reduction (16 vs. 21 hand-crafted features).

CONCLUSIONS

Our approach enables single-cell analyses at a population level, being able to automatically discover shared behaviors among different groups. This, in turn, enables the prediction of the therapy effectiveness based on their proportions within a study group.

AI analysis of super-resolution microscopy: Biological discovery in the absence of ground truth

Super-resolution microscopy, or nanoscopy, enables the use of fluorescent-based molecular localization tools to study molecular structure at the nanoscale level in the intact cell, bridging the mesoscale gap to classical structural biology methodologies. Analysis of super-resolution data by artificial intelligence (AI), such as machine learning, offers tremendous potential for the discovery of new biology, that, by definition, is not known and lacks ground truth. Herein, we describe the application of weakly supervised paradigms to super-resolution microscopy and its potential to enable the accelerated exploration of the nanoscale architecture of subcellular macromolecules and organelles.

Anomaly detection for high-content image-based phenotypic cell profiling

High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology.

Perspective on quantitative phase imaging to improve precision cancer medicine

Significance

Quantitative phase imaging (QPI) offers a label-free approach to non-invasively characterize cellular processes by exploiting their refractive index based intrinsic contrast. QPI captures this contrast by translating refractive index associated phase shifts into intensity-based quantifiable data with nanoscale sensitivity. It holds significant potential for advancing precision cancer medicine by providing quantitative characterization of the biophysical properties of cells and tissue in their natural states.

Aim

This perspective aims to discuss the potential of QPI to increase our understanding of cancer development and its response to therapeutics. It also explores new developments in QPI methods towards advancing personalized cancer therapy and early detection.

Approach

We begin by detailing the technical advancements of QPI, examining its implementations across transmission and reflection geometries and phase retrieval methods, both interferometric and non-interferometric. The focus then shifts to QPI's applications in cancer research, including dynamic cell mass imaging for drug response assessment, cancer risk stratification, and in-vivo tissue imaging.

Results

QPI has emerged as a crucial tool in precision cancer medicine, offering insights into tumor biology and treatment efficacy. Its sensitivity to detecting nanoscale changes holds promise for enhancing cancer diagnostics, risk assessment, and prognostication. The future of QPI is envisioned in its integration with artificial intelligence, morpho-dynamics, and spatial biology, broadening its impact in cancer research.

Conclusions

QPI presents significant potential in advancing precision cancer medicine and redefining our approach to cancer diagnosis, monitoring, and treatment. Future directions include harnessing high-throughput dynamic imaging, 3D QPI for realistic tumor models, and combining artificial intelligence with multi-omics data to extend QPI's capabilities. As a result, QPI stands at the forefront of cancer research and clinical application in cancer care.

Morphological profiling for drug discovery in the era of deep learning

Morphological profiling is a valuable tool in phenotypic drug discovery. The advent of high-throughput automated imaging has enabled the capturing of a wide range of morphological features of cells or organisms in response to perturbations at the single-cell resolution. Concurrently, significant advances in machine learning and deep learning, especially in computer vision, have led to substantial improvements in analyzing large-scale high-content images at high throughput. These efforts have facilitated understanding of compound mechanism of action, drug repurposing, characterization of cell morphodynamics under perturbation, and ultimately contributing to the development of novel therapeutics. In this review, we provide a comprehensive overview of the recent advances in the field of morphological profiling. We summarize the image profiling analysis workflow, survey a broad spectrum of analysis strategies encompassing feature engineering- and deep learning-based approaches, and introduce publicly available benchmark datasets. We place a particular emphasis on the application of deep learning in this pipeline, covering cell segmentation, image representation learning, and multimodal learning. Additionally, we illuminate the application of morphological profiling in phenotypic drug discovery and highlight potential challenges and opportunities in this field.

Machine learning inference of continuous single-cell state transitions during myoblast differentiation and fusion

Cells modify their internal organization during continuous state transitions, supporting functions from cell division to differentiation. However, tools to measure dynamic physiological states of individual transitioning cells are lacking. We combined live-cell imaging and machine learning to monitor ERK1/2-inhibited primary murine skeletal muscle precursor cells, that transition rapidly and robustly from proliferating myoblasts to post-mitotic myocytes and then fuse, forming multinucleated myotubes. Our models, trained using motility or actin intensity features from single-cell tracking data, effectively tracked real-time continuous differentiation, revealing that differentiation occurs 7.5-14.5 h post induction, followed by fusion ~3 h later. Co-inhibition of ERK1/2 and p38 led to differentiation without fusion. Our model inferred co-inhibition leads to terminal differentiation, indicating that p38 is specifically required for transitioning from terminal differentiation to fusion. Our model also predicted that co-inhibition leads to changes in actin dynamics. Mass spectrometry supported these in silico predictions and suggested novel fusion and maturation regulators downstream of differentiation. Collectively, this approach can be adapted to various biological processes to uncover novel links between dynamic single-cell states and their functional outcomes.

Orientation-invariant autoencoders learn robust representations for shape profiling of cells and organelles

Cell and organelle shape are driven by diverse genetic and environmental factors and thus accurate quantification of cellular morphology is essential to experimental cell biology. Autoencoders are a popular tool for unsupervised biological image analysis because they learn a low-dimensional representation that maps images to feature vectors to generate a semantically meaningful embedding space of morphological variation. The learned feature vectors can also be used for clustering, dimensionality reduction, outlier detection, and supervised learning problems. Shape properties do not change with orientation, and thus we argue that representation learning methods should encode this orientation invariance. We show that conventional autoencoders are sensitive to orientation, which can lead to suboptimal performance on downstream tasks. To address this, we develop O2-variational autoencoder (O2-VAE), an unsupervised method that learns robust, orientation-invariant representations. We use O2-VAE to discover morphology subgroups in segmented cells and mitochondria, detect outlier cells, and rapidly characterise cellular shape and texture in large datasets, including in a newly generated synthetic benchmark.

Particulate matter composition drives differential molecular and morphological responses in lung epithelial cells

Particulate matter (PM) is a ubiquitous component of air pollution that is epidemiologically linked to human pulmonary diseases. PM chemical composition varies widely, and the development of high-throughput experimental techniques enables direct profiling of cellular effects using compositionally unique PM mixtures. Here, we show that in a human bronchial epithelial cell model, exposure to three chemically distinct PM mixtures drive unique cell viability patterns, transcriptional remodeling, and the emergence of distinct morphological subtypes. Specifically, PM mixtures modulate cell viability, DNA damage responses, and induce the remodeling of gene expression associated with cell morphology, extracellular matrix organization, and cellular motility. Profiling cellular responses showed that cell morphologies change in a PM composition-dependent manner. Finally, we observed that PM mixtures with higher cadmium content induced increased DNA damage and drove redistribution among morphological subtypes. Our results demonstrate that quantitative measurement of individual cellular morphologies provides a robust, high-throughput approach to gauge the effects of environmental stressors on biological systems and score cellular susceptibilities to pollution.

Bridging live-cell imaging and next-generation cancer treatment

By providing spatial, molecular and morphological data over time, live-cell imaging can provide a deeper understanding of the cellular and signalling events that determine cancer response to treatment. Understanding this dynamic response has the potential to enhance clinical outcome by identifying biomarkers or actionable targets to improve therapeutic efficacy. Here, we review recent applications of live-cell imaging for uncovering both tumour heterogeneity in treatment response and the mode of action of cancer-targeting drugs. Given the increasing uses of T cell therapies, we discuss the unique opportunity of time-lapse imaging for capturing the interactivity and motility of immunotherapies. Although traditionally limited in the number of molecular features captured, novel developments in multidimensional imaging and multi-omics data integration offer strategies to connect single-cell dynamics to molecular phenotypes. We review the effect of these recent technological advances on our understanding of the cellular dynamics of tumour targeting and discuss their implication for next-generation precision medicine.

Machine learning enhanced cell tracking

Quantifying cell biology in space and time requires computational methods to detect cells, measure their properties, and assemble these into meaningful trajectories. In this aspect, machine learning (ML) is having a transformational effect on bioimage analysis, now enabling robust cell detection in multidimensional image data. However, the task of cell tracking, or constructing accurate multi-generational lineages from imaging data, remains an open challenge. Most cell tracking algorithms are largely based on our prior knowledge of cell behaviors, and as such, are difficult to generalize to new and unseen cell types or datasets. Here, we propose that ML provides the framework to learn aspects of cell behavior using cell tracking as the task to be learned. We suggest that advances in representation learning, cell tracking datasets, metrics, and methods for constructing and evaluating tracking solutions can all form part of an end-to-end ML-enhanced pipeline. These developments will lead the way to new computational methods that can be used to understand complex, time-evolving biological systems.

Particulate matter composition drives differential molecular and morphological responses in lung epithelial cells

Particulate matter (PM) is a ubiquitous component of indoor and outdoor air pollution that is epidemiologically linked to many human pulmonary diseases. PM has many emission sources, making it challenging to understand the biological effects of exposure due to the high variance in chemical composition. However, the effects of compositionally unique particulate matter mixtures on cells have not been analyzed using both biophysical and biomolecular approaches. Here, we show that in a human bronchial epithelial cell model (BEAS-2B), exposure to three chemically distinct PM mixtures drives unique cell viability patterns, transcriptional remodeling, and the emergence of distinct morphological subtypes. Specifically, PM mixtures modulate cell viability and DNA damage responses and induce the remodeling of gene expression associated with cell morphology, extracellular matrix organization and structure, and cellular motility. Profiling cellular responses showed that cell morphologies change in a PM composition-dependent manner. Lastly, we observed that particulate matter mixtures with high contents of heavy metals, such as cadmium and lead, induced larger drops in viability, increased DNA damage, and drove a redistribution among morphological subtypes. Our results demonstrate that quantitative measurement of cellular morphology provides a robust approach to gauge the effects of environmental stressors on biological systems and determine cellular susceptibilities to pollution.

Morphodynamical cell state description via live-cell imaging trajectory embedding

Time-lapse imaging is a powerful approach to gain insight into the dynamic responses of cells, but the quantitative analysis of morphological changes over time remains challenging. Here, we exploit the concept of "trajectory embedding" to analyze cellular behavior using morphological feature trajectory histories-that is, multiple time points simultaneously, rather than the more common practice of examining morphological feature time courses in single timepoint (snapshot) morphological features. We apply this approach to analyze live-cell images of MCF10A mammary epithelial cells after treatment with a panel of microenvironmental perturbagens that strongly modulate cell motility, morphology, and cell cycle behavior. Our morphodynamical trajectory embedding analysis constructs a shared cell state landscape revealing ligand-specific regulation of cell state transitions and enables quantitative and descriptive models of single-cell trajectories. Additionally, we show that incorporation of trajectories into single-cell morphological analysis enables (i) systematic characterization of cell state trajectories, (ii) better separation of phenotypes, and (iii) more descriptive models of ligand-induced differences as compared to snapshot-based analysis. This morphodynamical trajectory embedding is broadly applicable to the quantitative analysis of cell responses via live-cell imaging across many biological and biomedical applications.

Deep-Manager: a versatile tool for optimal feature selection in live-cell imaging analysis

One of the major problems in bioimaging, often highly underestimated, is whether features extracted for a discrimination or regression task will remain valid for a broader set of similar experiments or in the presence of unpredictable perturbations during the image acquisition process. Such an issue is even more important when it is addressed in the context of deep learning features due to the lack of a priori known relationship between the black-box descriptors (deep features) and the phenotypic properties of the biological entities under study. In this regard, the widespread use of descriptors, such as those coming from pre-trained Convolutional Neural Networks (CNNs), is hindered by the fact that they are devoid of apparent physical meaning and strongly subjected to unspecific biases, i.e., features that do not depend on the cell phenotypes, but rather on acquisition artifacts, such as brightness or texture changes, focus shifts, autofluorescence or photobleaching. The proposed Deep-Manager software platform offers the possibility to efficiently select those features having lower sensitivity to unspecific disturbances and, at the same time, a high discriminating power. Deep-Manager can be used in the context of both handcrafted and deep features. The unprecedented performances of the method are proven using five different case studies, ranging from selecting handcrafted green fluorescence protein intensity features in chemotherapy-related breast cancer cell death investigation to addressing problems related to the context of Deep Transfer Learning. Deep-Manager, freely available at https://github.com/BEEuniroma2/Deep-Manager , is suitable for use in many fields of bioimaging and is conceived to be constantly upgraded with novel image acquisition perturbations and modalities.

Optofluidic imaging meets deep learning: from merging to emerging

Propelled by the striking advances in optical microscopy and deep learning (DL), the role of imaging in lab-on-a-chip has dramatically been transformed from a silo inspection tool to a quantitative "smart" engine. A suite of advanced optical microscopes now enables imaging over a range of spatial scales (from molecules to organisms) and temporal window (from microseconds to hours). On the other hand, the staggering diversity of DL algorithms has revolutionized image processing and analysis at the scale and complexity that were once inconceivable. Recognizing these exciting but overwhelming developments, we provide a timely review of their latest trends in the context of lab-on-a-chip imaging, or coined optofluidic imaging. More importantly, here we discuss the strengths and caveats of how to adopt, reinvent, and integrate these imaging techniques and DL algorithms in order to tailor different lab-on-a-chip applications. In particular, we highlight three areas where the latest advances in lab-on-a-chip imaging and DL can form unique synergisms: image formation, image analytics and intelligent image-guided autonomous lab-on-a-chip. Despite the on-going challenges, we anticipate that they will represent the next frontiers in lab-on-a-chip imaging that will spearhead new capabilities in advancing analytical chemistry research, accelerating biological discovery, and empowering new intelligent clinical applications.

Morphological signatures of actin organization in single cells accurately classify genetic perturbations using CNNs with transfer learning

The actin cytoskeleton plays essential roles in countless cell processes, from cell division to migration to signaling. In cancer cells, cytoskeletal dynamics, cytoskeletal filament organization, and overall cell morphology are known to be altered substantially. We hypothesize that actin fiber organization and cell shape may carry specific signatures of genetic or signaling perturbations. We used convolutional neural networks (CNNs) on a small fluorescence microscopy image dataset of retinal pigment epithelial (RPE) cells and triple-negative breast cancer (TNBC) cells for identifying morphological signatures in cancer cells. Using a transfer learning approach, CNNs could be trained to accurately distinguish between normal and oncogenically transformed RPE cells with an accuracy of about 95% or better at the single cell level. Furthermore, CNNs could distinguish transformed cell lines differing by an oncogenic mutation from each other and could also detect knockdown of cofilin in TNBC cells, indicating that each single oncogenic mutation or cytoskeletal perturbation produces a unique signature in actin morphology. Application of the Local Interpretable Model-Agnostic Explanations (LIME) method for visually interpreting the CNN results revealed features of the global actin structure relevant for some cells and classification tasks. Interestingly, many of these features were supported by previous biological observation. Actin fiber organization is thus a sensitive marker for cell identity, and identification of its perturbations could be very useful for assaying cell phenotypes, including disease states.

Cerebral Organoids as an Experimental Platform for Human Neurogenomics

The cerebral cortex forms early in development according to a series of heritable neurodevelopmental instructions. Despite deep evolutionary conservation of the cerebral cortex and its foundational six-layered architecture, significant variations in cortical size and folding can be found across mammals, including a disproportionate expansion of the prefrontal cortex in humans. Yet our mechanistic understanding of neurodevelopmental processes is derived overwhelmingly from rodent models, which fail to capture many human-enriched features of cortical development. With the advent of pluripotent stem cells and technologies for differentiating three-dimensional cultures of neural tissue in vitro, cerebral organoids have emerged as an experimental platform that recapitulates several hallmarks of human brain development. In this review, we discuss the merits and limitations of cerebral organoids as experimental models of the developing human brain. We highlight innovations in technology development that seek to increase its fidelity to brain development in vivo and discuss recent efforts to use cerebral organoids to study regeneration and brain evolution as well as to develop neurological and neuropsychiatric disease models.