Deconvolution of subcellular protrusion heterogeneity and the underlying actin regulator dynamics from live cell imaging

PPP2R1A regulates migration persistence through the NHSL1-containing WAVE Shell Complex

The RAC1-WAVE-Arp2/3 signaling pathway generates branched actin networks that power lamellipodium protrusion of migrating cells. Feedback is thought to control protrusion lifetime and migration persistence, but its molecular circuitry remains elusive. Here, we identify PPP2R1A by proteomics as a protein differentially associated with the WAVE complex subunit ABI1 when RAC1 is activated and downstream generation of branched actin is blocked. PPP2R1A is found to associate at the lamellipodial edge with an alternative form of WAVE complex, the WAVE Shell Complex, that contains NHSL1 instead of the Arp2/3 activating subunit WAVE, as in the canonical WAVE Regulatory Complex. PPP2R1A is required for persistence in random and directed migration assays and for RAC1-dependent actin polymerization in cell extracts. PPP2R1A requirement is abolished by NHSL1 depletion. PPP2R1A mutations found in tumors impair WAVE Shell Complex binding and migration regulation, suggesting that the coupling of PPP2R1A to the WAVE Shell Complex is essential to its function.

Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses

Analyzing the dynamic changes of cellular morphology is important for understanding the various functions and characteristics of live cells, including stem cells and metastatic cancer cells. To this end, we need to track all points on the highly deformable cellular contour in every frame of live cell video. Local shapes and textures on the contour are not evident, and their motions are complex, often with expansion and contraction of local contour features. The prior arts for optical flow or deep point set tracking are unsuited due to the fluidity of cells, and previous deep contour tracking does not consider point correspondence. We propose the first deep learning-based tracking of cellular (or more generally viscoelastic materials) contours with point correspondence by fusing dense representation between two contours with cross attention. Since it is impractical to manually label dense tracking points on the contour, unsupervised learning comprised of the mechanical and cyclical consistency losses is proposed to train our contour tracker. The mechanical loss forcing the points to move perpendicular to the contour effectively helps out. For quantitative evaluation, we labeled sparse tracking points along the contour of live cells from two live cell datasets taken with phase contrast and confocal fluorescence microscopes. Our contour tracker quantitatively outperforms compared methods and produces qualitatively more favorable results. Our code and data are publicly available at https://github.com/JunbongJang/contour-tracking/.

Granger-causal inference of the lamellipodial actin regulator hierarchy by live cell imaging without perturbation

Many cell regulatory systems implicate nonlinearity and redundancy among components. The regulatory network governing lamellipodial and lamellar actin structures is prototypical of such a system, containing tens of actin-nucleating and -modulating molecules with functional overlap and feedback loops. Due to instantaneous and long-term compensation, phenotyping the system response to perturbation provides limited information on the roles the targeted component plays in the unperturbed system. Accordingly, how individual actin regulators contribute to lamellipodial dynamics remains ambiguous. Here, we present a perturbation-free reconstruction of cause-effect relations among actin regulators by applying Granger-causal inference to constitutive image fluctuations that indicate regulator recruitment as a proxy for activity. Our analysis identifies distinct zones of actin regulator activation and of causal effects on filament assembly and delineates actin-dependent and actin-independent regulator roles in controlling edge motion. We propose that edge motion is driven by assembly of two independently operating actin filament systems.

A machine learning pipeline revealing heterogeneous responses to drug perturbations on vascular smooth muscle cell spheroid morphology and formation

Machine learning approaches have shown great promise in biology and medicine discovering hidden information to further understand complex biological and pathological processes. In this study, we developed a deep learning-based machine learning algorithm to meaningfully process image data and facilitate studies in vascular biology and pathology. Vascular injury and atherosclerosis are characterized by neointima formation caused by the aberrant accumulation and proliferation of vascular smooth muscle cells (VSMCs) within the vessel wall. Understanding how to control VSMC behaviors would promote the development of therapeutic targets to treat vascular diseases. However, the response to drug treatments among VSMCs with the same diseased vascular condition is often heterogeneous. Here, to identify the heterogeneous responses of drug treatments, we created an in vitro experimental model system using VSMC spheroids and developed a machine learning-based computational method called HETEROID (heterogeneous spheroid). First, we established a VSMC spheroid model that mimics neointima-like formation and the structure of arteries. Then, to identify the morphological subpopulations of drug-treated VSMC spheroids, we used a machine learning framework that combines deep learning-based spheroid segmentation and morphological clustering analysis. Our machine learning approach successfully showed that FAK, Rac, Rho, and Cdc42 inhibitors differentially affect spheroid morphology, suggesting that multiple drug responses of VSMC spheroid formation exist. Overall, our HETEROID pipeline enables detailed quantitative drug characterization of morphological changes in neointima formation, that occurs in vivo, by single-spheroid analysis.

A deep learning-based segmentation pipeline for profiling cellular morphodynamics using multiple types of live cell microscopy

MOTIVATION

Quantitative studies of cellular morphodynamics rely on extracting leading-edge velocity time series based on accurate cell segmentation from live cell imaging. However, live cell imaging has numerous challenging issues regarding accurate edge localization. Fluorescence live cell imaging produces noisy and low-contrast images due to phototoxicity and photobleaching. While phase contrast microscopy is gentle to live cells, it suffers from the halo and shade-off artifacts that cannot be handled by conventional segmentation algorithms. Here, we present a deep learning-based pipeline, termed MARS-Net (Multiple-microscopy-type-based Accurate and Robust Segmentation Network), that utilizes transfer learning and data from multiple types of microscopy to localize cell edges with high accuracy, allowing quantitative profiling of cellular morphodynamics.

SUMMARY

To accurately segment cell edges and quantify cellular morphodynamics from live-cell imaging data, we developed a deep learning-based pipeline termed MARS-Net (multiple-microscopy-type-based accurate and robust segmentation network). MARS-Net utilizes transfer learning and data from multiple types of microscopy to localize cell edges with high accuracy. For effective training on distinct types of live-cell microscopy, MARS-Net comprises a pretrained VGG19 encoder with U-Net decoder and dropout layers. We trained MARS-Net on movies from phase-contrast, spinning-disk confocal, and total internal reflection fluorescence microscopes. MARS-Net produced more accurate edge localization than the neural network models trained with single-microscopy-type datasets. We expect that MARS-Net can accelerate the studies of cellular morphodynamics by providing accurate pixel-level segmentation of complex live-cell datasets.

Emerging machine learning approaches to phenotyping cellular motility and morphodynamics

Cells respond heterogeneously to molecular and environmental perturbations. Phenotypic heterogeneity, wherein multiple phenotypes coexist in the same conditions, presents challenges when interpreting the observed heterogeneity. Advances in live cell microscopy allow researchers to acquire an unprecedented amount of live cell image data at high spatiotemporal resolutions. Phenotyping cellular dynamics, however, is a nontrivial task and requires machine learning (ML) approaches to discern phenotypic heterogeneity from live cell images. In recent years, ML has proven instrumental in biomedical research, allowing scientists to implement sophisticated computation in which computers learn and effectively perform specific analyses with minimal human instruction or intervention. In this review, we discuss how ML has been recently employed in the study of cell motility and morphodynamics to identify phenotypes from computer vision analysis. We focus on new approaches to extract and learn meaningful spatiotemporal features from complex live cell images for cellular and subcellular phenotyping.

Data science in cell imaging

Cell imaging has entered the 'Big Data' era. New technologies in light microscopy and molecular biology have led to an explosion in high-content, dynamic and multidimensional imaging data. Similar to the 'omics' fields two decades ago, our current ability to process, visualize, integrate and mine this new generation of cell imaging data is becoming a critical bottleneck in advancing cell biology. Computation, traditionally used to quantitatively test specific hypotheses, must now also enable iterative hypothesis generation and testing by deciphering hidden biologically meaningful patterns in complex, dynamic or high-dimensional cell image data. Data science is uniquely positioned to aid in this process. In this Perspective, we survey the rapidly expanding new field of data science in cell imaging. Specifically, we highlight how data science tools are used within current image analysis pipelines, propose a computation-first approach to derive new hypotheses from cell image data, identify challenges and describe the next frontiers where we believe data science will make an impact. We also outline steps to ensure broad access to these powerful tools - democratizing infrastructure availability, developing sensitive, robust and usable tools, and promoting interdisciplinary training to both familiarize biologists with data science and expose data scientists to cell imaging.

New insights and best practices for the successful use of Empirical Mode Decomposition, Iterative Filtering and derived algorithms

Algorithms based on Empirical Mode Decomposition (EMD) and Iterative Filtering (IF) are largely implemented for representing a signal as superposition of simpler well-behaved components called Intrinsic Mode Functions (IMFs). Although they are more suitable than traditional methods for the analysis of nonlinear and nonstationary signals, they could be easily misused if their known limitations, together with the assumptions they rely on, are not carefully considered. In this work, we examine the main pitfalls and provide caveats for the proper use of the EMD- and IF-based algorithms. Specifically, we address the problems related to boundary errors, to the presence of spikes or jumps in the signal and to the decomposition of highly-stochastic signals. The consequences of an improper usage of these techniques are discussed and clarified also by analysing real data and performing numerical simulations. Finally, we provide the reader with the best practices to maximize the quality and meaningfulness of the decomposition produced by these techniques. In particular, a technique for the extension of signal to reduce the boundary effects is proposed; a careful handling of spikes and jumps in the signal is suggested; the concept of multi-scale statistical analysis is presented to treat highly stochastic signals.

Lamellipodin tunes cell migration by stabilizing protrusions and promoting adhesion formation

Efficient migration on adhesive surfaces involves the protrusion of lamellipodial actin networks and their subsequent stabilization by nascent adhesions. The actin-binding protein lamellipodin (Lpd) is thought to play a critical role in lamellipodium protrusion, by delivering Ena/VASP proteins onto the growing plus ends of actin filaments and by interacting with the WAVE regulatory complex, an activator of the Arp2/3 complex, at the leading edge. Using B16-F1 melanoma cell lines, we demonstrate that genetic ablation of Lpd compromises protrusion efficiency and coincident cell migration without altering essential parameters of lamellipodia, including their maximal rate of forward advancement and actin polymerization. We also confirmed lamellipodia and migration phenotypes with CRISPR/Cas9-mediated Lpd knockout Rat2 fibroblasts, excluding cell type-specific effects. Moreover, computer-aided analysis of cell-edge morphodynamics on B16-F1 cell lamellipodia revealed that loss of Lpd correlates with reduced temporal protrusion maintenance as a prerequisite of nascent adhesion formation. We conclude that Lpd optimizes protrusion and nascent adhesion formation by counteracting frequent, chaotic retraction and membrane ruffling.This article has an associated First Person interview with the first author of the paper.

Direct measurement of vertical forces shows correlation between mechanical activity and proteolytic ability of invadopodia

Mechanobiology plays a prominent role in cancer invasion and metastasis. The ability of a cancer to degrade extracellular matrix (ECM) is likely connected to its invasiveness. Many cancer cells form invadopodia-micrometer-sized cellular protrusions that promote invasion through matrix degradation (proteolysis). Although it has been hypothesized that invadopodia exert mechanical force that is implicated in cancer invasion, direct measurements remain elusive. Here, we use a recently developed interferometric force imaging technique that provides piconewton resolution to quantify invadopodial forces in cells of head and neck squamous carcinoma and to monitor their temporal dynamics. We compare the force exerted by individual protrusions to their ability to degrade ECM and investigate the mechanical effects of inhibiting invadopodia through overexpression of microRNA-375. By connecting the biophysical and biochemical characteristics of invadopodia, our study provides a new perspective on cancer invasion that, in the future, may help to identify biomechanical targets for cancer therapy.