Compound Activity Prediction with Dose-Dependent Transcriptomic Profiles and Deep Learning.

Predicting compound activity in assays is a long-standing challenge in drug discovery. Computational models based on compound-induced gene expression signatures from a single profiling assay have shown promise toward predicting compound activity in other, seemingly unrelated, assays. Applications of such models include predicting mechanisms-of-action (MoA) for phenotypic hits, identifying off-target activities, and identifying polypharmacologies. Here, we introduce transcriptomics-to-activity transformer (TAT) models that leverage gene expression profiles observed over compound treatment at multiple concentrations to predict the compound activity in other biochemical or cellular assays. We built TAT models based on gene expression data from a RASL-seq assay to predict the activity of 2692 compounds in 262 dose-response assays. We obtained useful models for 51% of the assays, as determined through a realistic held-out set. Prospectively, we experimentally validated the activity predictions of a TAT model in a malaria inhibition assay. With a 63% hit rate, TAT successfully identified several submicromolar malaria inhibitors. Our results thus demonstrate the potential of transcriptomic responses over compound concentration and the TAT modeling framework as a cost-efficient way to identify the bioactivities of promising compounds across many assays.

Morphological Characterization of Antibiotic Combinations.

Combination therapies are common in many therapeutic contexts, including infectious diseases and cancer. A common approach for evaluating combinations in vitro is to assess effects on cell growth as synergistic, antagonistic, or neutral using "checkerboard" experiments to systematically sample combinations of agents in multiple doses. To further understand the effects of antibiotic combinations, we employed high-content imaging to study the morphological changes caused by combination treatments in checkerboard experiments. Using an automated, unsupervised image analysis approach to group morphologies, and an "expert-in-the-loop" to annotate them, we attributed the heterogeneous morphological changes ofEscherichia coli cells to varying doses of both single-agent and combination treatments. We identified patterns of morphological change, including morphological potentiation, competition, and the emergence of unexpected morphologies. We found these frequently did not correlate with synergistic or antagonistic effects on viability, suggesting morphological approaches may provide a distinctive signature of the biological interaction between compounds over a range of conditions. Among the unexpected morphologies we observed, there were transitional changes associated with intermediate doses of compounds and uncharacterized phenotypes associated with well-studied antibiotics. Our approach exemplifies how unsupervised image analysis and expert knowledge can be combined to reckon with complex phenotypic changes arising from combination screening, dose titrations, or polypharmacology. In this way, quantification of morphological diversity across treatment conditions could aid in analysis and prioritization of complementary pairings of antibiotic agents by more closely capturing the true signature of the integrated cellular response.

Morphological Deconvolution of Beta-Lactam Polyspecificity in E. coli.

Beta-lactams comprise one of the earliest classes of antibiotic therapies. These molecules covalently inhibit enzymes from the family of penicillin-binding proteins (PBPs), which are essential in construction of the bacterial cell wall. As a result, beta-lactams cause striking changes to cellular morphology, the nature of which varies by the range of PBPs simultaneously engaged in the cell. The traditional method of exploring beta-lactam polyspecificity is a gel-based binding assay which is low-throughput and typically is run  ex situ in cell extracts. Here, we describe a medium-throughput, image-based assay combined with machine learning methods to automatically profile the activity of beta-lactams in E. coli cells. By testing for morphological change across a panel of strains with perturbations to individual PBP enzymes, our approach automatically and quantifiably relates different beta-lactam antibiotics according to their preferences for individual PBPs in cells. We show the potential of our approach for guiding the design of novel inhibitors toward different PBP-binding profiles by predicting the mechanisms of two recently reported PBP inhibitors.

Experimental and computational analyses reveal that environmental restrictions shape HIV-1 spread in 3D cultures.

Pathogens face varying microenvironments in vivo, but suitable experimental systems and analysis tools to dissect how three-dimensional (3D) tissue environments impact pathogen spread are lacking. Here we develop an Integrative method to Study Pathogen spread by Experiment and Computation within Tissue-like 3D cultures (INSPECT-3D), combining quantification of pathogen replication with imaging to study single-cell and cell population dynamics. We apply INSPECT-3D to analyze HIV-1 spread between primary human CD4 T-lymphocytes using collagen as tissue-like 3D-scaffold. Measurements of virus replication, infectivity, diffusion, cellular motility and interactions are combined by mathematical analyses into an integrated spatial infection model to estimate parameters governing HIV-1 spread. This reveals that environmental restrictions limit infection by cell-free virions but promote cell-associated HIV-1 transmission. Experimental validation identifies cell motility and density as essential determinants of efficacy and mode of HIV-1 spread in 3D. INSPECT-3D represents an adaptable method for quantitative time-resolved analyses of 3D pathogen spread.

Clathrin-adaptor ratio and membrane tension regulate the flat-to-curved transition of the clathrin coat during endocytosis.

Although essential for many cellular processes, the sequence of structural and molecular events during clathrin-mediated endocytosis remains elusive. While it was long believed that clathrin-coated pits grow with a constant curvature, it was recently suggested that clathrin first assembles to form flat structures that then bend while maintaining a constant surface area. Here, we combine correlative electron and light microscopy and mathematical growth laws to study the ultrastructural rearrangements of the clathrin coat during endocytosis in BSC-1 mammalian cells. We confirm that clathrin coats initially grow flat and demonstrate that curvature begins when around 70% of the final clathrin content is acquired. We find that this transition is marked by a change in the clathrin to clathrin-adaptor protein AP2 ratio and that membrane tension suppresses this transition. Our results support the notion that BSC-1 mammalian cells dynamically regulate the flat-to-curved transition in clathrin-mediated endocytosis by both biochemical and mechanical factors.

A multi-scale convolutional neural network for phenotyping high-content cellular images.

MOTIVATION: Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. RESULTS: Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, including those of other deep CNN architectures. In addition to using the network to simply obtain a yes-or-no prediction for a given phenotype, we use the probability outputs calculated by the network to quantitatively describe the phenotypes. This study shows that these probability values correlate with chemical treatment concentrations. This finding validates further our approach and enables chemical treatment potency estimation via CNNs. AVAILABILITY AND IMPLEMENTATION: The network specifications and solver definitions are provided in Supplementary Software 1. CONTACT: william_jose.godinez_navarro@novartis.com or xian-1.zhang@novartis.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Tracking Virus Particles in Fluorescence Microscopy Images Using Multi-Scale Detection and Multi-Frame Association.

Automatic fluorescent particle tracking is an essential task to study the dynamics of a large number of biological structures at a sub-cellular level. We have developed a probabilistic particle tracking approach based on multi-scale detection and two-step multi-frame association. The multi-scale detection scheme allows coping with particles in close proximity. For finding associations, we have developed a two-step multi-frame algorithm, which is based on a temporally semiglobal formulation as well as spatially local and global optimization. In the first step, reliable associations are determined for each particle individually in local neighborhoods. In the second step, the global spatial information over multiple frames is exploited jointly to determine optimal associations. The multi-scale detection scheme and the multi-frame association finding algorithm have been combined with a probabilistic tracking approach based on the Kalman filter. We have successfully applied our probabilistic tracking approach to synthetic as well as real microscopy image sequences of virus particles and quantified the performance. We found that the proposed approach outperforms previous approaches.

Tracking multiple particles in fluorescence time-lapse microscopy images via probabilistic data association.

Tracking subcellular structures as well as viral structures displayed as 'particles' in fluorescence microscopy images yields quantitative information on the underlying dynamical processes. We have developed an approach for tracking multiple fluorescent particles based on probabilistic data association. The approach combines a localization scheme that uses a bottom-up strategy based on the spot-enhancing filter as well as a top-down strategy based on an ellipsoidal sampling scheme that uses the Gaussian probability distributions computed by a Kalman filter. The localization scheme yields multiple measurements that are incorporated into the Kalman filter via a combined innovation, where the association probabilities are interpreted as weights calculated using an image likelihood. To track objects in close proximity, we compute the support of each image position relative to the neighboring objects of a tracked object and use this support to recalculate the weights. To cope with multiple motion models, we integrated the interacting multiple model algorithm. The approach has been successfully applied to synthetic 2-D and 3-D images as well as to real 2-D and 3-D microscopy images, and the performance has been quantified. In addition, the approach was successfully applied to the 2-D and 3-D image data of the recent Particle Tracking Challenge at the IEEE International Symposium on Biomedical Imaging (ISBI) 2012.

Investigating the role of F-actin in human immunodeficiency virus assembly by live-cell microscopy.

Human immunodeficiency virus type 1 (HIV-1) particles assemble at the plasma membrane, which is lined by a dense network of filamentous actin (F-actin). Large amounts of actin have been detected in HIV-1 virions, proposed to be incorporated by interactions with the nucleocapsid domain of the viral polyprotein Gag. Previous studies addressing the role of F-actin in HIV-1 particle formation using F-actin-interfering drugs did not yield consistent results. Filamentous structures pointing toward nascent HIV-1 budding sites, detected by cryo-electron tomography and atomic force microscopy, prompted us to revisit the role of F-actin in HIV-1 assembly by live-cell microscopy. HeLa cells coexpressing HIV-1 carrying fluorescently labeled Gag and a labeled F-actin-binding peptide were imaged by live-cell total internal reflection fluorescence microscopy (TIR-FM). Computational analysis of image series did not reveal characteristic patterns of F-actin in the vicinity of viral budding sites. Furthermore, no transient recruitment of F-actin during bud formation was detected by monitoring fluorescence intensity changes at nascent HIV-1 assembly sites. The chosen approach allowed us to measure the effect of F-actin-interfering drugs on the assembly of individual virions in parallel with monitoring changes in the F-actin network of the respective cell. Treatment of cells with latrunculin did not affect the efficiency and dynamics of Gag assembly under conditions resulting in the disruption of F-actin filaments. Normal assembly rates were also observed upon transient stabilization of F-actin by short-term treatment with jasplakinolide. Taken together, these findings indicate that actin filament dynamics are dispensable for HIV-1 Gag assembly at the plasma membrane of HeLa cells. Importance: HIV-1 particles assemble at the plasma membrane of virus-producing cells. This membrane is lined by a dense network of actin filaments that might either present a physical obstacle to the formation of virus particles or generate force promoting the assembly process. Drug-mediated interference with the actin cytoskeleton showed different results for the formation of retroviral particles in different studies, likely due to general effects on the cell upon prolonged drug treatment. Here, we characterized the effect of actin-interfering compounds on the HIV-1 assembly process by direct observation of virus formation in live cells, which allowed us to measure assembly rate constants directly upon drug addition. Virus assembly proceeded with normal rates when actin filaments were either disrupted or stabilized. Taken together with the absence of characteristic actin filament patterns at viral budding sites in our analyses, this indicates that the actin network is dispensable for HIV-1 assembly.

Objective comparison of particle tracking methods.

Particle tracking is of key importance for quantitative analysis of intracellular dynamic processes from time-lapse microscopy image data. Because manually detecting and following large numbers of individual particles is not feasible, automated computational methods have been developed for these tasks by many groups. Aiming to perform an objective comparison of methods, we gathered the community and organized an open competition in which participating teams applied their own methods independently to a commonly defined data set including diverse scenarios. Performance was assessed using commonly defined measures. Although no single method performed best across all scenarios, the results revealed clear differences between the various approaches, leading to notable practical conclusions for users and developers.

Chromosome segregation by the Escherichia coli Min system.

The mechanisms underlying chromosome segregation in prokaryotes remain a subject of debate and no unifying view has yet emerged. Given that the initial disentanglement of duplicated chromosomes could be achieved by purely entropic forces, even the requirement of an active prokaryotic segregation machinery has been questioned. Using computer simulations, we show that entropic forces alone are not sufficient to achieve and maintain full separation of chromosomes. This is, however, possible by assuming repeated binding of chromosomes along a gradient of membrane-associated tethering sites toward the poles. We propose that, in Escherichia coli, such a gradient of membrane tethering sites may be provided by the oscillatory Min system, otherwise known for its role in selecting the cell division site. Consistent with this hypothesis, we demonstrate that MinD binds to DNA and tethers it to the membrane in an ATP-dependent manner. Taken together, our combined theoretical and experimental results suggest the existence of a novel mechanism of chromosome segregation based on the Min system, further highlighting the importance of active segregation of chromosomes in prokaryotic cell biology.

Xenopus cytoplasmic linker-associated protein 1 (XCLASP1) promotes axon elongation and advance of pioneer microtubules.

Dynamic microtubules (MTs) are required for neuronal guidance, in which axons extend directionally toward their target tissues. We found that depletion of the MT-binding protein Xenopus cytoplasmic linker-associated protein 1 (XCLASP1) or treatment with the MT drug Taxol reduced axon outgrowth in spinal cord neurons. To quantify the dynamic distribution of MTs in axons, we developed an automated algorithm to detect and track MT plus ends that have been fluorescently labeled by end-binding protein 3 (EB3). XCLASP1 depletion reduced MT advance rates in neuronal growth cones, very much like treatment with Taxol, demonstrating a potential link between MT dynamics in the growth cone and axon extension. Automatic tracking of EB3 comets in different compartments revealed that MTs increasingly slowed as they passed from the axon shaft into the growth cone and filopodia. We used speckle microscopy to demonstrate that MTs experience retrograde flow at the leading edge. Microtubule advance in growth cone and filopodia was strongly reduced in XCLASP1-depleted axons as compared with control axons, but actin retrograde flow remained unchanged. Instead, we found that XCLASP1-depleted growth cones lacked lamellipodial actin organization characteristic of protrusion. Lamellipodial architecture depended on XCLASP1 and its capacity to associate with MTs, highlighting the importance of XCLASP1 in actin-microtubule interactions.

Identifying virus-cell fusion in two-channel fluorescence microscopy image sequences based on a layered probabilistic approach.

The entry process of virus particles into cells is decisive for infection. In this work, we investigate fusion of virus particles with the cell membrane via time-lapse fluorescence microscopy. To automatically identify fusion for single particles based on their intensity over time, we have developed a layered probabilistic approach. The approach decomposes the action of a single particle into three abstractions: the intensity over time, the underlying temporal intensity model, as well as a high level behavior. Each abstraction corresponds to a layer and these layers are represented via stochastic hybrid systems and hidden Markov models. We use a maxbelief strategy to efficiently combine both representations. To compute estimates for the abstractions we use a hybrid particle filter and the Viterbi algorithm. Based on synthetic image sequences, we characterize the performance of the approach as a function of the image noise. We also characterize the performance as a function of the tracking error. We have also successfully applied the approach to real image sequences displaying pseudotyped HIV-1 particles in contact with host cells and compared the experimental results with ground truth obtained by manual analysis.

Herpesviral replication compartments move and coalesce at nuclear speckles to enhance export of viral late mRNA.

The role of the intranuclear movement of chromatin in gene expression is not well-understood. Herpes simplex virus forms replication compartments (RCs) in infected cell nuclei as sites of viral DNA replication and late gene transcription. These structures develop from small compartments that grow in size, move, and coalesce. Quantitative analysis of RC trajectories, derived from 4D images, shows that most RCs move by directed motion. Directed movement is impaired in the presence of actin and myosin inhibitors as well as a transcription inhibitor. In addition, RCs coalesce at and reorganize nuclear speckles. Lastly, distinct effects of actin and myosin inhibitors on viral gene expression suggest that RC movement is not required for transcription, but rather, movement results in the bridging of transcriptionally active RCs with nuclear speckles to form structures that enhance export of viral late mRNAs.

Development of in vivo quantitative geometric mapping of the aortic arch for advanced endovascular aortic repair: feasibility and preliminary results.

PURPOSE: To evaluate whether quantitative characterization of aortic arch geometry including its branches is feasible based on in vivo computed tomography (CT) angiography and magnetic resonance (MR) angiography data in healthy and diseased aortic arches. MATERIALS AND METHODS: Ten healthy volunteers, 10 patients with abdominal aortic disease, and 10 patients with aortic arch disease underwent MR angiography (10 volunteers) or CT angiography (20 patients). Commercial software was used for individual segmentation of supraaortic arteries. In-house software was developed for segmentation of aortic arch landmarks based on standardized multiplanar reformations (MPRs) and for subsequent aortic arch mapping. RESULTS: Supraaortic arteries and aortic arch landmarks were successfully segmented in all 30 subjects for CT angiography and MR angiography data. Significant tapering within the first centimeter was observed in all supraaortic arteries (P < .001). The three supraaortic arteries showed significantly different vessel diameters and areas (P < .001). The software developed in-house allowed detailed aortic arch mapping with quantitative definitions of the positional relationships between each supraaortic artery and the aorta. Distances between supraaortic arteries were less than 5 mm in 77.6% (mean 4.1 mm ± 3.8). The brachiocephalic trunk tended to be positioned on the right side of the aortic arch, and the left subclavian and left common carotid arteries tended to be positioned on the left side of the aortic arch. CONCLUSIONS: The feasibility and application of a postprocessing method allowing quantification of geometry of supraaortic arteries and aortic arch mapping were successfully demonstrated. Validation and evaluation of clinical implications are warranted.

Tracking and quantitative analysis of dynamic movements of cells and particles.

Understanding complex cellular processes requires investigating the underlying mechanisms within a spatiotemporal context. Although cellular processes are dynamic in nature, most studies in molecular cell biology are based on fixed specimens, for example, using immunocytochemistry or fluorescence in situ hybridization (FISH). However, breakthroughs in fluorescence microscopy imaging techniques, in particular, the discovery of green fluorescent protein (GFP) and its spectral variants, have facilitated the study of a wide range of dynamic processes by allowing nondestructive labeling of target structures in living cells. In addition, the tremendous improvements in spatial and temporal resolution of light microscopes now allow cellular processes to be analyzed in unprecedented detail. These state-of-the-art imaging technologies, however, provide a huge amount of digital image data. To cope with the enormous amount of image data and to extract reproducible as well as quantitative information, computer-based image analysis is required. In this article, we describe methods for computer-based analysis of multidimensional live cell microscopy images and their application to study the dynamics of cells and particles. First, we sketch a general workflow for quantitative analysis of live cell images. Then, we detail computational methods for automatic image analysis comprising image preprocessing, segmentation, registration, tracking, and classification. We conclude with a discussion of quantitative analysis and systems biology.

Dynamics of HIV-1 assembly and release.

Assembly and release of human immunodeficiency virus (HIV) occur at the plasma membrane of infected cells and are driven by the Gag polyprotein. Previous studies analyzed viral morphogenesis using biochemical methods and static images, while dynamic and kinetic information has been lacking until very recently. Using a combination of wide-field and total internal reflection fluorescence microscopy, we have investigated the assembly and release of fluorescently labeled HIV-1 at the plasma membrane of living cells with high time resolution. Gag assembled into discrete clusters corresponding to single virions. Formation of multiple particles from the same site was rarely observed. Using a photoconvertible fluorescent protein fused to Gag, we determined that assembly was nucleated preferentially by Gag molecules that had recently attached to the plasma membrane or arrived directly from the cytosol. Both membrane-bound and cytosol derived Gag polyproteins contributed to the growing bud. After their initial appearance, assembly sites accumulated at the plasma membrane of individual cells over 1-2 hours. Assembly kinetics were rapid: the number of Gag molecules at a budding site increased, following a saturating exponential with a rate constant of approximately 5 x 10(-3) s(-1), corresponding to 8-9 min for 90% completion of assembly for a single virion. Release of extracellular particles was observed at approximately 1,500+/-700 s after the onset of assembly. The ability of the virus to recruit components of the cellular ESCRT machinery or to undergo proteolytic maturation, or the absence of Vpu did not significantly alter the assembly kinetics.

Automatic analysis of dividing cells in live cell movies to detect mitotic delays and correlate phenotypes in time.

Live-cell imaging allows detailed dynamic cellular phenotyping for cell biology and, in combination with small molecule or drug libraries, for high-content screening. Fully automated analysis of live cell movies has been hampered by the lack of computational approaches that allow tracking and recognition of individual cell fates over time in a precise manner. Here, we present a fully automated approach to analyze time-lapse movies of dividing cells. Our method dynamically categorizes cells into seven phases of the cell cycle and five aberrant morphological phenotypes over time. It reliably tracks cells and their progeny and can thus measure the length of mitotic phases and detect cause and effect if mitosis goes awry. We applied our computational scheme to annotate mitotic phenotypes induced by RNAi gene knockdown of CKAP5 (also known as ch-TOG) or by treatment with the drug nocodazole. Our approach can be readily applied to comparable assays aiming at uncovering the dynamic cause of cell division phenotypes.

Visualizing fusion of pseudotyped HIV-1 particles in real time by live cell microscopy.

BACKGROUND: Most retroviruses enter their host cells by fusing the viral envelope with the plasma membrane. Although the protein machinery promoting fusion has been characterized extensively, the dynamics of the process are largely unknown. RESULTS: We generated human immunodeficiency virus-1 (HIV-1) particles pseudotyped with the envelope (Env) protein of ecotropic murine leukemia virus eMLV to study retrovirus entry at the plasma membrane using live-cell microscopy. This Env protein mediates highly efficient pH independent fusion at the cell surface and can be functionally tagged with a fluorescent protein. To detect fusion events, double labeled particles carrying one fluorophor in Env and the other in the matrix (MA) domain of Gag were generated and characterized. Fusion events were defined as loss of Env signal after virus-cell contact. Single particle tracking of >20,000 individual traces in two color channels recorded 28 events of color separation, where particles lost the Env protein, with the MA layer remaining stable at least for a short period. Fourty-five events were detected where both colors were lost simultaneously. Importantly, the first type of event was never observed when particles were pseudotyped with a non-fusogenic Env. CONCLUSION: These results reveal rapid retroviral fusion at the plasma membrane and permit studies of the immediate post-fusion events.

Automated analysis of the mitotic phases of human cells in 3D fluorescence microscopy image sequences.

The evaluation of fluorescence microscopy images acquired in high-throughput cell phenotype screens constitutes a substantial bottleneck and motivates the development of automated image analysis methods. Here we introduce a computational scheme to process 3D multi-cell time-lapse images as they are produced in large-scale RNAi experiments. We describe an approach to automatically segment, track, and classify cell nuclei into different mitotic phases. This enables automated analysis of the duration of single phases of the cell life cycle and thus the identification of cell cultures that show an abnormal mitotic behavior. Our scheme proves a high accuracy, suggesting a promising future for automating the evaluation of high-throughput experiments.