AI-based histologic scoring enables automated and reproducible assessment of enrollment criteria and endpoints in NASH clinical trials.

Clinical trials in nonalcoholic steatohepatitis (NASH) require histologic scoring for assessment of inclusion criteria and endpoints. However, guidelines for scoring key features have led to variability in interpretation, impacting clinical trial outcomes. We developed an artificial intelligence (AI)-based measurement (AIM) tool for scoring NASH histology (AIM-NASH). AIM-NASH predictions for NASH Clinical Research Network (CRN) grades of necroinflammation and stages of fibrosis aligned with expert consensus scores and were reproducible. Continuous scores produced by AIM-NASH for key histological features of NASH correlated with mean pathologist scores and with noninvasive biomarkers and strongly predicted patient outcomes. In a retrospective analysis of the ATLAS trial, previously unmet pathological endpoints were met when scored by the AIM-NASH algorithm alone. Overall, these results suggest that AIM-NASH may assist pathologists in histologic review of NASH clinical trials, reducing inter-rater variability on trial outcomes and offering a more sensitive and reproducible measure of patient therapeutic response.

Association of artificial intelligence-powered and manual quantification of programmed death-ligand 1 (PD-L1) expression with outcomes in patients treated with nivolumab ± ipilimumab.

Assessment of programmed death ligand 1 (PD-L1) expression by immunohistochemistry (IHC) has emerged as an important predictive biomarker across multiple tumor types. However, manual quantitation of PD-L1 positivity can be difficult and leads to substantial inter-observer variability. Although the development of artificial intelligence (AI) algorithms may mitigate some of the challenges associated with manual assessment and improve the accuracy of PD-L1 expression scoring, use of AI-based approaches to oncology biomarker scoring and drug development has been sparse, primarily due to the lack of large-scale clinical validation studies across multiple cohorts and tumor types. We developed AI-powered algorithms to evaluate PD-L1 expression on tumor cells by IHC and compared it with manual IHC scoring in urothelial carcinoma, non-small cell lung cancer, melanoma, and squamous cell carcinoma of the head and neck (prospectively determined during the phase II and III CheckMate clinical trials). 1,746 slides were retrospectively analyzed, the largest investigation of digital pathology algorithms on clinical trial datasets performed to date. AI-powered quantification of PD-L1 expression on tumor cells identified more PD-L1-positive samples compared with manual scoring at cutoffs of ≥1% and ≥5% in most tumor types. Additionally, similar improvements in response and survival were observed in patients identified as PD-L1-positive compared with PD-L1-negative using both AI-powered and manual methods, while improved associations with survival were observed in patients with certain tumor types identified as PD-L1-positive using AI-powered scoring only. Our study demonstrates the potential for implementation of digital pathology-based methods in future clinical practice to identify more patients who would benefit from treatment with immuno-oncology therapy compared with current guidelines using manual assessment.

Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes.

Computational methods have made substantial progress in improving the accuracy and throughput of pathology workflows for diagnostic, prognostic, and genomic prediction. Still, lack of interpretability remains a significant barrier to clinical integration. We present an approach for predicting clinically-relevant molecular phenotypes from whole-slide histopathology images using human-interpretable image features (HIFs). Our method leverages >1.6 million annotations from board-certified pathologists across >5700 samples to train deep learning models for cell and tissue classification that can exhaustively map whole-slide images at two and four micron-resolution. Cell- and tissue-type model outputs are combined into 607 HIFs that quantify specific and biologically-relevant characteristics across five cancer types. We demonstrate that these HIFs correlate with well-known markers of the tumor microenvironment and can predict diverse molecular signatures (AUROC 0.601-0.864), including expression of four immune checkpoint proteins and homologous recombination deficiency, with performance comparable to 'black-box' methods. Our HIF-based approach provides a comprehensive, quantitative, and interpretable window into the composition and spatial architecture of the tumor microenvironment.

A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH.

BACKGROUND AND AIMS: Manual histological assessment is currently the accepted standard for diagnosing and monitoring disease progression in NASH, but is limited by variability in interpretation and insensitivity to change. Thus, there is a critical need for improved tools to assess liver pathology in order to risk stratify NASH patients and monitor treatment response. APPROACH AND RESULTS: Here, we describe a machine learning (ML)-based approach to liver histology assessment, which accurately characterizes disease severity and heterogeneity, and sensitively quantifies treatment response in NASH. We use samples from three randomized controlled trials to build and then validate deep convolutional neural networks to measure key histological features in NASH, including steatosis, inflammation, hepatocellular ballooning, and fibrosis. The ML-based predictions showed strong correlations with expert pathologists and were prognostic of progression to cirrhosis and liver-related clinical events. We developed a heterogeneity-sensitive metric of fibrosis response, the Deep Learning Treatment Assessment Liver Fibrosis score, which measured antifibrotic treatment effects that went undetected by manual pathological staging and was concordant with histological disease progression. CONCLUSIONS: Our ML method has shown reproducibility and sensitivity and was prognostic for disease progression, demonstrating the power of ML to advance our understanding of disease heterogeneity in NASH, risk stratify affected patients, and facilitate the development of therapies.

Highly Multiplexed Fluorescence in Situ Hybridization for in Situ Genomics.

The quantification of changes in gene copy number is critical to our understanding of tumor biology and for the clinical management of cancer patients. DNA fluorescence in situ hybridization is the gold standard method to detect copy number alterations, but it is limited by the number of genes one can quantify simultaneously. To increase the throughput of this informative technique, a fluorescent bar-code system for the unique labeling of dozens of genes and an automated image analysis algorithm that enabled their simultaneous hybridization for the quantification of gene copy numbers were devised. We demonstrate the reliability of this multiplex approach on normal human lymphocytes, metaphase spreads of transformed cell lines, and cultured circulating tumor cells. It also opens the door to the development of gene panels for more comprehensive analysis of copy number changes in tissue, including the study of heterogeneity and of high-throughput clinical assays that could provide rapid quantification of gene copy numbers in samples with limited cellularity, such as circulating tumor cells.

The organization of leukotriene biosynthesis on the nuclear envelope revealed by single molecule localization microscopy and computational analyses.

The initial steps in the synthesis of leukotrienes are the translocation of 5-lipoxygenase (5-LO) to the nuclear envelope and its subsequent association with its scaffold protein 5-lipoxygenase-activating protein (FLAP). A major gap in our understanding of this process is the knowledge of how the organization of 5-LO and FLAP on the nuclear envelope regulates leukotriene synthesis. We combined single molecule localization microscopy with Clus-DoC cluster analysis, and also a novel unbiased cluster analysis to analyze changes in the relationships between 5-LO and FLAP in response to activation of RBL-2H3 cells to generate leukotriene C4. We identified the time-dependent reorganization of both 5-LO and FLAP into higher-order assemblies or clusters in response to cell activation via the IgE receptor. Clus-DoC analysis identified a subset of these clusters with a high degree of interaction between 5-LO and FLAP that specifically correlates with the time course of LTC4 synthesis, strongly suggesting their role in the initiation of leukotriene biosynthesis.

Microscale arrays for the profiling of start and stop signals coordinating human-neutrophil swarming.

Neutrophil swarms protect healthy tissues by sealing off sites of infection. In the absence of swarming, microbial invasion of surrounding tissues can result in severe infections. Recent observations in animal models have shown that swarming requires rapid neutrophil responses and well-choreographed neutrophil migration patterns. However, in animal models physical access to the molecular signals coordinating neutrophil activities during swarming is limited. Here, we report the development and validation of large microscale arrays of zymosan-particle clusters for the study of human neutrophils during swarming ex vivo. We characterized the synchronized swarming of human neutrophils under the guidance of neutrophil-released chemokines, and measured the mediators released at different phases of human-neutrophil swarming against targets simulating infections. We found that the network of mediators coordinating human-neutrophil swarming includes start and stop signals, proteolytic enzymes and enzyme inhibitors, as well as modulators of activation of other immune and non-immune cells. We also show that the swarming behavior of neutrophils from patients following major trauma is deficient and gives rise to smaller swarms than those of neutrophils from healthy individuals.

Development of MAST: A Microscopy-Based Antimicrobial Susceptibility Testing Platform.

Antibiotic resistance is compromising our ability to treat bacterial infections. Clinical microbiology laboratories guide appropriate treatment through antimicrobial susceptibility testing (AST) of patient bacterial isolates. However, increasingly, pathogens are developing resistance to a broad range of antimicrobials, requiring AST of alternative agents for which no commercially available testing methods are available. Therefore, there exists a significant AST testing gap in which current methodologies cannot adequately address the need for rapid results in the face of unpredictable susceptibility profiles. To address this gap, we developed a multicomponent, microscopy-based AST (MAST) platform capable of AST determinations after only a 2 h incubation. MAST consists of a solid-phase microwell growth surface in a 384-well plate format, inkjet printing-based application of both antimicrobials and bacteria at any desired concentrations, automated microscopic imaging of bacterial replication, and a deep learning approach for automated image classification and determination of antimicrobial minimal inhibitory concentrations (MICs). In evaluating a susceptible strain set, 95.8% were within ±1 and 99.4% were within ±2, twofold dilutions, respectively, of reference broth microdilution MIC values. Most (98.3%) of the results were in categorical agreement. We conclude that MAST offers promise for rapid, accurate, and flexible AST to help address the antimicrobial testing gap.

Coordinated integrin activation by actin-dependent force during T-cell migration.

For a cell to move forward it must convert chemical energy into mechanical propulsion. Force produced by actin polymerization can generate traction across the plasma membrane by transmission through integrins to their ligands. However, the role this force plays in integrin activation is unknown. Here we show that integrin activity and cytoskeletal dynamics are reciprocally linked, where actin-dependent force itself appears to regulate integrin activity. We generated fluorescent tension-sensing constructs of integrin αLß2 (LFA-1) to visualize intramolecular tension during cell migration. Using quantitative imaging of migrating T cells, we correlate tension in the αL or ß2 subunit with cell and actin dynamics. We find that actin engagement produces tension within the ß2 subunit to induce and stabilize an active integrin conformational state and that this requires intact talin and kindlin motifs. This supports a general mechanism where localized actin polymerization can coordinate activation of the complex machinery required for cell migration.

Purkinje Cells Directly Inhibit Granule Cells in Specialized Regions of the Cerebellar Cortex.

Inhibition of granule cells plays a key role in gating the flow of signals into the cerebellum, and it is thought that Golgi cells are the only interneurons that inhibit granule cells. Here we show that Purkinje cells, the sole output neurons of the cerebellar cortex, also directly inhibit granule cells via their axon collaterals. Anatomical and optogenetic studies indicate that this non-canonical feedback is region specific: it is most prominent in lobules that regulate eye movement and process vestibular information. Collaterals provide fast, slow, and tonic inhibition to granule cells, and thus allow Purkinje cells to regulate granule cell excitability on multiple timescales. We propose that this feedback mechanism could regulate excitability of the input layer, contribute to sparse coding, and mediate temporal integration.

The RNA-binding protein SFPQ orchestrates an RNA regulon to promote axon viability.

To achieve accurate spatiotemporal patterns of gene expression, RNA-binding proteins (RBPs) guide nuclear processing, intracellular trafficking and local translation of target mRNAs. In neurons, RBPs direct transport of target mRNAs to sites of translation in remote axons and dendrites. However, it is not known whether an individual RBP coordinately regulates multiple mRNAs within these morphologically complex cells. Here we identify SFPQ (splicing factor, poly-glutamine rich) as an RBP that binds and regulates multiple mRNAs in dorsal root ganglion sensory neurons and thereby promotes neurotrophin-dependent axonal viability. SFPQ acts in nuclei, cytoplasm and axons to regulate functionally related mRNAs essential for axon survival. Notably, SFPQ is required for coassembly of LaminB2 (Lmnb2) and Bclw (Bcl2l2) mRNAs in RNA granules and for axonal trafficking of these mRNAs. Together these data demonstrate that SFPQ orchestrates spatial gene expression of a newly identified RNA regulon essential for axonal viability.

Dynamics of Snake-like Swarming Behavior of Vibrio alginolyticus.

Swarming represents a special case of bacterial behavior where motile bacteria migrate rapidly and collectively on surfaces. Swarming and swimming motility of bacteria has been studied well for rigid, self-propelled rods. In this study we report a strain of Vibrio alginolyticus, a species that exhibits similar collective motility but a fundamentally different cell morphology with highly flexible snake-like swarming cells. Investigating swarming dynamics requires high-resolution imaging of single cells with coverage over a large area: thousands of square microns. Researchers previously have employed various methods of motion analysis but largely for rod-like bacteria. We employ temporal variance analysis of a short time-lapse microscopic image series to capture the motion dynamics of swarming Vibrio alginolyticus at cellular resolution over hundreds of microns. Temporal variance is a simple and broadly applicable method for analyzing bacterial swarming behavior in two and three dimensions with both high-resolution and wide-spatial coverage. This study provides detailed insights into the swarming architecture and dynamics of Vibrio alginolyticus isolate B522 on carrageenan agar that may lay the foundation for swarming studies of snake-like, nonrod-shaped motile cell types.

Functional hierarchy of redundant actin assembly factors revealed by fine-grained registration of intrinsic image fluctuations.

Highly redundant pathways often contain components whose functions are difficult to decipher from the responses induced by genetic or molecular perturbations. Here, we present a statistical approach that samples and registers events observed in images of intrinsic fluctuations in unperturbed cells to establish the functional hierarchy of events in systems with redundant pathways. We apply this approach to study the recruitment of actin assembly factors involved in the protrusion of the cell membrane. We find that the formin mDia1, along with nascent adhesion components, is recruited to the leading edge of the cell before protrusion onset, initiating linear growth of the lamellipodial network. Recruitment of Arp2/3, VASP, cofilin, and the formin mDia2 then promotes sustained exponential growth of the network. Experiments changing membrane tension suggest that Arp2/3 recruitment is mechano-responsive. These results indicate that cells adjust the overlapping contributions of multiple factors to actin filament assembly during protrusion on a ten-second timescale and in response to mechanical cues.

Cytoplasmic dynein is required for the spatial organization of protein aggregates in filamentous fungi.

Eukaryotes have evolved multiple strategies for maintaining cellular protein homeostasis. One such mechanism involves neutralization of deleterious protein aggregates via their defined spatial segregation. Here, using the molecular disaggregase Hsp104 as a marker for protein aggregation, we describe the spatial and temporal dynamics of protein aggregates in the filamentous fungus Aspergillus nidulans. Filamentous fungi, such as A. nidulans, are a diverse group of species of major health and economic importance and also serve as model systems for studying highly polarized eukaryotic cells. We find that microtubules promote the formation of Hsp104-positive aggregates, which coalesce into discrete subcellular structures in a process dependent on the microtubule-based motor cytoplasmic dynein. Finally, we find that impaired clearance of these inclusions negatively impacts retrograde trafficking of endosomes, a conventional dynein cargo, indicating that microtubule-based transport can be overwhelmed by chronic cellular stress.

A direct GABAergic output from the basal ganglia to frontal cortex.

The basal ganglia are phylogenetically conserved subcortical nuclei necessary for coordinated motor action and reward learning. Current models postulate that the basal ganglia modulate cerebral cortex indirectly via an inhibitory output to thalamus, bidirectionally controlled by direct- and indirect-pathway striatal projection neurons (dSPNs and iSPNs, respectively). The basal ganglia thalamic output sculpts cortical activity by interacting with signals from sensory and motor systems. Here we describe a direct projection from the globus pallidus externus (GP), a central nucleus of the basal ganglia, to frontal regions of the cerebral cortex (FC). Two cell types make up the GP-FC projection, distinguished by their electrophysiological properties, cortical projections and expression of choline acetyltransferase (ChAT), a synthetic enzyme for the neurotransmitter acetylcholine (ACh). Despite these differences, ChAT(+) cells, which have been historically identified as an extension of the nucleus basalis, as well as ChAT(-) cells, release the inhibitory neurotransmitter GABA (γ-aminobutyric acid) and are inhibited by iSPNs and dSPNs of dorsal striatum. Thus, GP-FC cells comprise a direct GABAergic/cholinergic projection under the control of striatum that activates frontal cortex in vivo. Furthermore, iSPN inhibition of GP-FC cells is sensitive to dopamine 2 receptor signalling, revealing a pathway by which drugs that target dopamine receptors for the treatment of neuropsychiatric disorders can act in the basal ganglia to modulate frontal cortices.

Myosin II controls cellular branching morphogenesis and migration in three dimensions by minimizing cell-surface curvature.

In many cases, cell function is intimately linked to cell shape control. We used endothelial cell branching morphogenesis as a model to understand the role of myosin II in shape control of invasive cells migrating in 3D collagen gels. We applied principles of differential geometry and mathematical morphology to 3D image sets to parameterize cell branch structure and local cell-surface curvature. We find that Rho/ROCK-stimulated myosin II contractility minimizes cell-scale branching by recognizing and minimizing local cell-surface curvature. Using microfabrication to constrain cell shape identifies a positive feedback mechanism in which low curvature stabilizes myosin II cortical association, where it acts to maintain minimal curvature. The feedback between regulation of myosin II by curvature and control of curvature by myosin II drives cycles of localized cortical myosin II assembly and disassembly. These cycles in turn mediate alternating phases of directionally biased branch initiation and retraction to guide 3D cell migration.

Fluctuation analysis of activity biosensor images for the study of information flow in signaling pathways.

Comprehensive understanding of cellular signal transduction requires accurate measurement of the information flow in molecular pathways. In the past, information flow has been inferred primarily from genetic or protein-protein interactions. Although useful for overall signaling, these approaches are limited in that they typically average over populations of cells. Single-cell data of signaling states are emerging, but these data are usually snapshots of a particular time point or limited to averaging over a whole cell. However, many signaling pathways are activated only transiently in specific subcellular regions. Protein activity biosensors allow measurement of the spatiotemporal activation of signaling molecules in living cells. These data contain highly complex, dynamic information that can be parsed out in time and space and compared with other signaling events as well as changes in cell structure and morphology. We describe in this chapter the use of computational tools to correct, extract, and process information from time-lapse images of biosensors. These computational tools allow one to explore the biosensor signals in a multiplexed approach in order to reconstruct the sequence of signaling events and consequently the topology of the underlying pathway. The extraction of this information, dynamics and topology, provides insight into how the inputs of a signaling network are translated into its biochemical or mechanical outputs.

Lawn soil carbon storage in abandoned residential properties: an examination of ecosystem structure and function following partial human-natural decoupling.

Residential abandonment is on the rise in many urban areas, with unknown implications for ecosystem structure and function on land slated for partial or full restoration to native habitat. Partial decoupling of human and natural systems could reduce disturbance (e.g., trampling, recreational traffic) and modify vegetation structure in a way that alters soil carbon storage, an ecosystem function that many municipalities consider a management objective of growing importance. We quantified soil carbon percent and mass to 10 cm depth and examined vegetation structure in 50 vacant and 10 occupied residential lawns located in Richmond, VA, with the principal objective of determining whether occupancy status alters trajectories of soil carbon storage or its correspondence with household economic/demographic indicators and vegetation cover. Abandoned residential lawns supported significantly less grass cover, but these declines were largely offset by increases in emergent overstory (>1 m height) vegetation cover. Soil carbon percent and mass did not differ between lawns of occupied and abandoned residences, even though significant, but highly uncertain, increases in soil carbon mass occurred in the first decade following vacancy. Instead, all residential lawns exhibited similar significant increases in soil carbon percent and mass with increasing residence age and neighborhood affluence, the former indicating annual carbon accretion rates of 20 g m(-2). We conclude that in this early stage of vacancy, soil carbon storage is already subtly responding to declines in human intervention, with reduced soil disturbance and sustained vegetation cover in abandoned lawns playing likely roles in emerging soil carbon storage trajectories.

Imaging the coordination of multiple signalling activities in living cells.

Cellular signal transduction occurs in complex and redundant interaction networks, which are best understood by simultaneously monitoring the activation dynamics of multiple components. Recent advances in biosensor technology have made it possible to visualize and quantify the activation of multiple network nodes in the same living cell. The precision and scope of this approach has been greatly extended by novel computational approaches (referred to as computational multiplexing) that can reveal relationships between network nodes imaged in separate cells.

ERK-MAPK drives lamellipodia protrusion by activating the WAVE2 regulatory complex.

Cell movement begins with a leading edge protrusion, which is stabilized by nascent adhesions and retracted by mature adhesions. The ERK-MAPK (extracellular signal-regulated kinase-mitogen-activated protein kinase) localizes to protrusions and adhesions, but how it regulates motility is not understood. We demonstrate that ERK controls protrusion initiation and protrusion speed. Lamellipodial protrusions are generated via the WRC (WAVE2 regulatory complex), which activates the Arp2/3 actin nucleator for actin assembly. The WRC must be phosphorylated to be activated, but the sites and kinases that regulate its intermolecular changes and membrane recruitment are unknown. We show that ERK colocalizes with the WRC at lamellipodial leading edges and directly phosphorylates two WRC components: WAVE2 and Abi1. The phosphorylations are required for functional WRC interaction with Arp2/3 and actin during cell protrusion. Thus, ERK coordinates adhesion disassembly with WRC activation and actin polymerization to promote productive leading edge advancement during cell migration.