Aqueous film-forming foams (AFFFs) are complex product mixtures that often contain per- and polyfluorinated alkyl substances (PFAS) to enhance fire suppression and protect firefighters. However, PFAS have been associated with a range of adverse health effects (e.g., liver and thyroid disease and cancer), and innovative approach methods to better understand their toxicity potential and identify safer alternatives are needed. In this study, we investigated a set of 30 substances (e.g., AFFF, PFAS, and clinical drugs) using differentiated cultures of human hepatocytes (HepaRG, 2D), high-throughput transcriptomics, deep learning of cell morphology images, and liver enzyme leakage assays with benchmark dose analysis to (1) predict the potency ranges for human liver injury, (2) delineate gene- and pathway-level transcriptomic points-of-departure for molecular hazard characterization and prioritization, (3) characterize human hepatocellular response similarities to inform regulatory read-across efforts, and (4) introduce an innovative approach to translate mechanistic hepatocellular response data to predict the potency ranges for PFAS-induced hepatomegaly in vivo. Collectively, these data fill important mechanistic knowledge gaps with PFAS/AFFF and represent a scalable platform to address the thousands of PFAS in commerce for greener chemistries and next-generation risk assessments.

Screening chemicals using the zebrafish embryo developmental toxicity assay requires visual assessment of larval morphological changes based on images by experienced screeners. The process is time-consuming and prone to subjectivity. However, deep learning models trained using labeled image data offer a more objective and efficient alternative. As part of the Systematic Evaluation of the Application of Zebrafish in Toxicology (SEAZIT) project, which aims to provide a scientific basis for programmatic decisions on the routine use of zebrafish in toxicological evaluations, we developed deep-learning classification and segmentation models to support image-based assessments. Using labeled SEAZIT image data from embryos exposed to various chemicals for 5 days, we trained classification models to detect 20 distinct types of larval morphological changes. We also developed segmentation models to identify and measure larval regions of interest. In a baseline binary classification task distinguishing normal embryos from those with any morphological change, our multi-view convolutional neural network (MVCNN) achieved an F1 score of 0.88, demonstrating strong overall performance. Among classifiers for specific morphological changes, eight achieved F1 scores above 0.70. Grouping related abnormalities further improved performance, with five out of seven grouped classifiers reaching F1 scores near 0.80. Segmentation models for most of the regions of interest (9 out of 11) have an Intersection over Union (IoU) score of at least 0.80. Together, these models facilitate rapid, standardized and reliable evaluation of larval morphological changes in zebrafish images, reducing the need for subjective manual review and enhancing reproducibility in development toxicity screening.

High-throughput chemical screening approaches often employ microscopy to capture photomicrographs from multi-well cell culture plates, generating thousands of images that require time-consuming human analysis. To automate this subjective and time-consuming manual process, we have developed a method that uses deep learning to automatically classify digital assay images. We have trained a convolutional neural network (CNN) to perform binary and multi-class classification. The binary classifier binned assay images into healthy (comparable to untreated controls) and altered (not comparable to untreated-control) classes with >98% accuracy; the multi-class classifier assigned "Healthy," "Intermediate" and "Altered" labels to assay images with >95% accuracy. Our dataset comprised high-resolution assay images from primary human hepatocytes and undifferentiated (proliferating) and differentiated 2D cultures of HepaRG cells. In this study we have focused on testing and fine-tuning various CNN architectures, including ResNet 34, 50 and 101. To visualize regions in the images that the CNN model used for classification, we employed Class Activation Maps (CAM). This allowed us to better understand the inner workings of the neural network and led to additional optimizations of the algorithm. The results indicate a strong correspondence between dosage and classifier-predicted scores, suggesting that these scores might be useful in further characterizing benchmark dose. Together, these results clearly demonstrate that deep-learning based automated image classification of cell morphology changes upon chemical-induced stress can yield highly accurate and reproducible assessments of cytotoxicity across a variety of cell types.

Background: Given the worldwide spread of the 2019 Novel Coronavirus (COVID-19), there is an urgent need to identify risk and protective factors and expose areas of insufficient understanding. Emerging tools, such as the Rapid Evidence Map (rEM), are being developed to systematically characterize large collections of scientific literature. We sought to generate an rEM of risk and protective factors to comprehensively inform areas that impact COVID-19 outcomes for different sub-populations in order to better protect the public. Methods: We developed a protocol that includes a study goal, study questions, a PECO statement, and a process for screening literature by combining semi-automated machine learning with the expertise of our review team. We applied this protocol to reports within the COVID-19 Open Research Dataset (CORD-19) that were published in early 2020. SWIFT-Active Screener was used to prioritize records according to pre-defined inclusion criteria. Relevant studies were categorized by risk and protective status; susceptibility category (Behavioral, Physiological, Demographic, and Environmental); and affected sub-populations. Using tagged studies, we created an rEM for COVID-19 susceptibility that reveals: (1) current lines of evidence; (2) knowledge gaps; and (3) areas that may benefit from systematic review. Results: We imported 4,330 titles and abstracts from CORD-19. After screening 3,521 of these to achieve 99% estimated recall, 217 relevant studies were identified. Most included studies concerned the impact of underlying comorbidities (Physiological); age and gender (Demographic); and social factors (Environmental) on COVID-19 outcomes. Among the relevant studies, older males with comorbidities were commonly reported to have the poorest outcomes. We noted a paucity of COVID-19 studies among children and susceptible sub-groups, including pregnant women, racial minorities, refugees/migrants, and healthcare workers, with few studies examining protective factors. Conclusion: Using rEM analysis, we synthesized the recent body of evidence related to COVID-19 risk and protective factors. The results provide a comprehensive tool for rapidly elucidating COVID-19 susceptibility patterns and identifying resource-rich/resource-poor areas of research that may benefit from future investigation as the pandemic evolves.

BACKGROUND:In the screening phase of systematic review, researchers use detailed inclusion/exclusion criteria to decide whether each article in a set of candidate articles is relevant to the research question under consideration. A typical review may require screening thousands or tens of thousands of articles in and can utilize hundreds of person-hours of labor.METHODS:Here we introduce SWIFT-Active Screener, a web-based, collaborative systematic review software application, designed to reduce the overall screening burden required during this resource-intensive phase of the review process. To prioritize articles for review, SWIFT-Active Screener uses active learning, a type of machine learning that incorporates user feedback during screening. Meanwhile, a negative binomial model is employed to estimate the number of relevant articles remaining in the unscreened document list. Using a simulation involving 26 diverse systematic review datasets that were previously screened by reviewers, we evaluated both the document prioritization and recall estimation methods.RESULTS:On average, 95% of the relevant articles were identified after screening only 40% of the total reference list. In the 5 document sets with 5,000 or more references, 95% recall was achieved after screening only 34% of the available references, on average. Furthermore, the recall estimator we have proposed provides a useful, conservative estimate of the percentage of relevant documents identified during the screening process.CONCLUSION:SWIFT-Active Screener can result in significant time savings compared to traditional screening and the savings are increased for larger project sizes. Moreover, the integration of explicit recall estimation during screening solves an important challenge faced by all machine learning systems for document screening: when to stop screening a prioritized reference list. The software is currently available in the form of a multi-user, collaborative, online web application.

Moving toward species-relevant chemical safety assessments and away from animal testing requires access to reliable data to develop and build confidence in new approaches. The Integrated Chemical Environment (ICE) provides tools and curated data centered around chemical safety assessment. This article describes updates to ICE, including improved accessibility and interpretability of in vitro data via mechanistic target mapping and enhanced interactive tools for in vitro to in vivo extrapolation (IVIVE). Mapping of in vitro assay targets to toxicity endpoints of regulatory importance uses literature-based mode-of-action information and controlled terminology from existing knowledge organization systems to support data interoperability with external resources. The most recent ICE update includes Tox21 high-throughput screening data curated using analytical chemistry data and assay-specific parameters to eliminate potential artifacts or unreliable activity. Also included are physicochemical/ADME parameters for over 800,000 chemicals predicted by quantitative structure-activity relationship models. These parameters are used by the new ICE IVIVE tool in combination with the U.S. Environmental Protection Agency's httk R package to estimate in vivo exposures corresponding to in vitro bioactivity concentrations from stored or user-defined assay data. These new ICE features allow users to explore the applications of an expanded data space and facilitate building confidence in non-animal approaches.

SUMMARY A new version (version 2) of the genomic dose-response analysis software, BMDExpress, has been created. The software addresses the increasing use of transcriptomic dose-response data in toxicology, drug design, risk assessment and translational research. In this new version, we have implemented additional statistical filtering options (e.g. Williams' trend test), curve fitting models, Linux and Macintosh compatibility and support for additional transcriptomic platforms with up-to-date gene annotations. Furthermore, we have implemented extensive data visualizations, on-the-fly data filtering, and a batch-wise analysis workflow. We have also significantly re-engineered the code base to reflect contemporary software engineering practices and streamline future development. The first version of BMDExpress was developed in 2007 to meet an unmet demand for easy-to-use transcriptomic dose-response analysis software. Since its original release, however, transcriptomic platforms, technologies, pathway annotations and quantitative methods for data analysis have undergone a large change necessitating a significant re-development of BMDExpress. To that end, as of 2016, the National Toxicology Program assumed stewardship of BMDExpress. The result is a modernized and updated BMDExpress 2 that addresses the needs of the growing toxicogenomics user community. AVAILABILITY AND IMPLEMENTATION BMDExpress 2 is available at https://github.com/auerbachs/BMDExpress-2/releases. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.

Lymphatic vasculature is an important part of the cardiovascular system with multiple functions, including regulation of the return of interstitial fluid ( lymph) to the bloodstream, immune responses, and fat absorption. Consequently, lymphatic vasculature defects are involved in many pathological processes, including tumor metastasis and lymphedema. BRG1 is an important player in the developmental window when the lymphatic system is initiated. In the current study, we used tamoxifen inducible Rosa26CreERT2-BRG1(floxed/floxed) mice that allowed temporal analysis of the impact of BRG1 inactivation in the embryo. The BRG1(floxed/floxed/Cre-TM) embryos exhibited edema and hemorrhage at embryonic day-13 and began to die. BRG1 deficient embryos had abnormal lymphatic sac linings with fewer LYVE1 positive lymphatic endothelial cells. Indeed, loss of BRG1 attenuated expression of a subset of lymphatic genes in-vivo. Furthermore, BRG1 binds at the promoters of COUP-TFII and LYVE1, suggesting that BRG1 modulates expression of these genes in the developing embryos. Conversely, re-expression of BRG1 in cells lacking endogenous BRG1 resulted in induction of lymphatic gene expression in-vitro, suggesting that BRG1 was both required and sufficient for lymphatic gene expression. These studies provide important insights into intrinsic regulation of BRG1-mediated lymphatic-gene expression, and further an understanding of lymphatic gene dysregulation in lymphedema and other disease conditions.

SUMMARY: Access to high-quality reference data is essential for the development, validation, and implementation of in vitro and in silico approaches that reduce and replace the use of animals in toxicity testing. Currently, these data must often be pooled from a variety of disparate sources to efficiently link a set of assay responses and model predictions to an outcome or hazard classification. To provide a central access point for these purposes, the National Toxicology Program Interagency Center for the Evaluation of Alternative Toxicological Methods developed the Integrated Chemical Environment (ICE) web resource. The ICE data integrator allows users to retrieve and combine data sets and to develop hypotheses through data exploration. Open-source computational workflows and models will be available for download and application to local data. ICE currently includes curated in vivo test data, reference chemical information, in vitro assay data (including Tox21TM/ToxCast™ high-throughput screening data), and in silico model predictions. Users can query these data collections focusing on end points of interest such as acute systemic toxicity, endocrine disruption, skin sensitization, and many others. ICE is publicly accessible at https://ice.ntp.niehs.nih.gov. https://doi.org/10.1289/EHP1759.

Background: There is growing interest in using machine learning approaches to priority rank studies and reduce human burden in screening literature when conducting systematic reviews. In addition, identifying addressable questions during the problem formulation phase of systematic review can be challenging, especially for topics having a large literature base. Here, we assess the performance of the SWIFT-Review priority ranking algorithm for identifying studies relevant to a given research question. We also explore the use of SWIFT-Review during problem formulation to identify, categorize, and visualize research areas that are data rich/data poor within a large literature corpus.Methods: Twenty case studies, including 15 public data sets, representing a range of complexity and size, were used to assess the priority ranking performance of SWIFT-Review. For each study, seed sets of manually annotated included and excluded titles and abstracts were used for machine training. The remaining references were then ranked for relevance using an algorithm that considers term frequency and latent Dirichlet allocation (LDA) topic modeling. This ranking was evaluated with respect to (1) the number of studies screened in order to identify 95 % of known relevant studies and (2) the "Work Saved over Sampling" (WSS) performance metric. To assess SWIFT-Review for use in problem formulation, PubMed literature search results for 171 chemicals implicated as EDCs were uploaded into SWIFT-Review (264,588 studies) and categorized based on evidence stream and health outcome. Patterns of search results were surveyed and visualized using a variety of interactive graphics.Results: Compared with the reported performance of other tools using the same datasets, the SWIFT-Review ranking procedure obtained the highest scores on 11 out of 15 of the public datasets. Overall, these results suggest that using machine learning to triage documents for screening has the potential to save, on average, more than 50 % of the screening effort ordinarily required when using un-ordered document lists. In addition, the tagging and annotation capabilities of SWIFT-Review can be useful during the activities of scoping and problem formulation.Conclusions: Text-mining and machine learning software such as SWIFT-Review can be valuable tools to reduce the human screening burden and assist in problem formulation.

SWI/SNF (switching/sucrose nonfermenting)-dependent chromatin remodeling establishes coordinated gene expression programs during development, yet important functional details remain to be elucidated. We show that the Brg1 (Brahma-related gene 1; Smarca4) ATPase is globally expressed at high levels during postimplantation development and its conditional ablation, beginning at gastrulation, results in increased apoptosis, growth retardation, and, ultimately, embryonic death. Global gene expression analysis revealed that genes upregulated in Rosa26CreERT2; Brg1(flox/flox) embryos (here referred to as Brg1(d/d) embryos to describe embryos with deletion of the Brg1(flox/flox) alleles) negatively regulate cell cycle progression and cell growth. In addition, the p53 (Trp53) protein, which is virtually undetectable in early wild-type embryos, accumulated in the Brg1(d/d) embryos and activated the p53-dependent pathways. Using P19 cells, we show that Brg1 and CHD4 (chromodomain helicase DNA binding protein 4) coordinate to control target gene expression. Both proteins physically interact and show a substantial overlap of binding sites at chromatin-accessible regions adjacent to genes differentially expressed in the Brg1(d/d) embryos. Specifically, Brg1 deficiency results in reduced levels of the repressive histone H3 lysine K27 trimethylation (H3K27me3) histone mark and an increase in the amount of open chromatin at the regulatory region of the p53 and p21 (Cdkn1a) genes. These results provide insights into the mechanisms by which Brg1 functions, which is in part via the p53 program, to constrain gene expression and facilitate rapid embryonic growth.

BACKGROUND:Interactions between the epigenome and structural genomic variation are potentially bi-directional. In one direction, structural variants may cause epigenomic changes in cis. In the other direction, specific local epigenomic states such as DNA hypomethylation associate with local genomic instability.METHODS:To study these interactions, we have developed several tools and exposed them to the scientific community using the Software-as-a-Service model via the Genboree Workbench. One key tool is Breakout, an algorithm for fast and accurate detection of structural variants from mate pair sequencing data.RESULTS:By applying Breakout and other Genboree Workbench tools we map breakpoints in breast and prostate cancer cell lines and tumors, discriminate between polymorphic breakpoints of germline origin and those of somatic origin, and analyze both types of breakpoints in the context of the Human Epigenome Atlas, ENCODE databases, and other sources of epigenomic profiles. We confirm previous findings that genomic instability in human germline associates with hypomethylation of DNA, binding sites of Suz12, a key member of the PRC2 Polycomb complex, and with PRC2-associated histone marks H3K27me3 and H3K9me3. Breakpoints in germline and in breast cancer associate with distal regulatory of active gene transcription. Breast cancer cell lines and tumors show distinct patterns of structural mutability depending on their ER, PR, or HER2 status.CONCLUSIONS:The patterns of association that we detected suggest that cell-type specific epigenomes may determine cell-type specific patterns of selective structural mutability of the genome.

BRG1, a catalytic subunit of the SWI/SNF ATPase chromatin‐remodeling complex, plays a vital role in gene regulation and tumorigenesis. Germline SWI/SNF function loss results in early embryonic lethality at approximately E3.5 in the mouse. BRG1 necessity during development beyond the pre‐implantation stage, however, has not been defined. The myriad temporal genomic changes during development require chromatin remodeling to facilitate differential gene expression. We hypothesized that BRG1 deficiency during post‐implantation development will cause gastrulation failure. Using a tamoxifen inducible conditional mouse model, we show that BRG1 ablation beginning at gastrulation results in arrested growth and early embryonic death. Mutant embryos failed to grow; histologic analysis revealed several developmental defects such as lack of normal cardiac structure and disrupted neural fold architecture. Immunohistochemistry analysis revealed aberrant expression of cell cycle and apoptosis marker proteins in BRG1 mutants. Microarray analysis revealed BRG1 ablation increased expression of cell cycle regulators, particularly within the p53 pathway. Co‐IP analyses reveal BRG1 interacts with CHD4 to suppress p53 pathways in P19 cells. These results suggest BRG1 plays a critical role in genomic surveillance essential for cell survival after the pre‐implantation period for normal cellular survival, proliferation and differentiation.Grant Funding Source: Z01 ES071006‐13

Apoptosis of lymphocytes governs the response of the immune system to environmental stress and toxic insult. Signaling through the ubiquitously expressed glucocorticoid receptor, stress-induced glucocorticoid hormones induce apoptosis via mechanisms requiring altered gene expression. Several reports have detailed the changes in gene expression mediating glucocorticoid-induced apoptosis of lymphocytes. However, few studies have examined the role of non-coding miRNAs in this essential physiological process. Previously, using hybridization-based gene expression analysis and deep sequencing of small RNAs, we described the prevalent post-transcriptional repression of annotated miRNAs during glucocorticoid-induced apoptosis of lymphocytes. Here, we describe the development of a customized bioinformatics pipeline that facilitates the deep sequencing-mediated discovery of novel glucocorticoid-responsive miRNAs in apoptotic primary lymphocytes. This analysis identifies the potential presence of over 200 novel glucocorticoid-responsive miRNAs. We have validated the expression of two novel glucocorticoid-responsive miRNAs using small RNA-specific qPCR. Furthermore, through the use of Ingenuity Pathways Analysis (IPA) we determined that the putative targets of these novel validated miRNAs are predicted to regulate cell death processes. These findings identify two and predict the presence of additional novel glucocorticoid-responsive miRNAs in the rat transcriptome, suggesting a potential role for both annotated and novel miRNAs in glucocorticoid-induced apoptosis of lymphocytes.