Establishment and application of a surrogate model for human Ebola virus disease in BSL-2 laboratory

The Ebola virus (EBOV) is a member of the Orthoebolavirus genus, Filoviridae family, which causes severe hemorrhagic diseases in humans and non-human primates (NHPs), with a case fatality rate of up to 90%. The development of countermeasures against EBOV has been hindered by the lack of ideal animal models, as EBOV requires handling in biosafety level (BSL)-4 facilities. Therefore, accessible and convenient animal models are urgently needed to promote prophylactic and therapeutic approaches against EBOV. In this study, a recombinant vesicular stomatitis virus expressing Ebola virus glycoprotein (VSV-EBOV/GP) was constructed and applied as a surrogate virus, establishing a lethal infection in hamsters. Following infection with VSV-EBOV/GP, 3-week-old female Syrian hamsters exhibited disease signs such as weight loss, multi-organ failure, severe uveitis, high viral loads, and developed severe systemic diseases similar to those observed in human EBOV patients. All animals succumbed at 2-3 days post-infection (dpi). Histopathological changes indicated that VSV-EBOV/GP targeted liver cells, suggesting that the tissue tropism of VSV-EBOV/GP was comparable to wild-type EBOV (WT EBOV). Notably, the pathogenicity of the VSV-EBOV/GP was found to be species-specific, age-related, gender-associated, and challenge route-dependent. Subsequently, equine anti-EBOV immunoglobulins and a subunit vaccine were validated using this model. Overall, this surrogate model represents a safe, effective, and economical tool for rapid preclinical evaluation of medical countermeasures against EBOV under BSL-2 conditions, which would accelerate technological advances and breakthroughs in confronting Ebola virus disease.

state-of-the-art machine learning models

Hydrodynamic models can accurately simulate flood inundation but are limited by their high computational demand that scales non-linearly with model complexity, resolution, and domain size. Therefore, it is often not feasible to use high-resolution hydrodynamic models for real-time flood predictions or when a large number of predictions are needed for probabilistic flood design. Computationally efficient surrogate models have been developed to address this issue. The recently developed Low-fidelity, Spatial analysis, and Gaussian Process Learning (LSG) model has shown strong performance in both computational efficiency and simulation accuracy. The LSG model is a physics-guided surrogate model that simulates flood inundation by first using an extremely coarse and simplified (i.e. low-fidelity) hydrodynamic model to provide an initial estimate of flood inundation. Then, the low-fidelity estimate is upskilled via Empirical Orthogonal Functions (EOF) analysis and Sparse Gaussian Process models to provide accurate high-resolution predictions. Despite the promising results achieved thus far, the LSG model has not been benchmarked against other surrogate models. Such a comparison is needed to fully understand the value of the LSG model and to provide guidance for future research efforts in flood inundation simulation. This study compares the LSG model to four state-of-the-art surrogate flood inundation models. The surrogate models are assessed for their ability to simulate the temporal and spatial evolution of flood inundation for events both within and beyond the range used for model training. The models are evaluated for three distinct case studies in Australia and the United Kingdom. The LSG model is found to be superior in accuracy for both flood extent and water depth, including when applied to flood events outside the range of training data used, while achieving high computational efficiency. In addition, the low-fidelity model is found to play a crucial role in achieving the overall superior performance of the LSG model.

Site-scale groundwater pollution risk assessment using surrogate models and statistical analysis

Petroleum pollution in soil and groundwater has emerged as a significant environmental concern worldwide. As a sustainable and cost-effective in-situ remediation technique, Monitored Natural Attenuation (MNA) exhibits significant promise in addressing sites contaminated by petrochemicals. This study specifically targets a typical petrochemical-contaminated site in northern China and employs GMS software to establish a comprehensive physical model. The model relies on time-series monitoring data of phenol concentrations spanning from 2018 to 2020, effectively simulating both the leakage and natural attenuation of phenol. Within this study, the adsorption coefficient and maximum adsorption capacity emerge as the foremost influential factors shaping the outcomes of the model. Given the inherent heterogeneity of the site and the variability of hydrochemical conditions, parameters such as dispersion, porosity, and adsorption coefficient exhibit significant uncertainties. Consequently, relying on traditional deterministic models to predict the feasibility of MNA technology is not reliable. Therefore, this study employs machine learning (ML) methods to construct stochastic parameter models based on physical processes. The Random Forest Regression (RFR) algorithm, after trained, demonstrates strong alignment with numerical model output, exhibiting an average Nash-Sutcliffe Efficiency (NSE) >0.96. Using a stochastic approach, RFR iteratively computes phenol concentration across 6000 sets of parameters. Applying probability statistics, the model shows a notable reduction in the likelihood of phenol concentrations exceeding a threshold, dropping from 64.0% to 15.7% before and after natural attenuation. In parameter uncertainty, the stochastic model emphasizes natural attenuation's efficacy in mitigating phenol pollution risk (porosity being the most influential factor). This case study proposed a novel method to quickly assess the pollution risks at petrochemical sites under the influence of the uncertainty of pollutant transport and reaction parameters. The results can provide a reference for the pollution risk assessment at petrochemical sites, especially in sites with high stratigraphic heterogeneity or insufficient transport parameter data.

Design space determination of pharmaceutical processes: Effects of control strategies and uncertainty

The identification of process Design Space (DS) is of high interest in highly regulated industrial sectors, such as pharmaceutical industry, where assurance of manufacturability and product quality is key for process development and decision-making. If the process can be controlled by a set of manipulated variables, the DS can be expanded in comparison to an open-loop scenario, where there are no controls in place. Determining the benefits of control strategies may be challenging, particularly when the available model is complex and computationally expensive - which is typically the case of pharmaceutical manufacturing. In this study, we exploit surrogate-based feasibility analysis to determine whether the process satisfies all process constraints by manipulating the process inputs and reduce the effect of uncertainty. The proposed approach is successfully tested on two simulated pharmaceutical case studies of increasing complexity, i.e., considering (i) a single pharmaceutical unit operation, and (ii) a pharmaceutical manufacturing line comprised of a sequence of connected unit operations. Results demonstrate that different control actions can be effectively exploited to operate the process in a wider range of inputs and mitigate uncertainty.

Integrating artificial intelligence, machine learning, and deep learning approaches into remediation of contaminated sites: A review

The growing number of contaminated sites across the world pose a considerable threat to the environment and human health. Remediating such sites is a cumbersome process with the complexity originating from the need for extensive sampling and testing during site characterization. Selection and design of remediation technology is further complicated by the uncertainties surrounding contaminant attributes, concentration, as well as soil and groundwater properties, which influence the remediation efficiency. Additionally, challenges emerge in identifying contamination sources and monitoring the affected area. Often, these problems are overly simplified, and the data gathered is underutilized rendering the remediation process inefficient. The potential of artificial intelligence (AI), machine-learning (ML), and deep-learning (DL) to address these issues is noteworthy, as their emergence revolutionized the process of data management/analysis. Researchers across the world are increasingly leveraging AI/ML/DL to address remediation challenges. Current study aims to perform a comprehensive literature review on the integration of AI/ML/DL tools into contaminated site remediation. A brief introduction to various emerging and existing AI/ML/DL technologies is presented, followed by a comprehensive literature review. In essence, ML/DL based predictive models can facilitate a thorough understanding of contamination patterns, reducing the need for extensive soil and groundwater sampling. Additionally, AI/ML/DL algorithms can play a pivotal role in identifying optimal remediation strategies by analyzing historical data, simulating scenarios through surrogate models, parameter-optimization using nature inspired algorithms, and enhancing decision-making with AI-based tools. Overall, with supportive measures like open-data policies and data integration, AI/ML/DL possess the potential to revolutionize the practice of contaminated site remediation.

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN models on HPC systems to predict material properties of millions of molecules. We use HydraGNN, our in-house library for large-scale GCNN training, leveraging distributed data parallelism in PyTorch. We use ADIOS, a high-performance data management framework for efficient storage and reading of large molecular graph data. We perform parallel training on two open-source large-scale graph datasets to build a GCNN predictor for an important quantum property known as the HOMO-LUMO gap. We measure the scalability, accuracy, and convergence of our approach on two DOE supercomputers: the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF) and the Perlmutter system at the National Energy Research Scientific Computing Center (NERSC). We present our experimental results with HydraGNN showing (i) reduction of data loading time up to 4.2 times compared with a conventional method and (ii) linear scaling performance for training up to 1024 GPUs on both Summit and Perlmutter.

Enabling probabilistic retrospective transport modeling for accurate source detection

Predicting source or background radionuclide emissions is limited by the effort needed to run gas/aerosol atmospheric transport models (ATMs). A high-performance surrogate model is developed for the HYSPLIT4 (NOAA) ATM to accelerate transport simulation through model reduction, code optimization, and improved scaling on high performance computing systems. The surrogate model parameters are a grid of short-duration transport simulations stored offline. The surrogate model then predicts the path of a plume of radionuclide particles emitted from a source, or the field of sources which may have contributed to a detected signal, more efficiently than direct simulation by HYSPLIT4. Termed the Atmospheric Transport Model Surrogate (ATaMS), this suite of capabilities forms a basis to accelerate workflows for probabilistic source prediction and estimation of the radionuclide atmospheric background.

Surrogate-based follow-up of activated carbon adsorption preceded by ozonation for removal of bulk organics and micropollutants from landfill leachate

Although combined ozonation with activated carbon (AC) adsorption is a promising technique for leachate treatment, little is known about how ozone-induced changes in leachate characteristics affect the organics adsorption, especially in view of emerging micropollutants (MPs) removal. Furthermore, the online monitoring of MPs is challenging but desirable for efficient treatment operation. This study investigates how preceding ozonation impacts the adsorption of bulk organics (expressed as chemical oxygen demand (COD)) and ozone-recalcitrant MPs, i.e., primidone, atrazine and alachlor, in leachate using batch and column adsorption tests. Additionally, a new surrogate-based model was evaluated for predicting MPs breakthrough. Batch tests revealed that ozonation results in a decreasing apparent affinity of COD towards AC, but the non-adsorbable part did not obviously change. The adsorption of MPs in ozonated leachate was (1-41%) higher than that in non-ozonated leachate, especially for the more hydrophobic alachlor and atrazine, due to a reduced sites competition from bulk organics. Column adsorption showed that ozonation delayed COD and MPs breakthrough due to the reduced COD loading and sites competition, respectively. An increased empty bed contact time (EBCT, 10-40 min) led to an increased COD uptake by a factor of 3.0-3.2 for ozonated and non-ozonated leachates, while MPs adsorption also increased, suggesting that pore blockage rather than site competition could be the dominant inhibitory effect. The data from column adsorption demonstrate the applicability of developed surrogate-based model for predicting MPs breakthrough. Particularly, the fitting parameters were not affected by change of leachate characteristics, while they were impacted by change of EBCT.

Mouse avatars of human cancers: the temporality of translation in precision oncology

Patient-derived xenografts (PDXs) are currently promoted as new translational models in precision oncology. PDXs are immunodeficient mice with human tumors that are used as surrogate models to represent specific types of cancer. By accounting for the genetic heterogeneity of cancer tumors, PDXs are hoped to provide more clinically relevant results in preclinical research. Further, in the function of so-called "mouse avatars", PDXs are hoped to allow for patient-specific drug testing in real-time (in parallel to treatment of the corresponding cancer patient). This paper examines the circulation of knowledge and bodily material across the species boundary of human and personalized mouse model, historically as well as in contemporary practices. PDXs raise interesting questions about the relation between animal model and human patient, and about the capacity of hybrid or interspecies models to close existing translational gaps. We highlight that the translational potential of PDXs not only depends on representational matching of model and target, but also on temporal alignment between model development and practical uses. Aside from the importance of ensuring temporal stability of human tumors in a murine body, the mouse avatar concept rests on the possibility of aligning the temporal horizons of the clinic and the lab. We examine strategies to address temporal challenges, including cryopreservation and biobanking, as well as attempts to speed up translation through modification and use of faster developing organisms. We discuss how featured model virtues change with precision oncology, and contend that temporality is a model feature that deserves more philosophical attention.

A simulation-based approach to assess the power of trend detection in high- and low-frequency water quality records

To provide more precise understanding of water quality changes, continuous sampling is being used more in surface water quality monitoring networks. However, it remains unclear how much improvement continuous monitoring provides over spot sampling, in identifying water quality changes over time. This study aims (1) to assess our ability to detect trends using water quality data of both high and low frequencies and (2) to assess the value of using high-frequency data as a surrogate to help detect trends in other constituents. Statistical regression models were used to identify temporal trends and then to assess the trend detection power of high-frequency (15 min) and low-frequency (monthly) data for turbidity and electrical conductivity (EC) data collected across Victoria, Australia. In addition, we developed surrogate models to simulate five sediment and nutrients constituents from runoff, turbidity and EC. A simulation-based statistical approach was then used to the compare the power to detect trends between the low- and high-frequency water quality records. Results show that high-frequency sampling shows clear benefits in trend detection power for turbidity, EC, as well as simulated sediment and nutrients, especially over short data periods. For detecting a 1% annual trend with 5 years of data, up to 97% and 94% improvements on the trend detection probability are offered by high-frequency data compared with monthly data, for turbidity and EC, respectively. Our results highlight the benefits of upgrading monitoring networks with wider application of high-frequency sampling.

Sensitivity analysis in digital pathology: Handling large number of parameters with compute expensive workflows

Digital pathology imaging enables valuable quantitative characterizations of tissue state at the sub-cellular level. While there is a growing set of methods for analysis of whole slide tissue images, many of them are sensitive to changes in input parameters. Evaluating how analysis results are affected by variations in input parameters is important for the development of robust methods. Executing algorithm sensitivity analyses by systematically varying input parameters is an expensive task because a single evaluation run with a moderate number of tissue images may take hours or days. Our work investigates the use of Surrogate Models (SMs) along with parallel execution to speed up parameter sensitivity analysis (SA). This approach significantly reduces the SA cost, because the SM execution is inexpensive. The evaluation of several SM strategies with two image segmentation workflows demonstrates that a SA study with SMs attains results close to a SA with real application runs (mean absolute error lower than 0.022), while the SM accelerates the SA execution by 51 × . We also show that, although the number of parameters in the example workflows is high, most of the uncertainty can be associated with a few parameters. In order to identify the impact of variations in segmentation results to downstream analyses, we carried out a survival analysis with 387 Lung Squamous Cell Carcinoma cases. This analysis was repeated using 3 values for the most significant parameters identified by the SA for the two segmentation algorithms; about 600 million cell nuclei were segmented per run. The results show that significance of the survival correlations of patient groups, assessed by a logrank test, are strongly affected by the segmentation parameter changes. This indicates that sensitivity analysis is an important tool for evaluating the stability of conclusions from image analyses.

Global optimization of distillation columns using surrogate models

Surrogate-based optimization of distillation columns using an iterative Kriging approach is investigated. Focus is on deterministic global optimization to avoid suboptimal local minima. The determination of optimal setups and operating conditions for ideal and non-ideal distillation columns, leading to mixed-integer nonlinear programming problems, serve as case studies. It is found that the optimization using the adapted Kriging approach yields similar results compared to the direct global optimization of the original problem in the ideal case, while it leads to a huge improvement compared to a multistart local optimization approach in the non-ideal case.

Adding spatial flexibility to source-receptor relationships for air quality modeling

To cope with computing power limitations, air quality models that are used in integrated assessment applications are generally approximated by simpler expressions referred to as "source-receptor relationships (SRR)". In addition to speed, it is desirable for the SRR also to be spatially flexible (application over a wide range of situations) and to require a "light setup" (based on a limited number of full Air Quality Models - AQM simulations). But "speed", "flexibility" and "light setup" do not naturally come together and a good compromise must be ensured that preserves "accuracy", i.e. a good comparability between SRR results and AQM. In this work we further develop a SRR methodology to better capture spatial flexibility. The updated methodology is based on a cell-to-cell relationship, in which a bell-shape function links emissions to concentrations. Maintaining a cell-to-cell relationship is shown to be the key element needed to ensure spatial flexibility, while at the same time the proposed approach to link emissions and concentrations guarantees a "light set-up" phase. Validation has been repeated on different areas and domain sizes (countries, regions, province throughout Europe) for precursors reduced independently or contemporarily. All runs showed a bias around 10% between the full AQM and the SRR. This methodology allows assessing the impact on air quality of emission scenarios applied over any given area in Europe (regions, set of regions, countries), provided that a limited number of AQM simulations are performed for training.

Prediction of contact mechanics in metal-on-metal Total Hip Replacement for parametrically comprehensive designs and loads

Manufacturers and investigators of Total Hip Replacement (THR) bearings require tools to predict the contact mechanics resulting from diverse design and loading parameters. This study provides contact mechanics solutions for metal-on-metal (MoM) bearings that encompass the current design space and could aid pre-clinical design optimization and evaluation. Stochastic finite element (FE) simulation was used to calculate the head-on-cup contact mechanics for five thousand combinations of design and loading parameters. FE results were used to train a Random Forest (RF) surrogate model to rapidly predict the contact patch dimensions, contact area, pressures and plastic deformations for arbitrary designs and loading. In addition to widely observed polar and edge contact, FE results included ring-polar, asymmetric-polar, and transitional categories which have previously received limited attention. Combinations of design and load parameters associated with each contact category were identified. Polar contact pressures were predicted in the range of 0-200 MPa with no permanent deformation. Edge loading (with subluxation) was associated with pressures greater than 500 MPa and induced permanent deformation in 83% of cases. Transitional-edge contact (with little subluxation) was associated with intermediate pressures and permanent deformation in most cases, indicating that, even with ideal anatomical alignment, bearings may face extreme wear challenges. Surrogate models were able to accurately predict contact mechanics 18,000 times faster than FE analyses. The developed surrogate models enable rapid prediction of MoM bearing contact mechanics across the most comprehensive range of loading and designs to date, and may be useful to those performing bearing design optimization or evaluation.

Central origin of pinprick hyperalgesia adjacent to an UV-B induced inflammatory skin pain model in healthy volunteers

Background and purpose The UV-B model is an established pain model of different types of hyperalgesia in animal and human pain research. Beside the skin region of the sunburn in human volunteers pinprick hyperalgesia has been described in a large zone of non-inflamed skin adjacent to the sunburn. However, there are opposing results on the existence of pinprick hyperalgesia and most notably a controversial discussion is still on-going whether this mechanical hyperalgesia in the undamaged tissue adjacent to and at some distance from the site of inflammation is of peripheral or central origin. We therefore addressed this in our study by hypothesising that pinprick hyperalgesia around a circular spot of UV-B inflamed skin is not reduced by a superficial local anaesthetic block and therefore underlies centrally mediated mechanisms. Methods This exploratory study was conducted in a prospective, controlled, randomised, single-blinded fashion in relation to the study hypothesis in 12 healthy volunteers. Before circular irradiation with UV-B light (3-times the individual minimal erythema dose at both thighs), a strip of continuous intradermal local anaesthetic block with lidocaine 2% was established via two single plasmaphoresis hollow fibres. These were positioned perpendicular to one thigh overlapping on the midline of the leg at the distal part of the planned irradiation site, and compared with the contralateral control side without anaesthetic block. The local anaesthetic block was established and then maintained via a syringe pump. The area of pinprick hyperalgesia was measured by pricking on a large skin surface including 360° around the circular irradiation site. This was done with a slightly painful pin (256 mN) until 8h after irradiation. Primary outcome was the area of pinprick hyperalgesia in the skin adjacent to the sunburn at 8h. Results Large areas of mechanical hyperalgesia to pinprick surrounding the adjacent skin of the sunburn developed on both sides after 8h without any significant difference between the side of the anaesthetic strip showing an area of 72.6±39.7 cm2 (mean±SD) and the control side (59.1±20.1 cm2); p = 0.24. Moreover, mechanical hyperalgesia to various pin stimuli of different strength was unchanged by the anaesthetic block. Conclusion This trial provides evidence that the development of mechanical hyperalgesia surrounding an experimental sunburn was not influenced by continuous peripheral afferent blockade with local anaesthetic at 8h after UV-B irradiation. Our data support the hypothesis that in the UV-B model peripheral nociceptive afferent input of inflamed skin may enhance central hypersensitivity of mechanosensitive nociceptors in a larger receptive field far beyond the inflamed skin. Furthermore, these findings are in line with other pain models demonstrating comparable central hypersensitivity around the site of injury. Implications As for other pain models this finding provides further evidence that the UV-B model offers secondary mechanical hyperalgesia in addition to its known primary hyperalgesia. Consequently, this is a further validation for the utilisation of the UV-B model in human pain research.