RESUMEN

Machine learning (ML) methods present a valuable opportunity for modeling the non-linear behavior of the injection molding process. They have the potential to predict how various process and material parameters affect the quality of the resulting parts. However, the dynamic nature of the injection molding process and the challenges associated with collecting process data remain significant obstacles for the application of ML methods. To address this, within this study, hybrid approaches are compared that combine process data with additional process knowledge, such as constitutive equations and high-fidelity numerical simulations. The hybrid modeling approaches include feature learning, fine-tuning, delta-modeling, preprocessing, and using physical constraints, as well as combinations of the individual approaches. To train and validate the hybrid models, both the experimental and simulated shrinkage data of an injection-molded part are utilized. While all hybrid approaches outperform the purely data-based model, the fine-tuning approach yields the best result in the simulation setting. The combination of calibrating a physical model (feature learning) and incorporating it implicitly into the training process (physical constraints) outperforms the other approaches in the experimental setting.

RESUMEN

Global warming poses a threat to lizard populations by raising ambient temperatures above historical norms and reducing thermoregulation opportunities. Whereas the reptile fauna of desert systems is relatively well studied, the lizard fauna of saline environments has not received much attention and-to our knowledge-thermal ecology and the effects of global warming on lizards from saline environments have not been yet addressed. This pioneer study investigates the thermal ecology, locomotor performance and potential effects of climate warming on Liolaemus ditadai, a lizard endemic to one of the largest salt flats on Earth. We sampled L. ditadai using traps and active searches along its known distribution, as well as in other areas within Salinas Grandes and Salinas de Ambargasta, where the species had not been previously recorded. Using ensemble models (GAM, MARS, RandomForest), we modeled climatically suitable habitats for L. ditadai in the present and under a pessimistic future scenario (SSP585, 2070). L. ditadai emerges as an efficient thermoregulator, tolerating temperatures near its upper thermal limits. Our ecophysiological model suggests that available activity hours predict its distribution, and the projected temperature increase due to global climate change should minimally impact its persistence or may even have a positive effect on suitable thermal habitat. However, this theoretical increase in habitat could be linked to the distribution of halophilous scrub in the future. Our surveys reveal widespread distribution along the borders of Salinas Grandes and Salinas de Ambargasta, suggesting a potential presence along the entire border of both salt plains wherever halophytic vegetation exists. Optimistic model results, extended distribution, and no evidence of flood-related adverse effects offer insights into assessing the conservation status of L. ditadai, making it and the Salinas Grandes system suitable models for studying lizard ecophysiology in largely unknown saline environments.

Asunto(s)

RESUMEN

Advances in upstream production of biologics-particularly intensified fed-batch processes beyond 10% cell solids-have severely strained harvest operations, especially depth filtration. Bioreactors containing high amounts of cell debris (more than 40% particles <10 µm in diameter) are increasingly common and drive the need for more robust depth filtration processes, while accelerated timelines emphasize the need for predictive tools to accelerate development. Both needs are constrained by the current limited mechanistic understanding of the harvest filter-feedstream system. Historically, process development relied on screening scale-down depth filter devices and conditions to define throughput before fouling, indicated by increasing differential pressure and/or particle breakthrough (measured via turbidity). This approach is straightforward, but resource-intensive, and its results are inherently limited by the variability of the feedstream. Semi-empirical models have been developed from first principles to describe various mechanisms of filter fouling, that is, pore constriction, pore blocking, and/or surface deposit. Fitting these models to experimental data can assist in identifying the dominant fouling mechanism. Still, this approach sees limited application to guide process development, as it is descriptive, not predictive. To address this gap, we developed a hybrid modeling approach. Leveraging historical bench scale filtration process data, we built a partial least squares regression model to predict particle breakthrough from filter and feedstream attributes, and leveraged the model to demonstrate prediction of filter performance a priori. The fouling models are used to interpret and provide physical meaning to these computational models. This hybrid approach-combining the mechanistic insights of fouling models and the predictive capability of computational models-was used to establish a robust platform strategy for depth filtration of Chinese hamster ovary cell cultures. As new data continues to teach the computational models, in silico tools will become an essential part of harvest process development by enabling prospective experimental design, reducing total experimental load, and accelerating development under strict timelines.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: The fetal representation as a 3D articulated body plays an essential role to describe a realistic vaginal delivery simulation. However, the current computational solutions have been oversimplified. The objective of the present work was to develop and evaluate a novel hybrid rigid-deformable modeling approach for the fetal body and then simulate its interaction with surrounding fetal soft tissues and with other maternal pelvis soft tissues during the second stage of labor. METHODS: CT scan data was used for 3D fetal skeleton reconstruction. Then, a novel hybrid rigid-deformable model of the fetal body was developed. This model was integrated into a maternal 3D pelvis model to simulate the vaginal delivery. Soft tissue deformation was simulated using our novel HyperMSM formulation. Magnetic resonance imaging during the second stage of labor was used to impose the trajectory of the fetus during the delivery. RESULTS: Our hybrid rigid-deformable fetal model showed a potential capacity for simulating the movements of the fetus along with the deformation of the fetal soft tissues during the vaginal delivery. The deformation energy density observed in the simulation for the fetal head fell within the strain range of 3 % to 5 %, which is in good agreement with the literature data. CONCLUSIONS: This study developed, for the first time, a hybrid rigid-deformation modeling of the fetal body and then performed a vaginal delivery simulation using MRI-driven kinematic data. This opens new avenues for describing more realistic behavior of the fetal body kinematics and deformation during the second stage of labor. As perspectives, the integration of the full skeleton body, especially the upper and lower limbs will be investigated. Then, the completed model will be integrated into our developed next-generation childbirth training simulator for vaginal delivery simulation and associated complication scenarios.

Asunto(s)

RESUMEN

Digitalization has paved the way for new paradigms such as digital shadows and digital twins for fermentation processes, opening the door for real-time process monitoring, control, and optimization. With a digital shadow, real-time model adaptation to accommodate complex metabolic phenomena such as metabolic shifts of a process can be monitored. Despite the many benefits of digitalization, the potential has not been fully reached in the industry. This study investigates the development of a digital shadow for a very complex fungal fermentation process in terms of microbial physiology and fermentation operation on pilot-scale at Novonesis and the challenges thereof. The process has historically been difficult to optimize and control due to a lack of offline measurements and an absence of biomass measurements. Pilot-scale and lab-scale fermentations were conducted for model development and validation. With all available pilot-scale data, a data-driven soft sensor was developed to estimate the main substrate concentration (glucose) with a normalized root mean squared error (N-RMSE) of 2%. This robust data-driven soft sensor was able to estimate accurately in lab-scale (volume < 20× pilot) with a N-RMSE of 7.8%. A hybrid soft sensor was developed by combining the data-driven soft sensor with a mass balance to estimate the glycerol and biomass concentrations on pilot-scale data with N-RMSEs of 11% and 21%, respectively. A digital shadow modeling framework was developed by coupling a mechanistic model (MM) with the hybrid soft sensor. The digital shadow modeling framework significantly improved the predictability compared with the MM. The contribution of this study brings the application of digital shadows closer to industrial implementation. It demonstrates the high potential of using this type of modeling framework for scale-up and leads the way to a new generation of in silico-based process development.

Asunto(s)

RESUMEN

The development of reliable mortality risk stratification models is an active research area in computational healthcare. Mortality risk stratification provides a standard to assist physicians in evaluating a patient's condition or prognosis objectively. Particular interest lies in methods that are transparent to clinical interpretation and that retain predictive power once validated across diverse datasets they were not trained on. This study addresses the challenge of consolidating numerous ICD codes for predictive modeling of ICU mortality, employing a hybrid modeling approach that integrates mechanistic, clinical knowledge with mathematical and machine learning models . A tree-structured network connecting independent modules that carry clinical meaning is implemented for interpretability. Our training strategy utilizes graph-theoretic methods for data analysis, aiming to identify the functions of individual black-box modules within the tree-structured network by harnessing solutions from specific max-cut problems. The trained model is then validated on external datasets from different hospitals, demonstrating successful generalization capabilities, particularly in binary-feature datasets where label assessment involves extrapolation.

Asunto(s)

RESUMEN

Microcarrier-based cell culture is a commonly used method to facilitate the growth of anchorage-dependent cells like MA 104 for antigen manufacturing. However, conventionally, static cell culture is employed for cell propagation before seeding the production bioreactor with microcarriers (MCs). This study demonstrates the effective replacement of the conventional method by serial subculturing on MCs with in situ cell detachment under optimal conditions in closed culture units. This study proves that MA 104 can be subcultured at least five times on Cytodex 1 MC without the need for separating cells and MC after cell harvest. Process parameters impacting cell growth were studied post in situ cell detachment in a scaled-down model. Optimization, using augmented Design of Experiments (DoE) combined with hybrid modeling, facilitated rapid screening of the design space for critical process parameters (CPPs). Optimized conditions included an inoculation density of >16 cells/bead, 3.5-4.5 g/L of Cytodex 1, and a controlled agitation speed, starting at Njs (minimum agitation speed) for the first day with a maximum increase of 25% thereafter. With these design spaces for CPPs, a cell density of 2.6 ± 0.5 × 106 cells/mL was achieved after five days. This refined bioprocess methodology offers a reliable and efficient approach for seed training in stirred tank reactors, which is particularly beneficial for viral vaccine production.

RESUMEN

Microalgae plays a crucial role in biomass production within aquatic environments and are increasingly recognized for their potential in generating biofuels, biomaterials, bioactive compounds, and bio-based chemicals. This growing significance is driven by the need to address imminent global challenges such as food and fuel shortages. Enhancing the value chain of bio-based products necessitates the implementation of an advanced screening and monitoring system. This system is crucial for tailoring and optimizing the cultivation conditions, ensuring the lucrative and efficient production of the final desired product. This, in turn, underscores the necessity for robust predictive models to accurately emulate algae growth in different conditions during the initial cultivation phase and simulate their subsequent processing in the downstream stage. In pursuit of these objectives, diverse mechanistic and machine learning-based methods have been independently employed to model and optimize microalgae processes. This review article thoroughly examines the techniques delineated in the literature for modeling, predicting, and monitoring microalgal biomass across various applications such as bioenergy, pharmaceuticals, and the food industry. While highlighting the merits and limitations of each method, we delve into the realm of newly emerging hybrid approaches and conduct an exhaustive survey of this evolving methodology. The challenges currently impeding the practical implementation of hybrid techniques are explored, and drawing inspiration from successful applications in other machine-learning-assisted fields, we review various plausible solutions to overcome these obstacles.

Asunto(s)

RESUMEN

Bacillus licheniformis is widely utilized in disease prevention and environmental remediation. Spore quantity is a critical factor in determining the quality of microbiological agents containing vegetative cells. To improve the understanding of Bacillus licheniformis BF-002 strain culture, a hybrid model integrating traditional dynamic modeling and recurrent neural network was developed. This model enabled the optimization of carbon/nitrogen source feeding rates, pH, temperature and agitation speed using genetic algorithms. Carbon and nitrogen source consumption in the optimal duplicate batches showed no significant difference compared to the control batch. However, the spore quantity in the broth increased by 16.2% and 35.2% in the respective duplicate batches. Overall, the hybrid model outperformed the traditional dynamic model in accurately tracking the cultivation dynamics of Bacillus licheniformis, leading to increased spore production when used for optimizing cultivation conditions.

Asunto(s)

RESUMEN

Human induced pluripotent stem (hiPS) cells have demonstrated promising potential in regenerative medical therapeutics. After successful clinical trials, the demand for hiPS cells has steadily increased. Therefore, the optimization of hiPS cell freezing processes for storage and transportation is essential. Here, we presented a computer-aided exploration of multiobjective optimal temperature profiles in slow freezing for hiPS cells. This study was based on a model that calculates cell survival rates after thawing, and the model was extended to evaluate cell potentials until 24 h after seeding. To estimate parameter values for this extension, freezing experiments were performed using constant cooling rates. Using quality and productivity indicators, we evaluated 16,206 temperature profiles using our model, and a promising profile was obtained. Finally, an experimental investigation of the profile was undertaken, and the contribution of the temperature profile to both quality and productivity was confirmed.

Asunto(s)

RESUMEN

The combination of physical equations with deep learning is becoming a promising methodology for bioprocess digitalization. In this paper, we investigate for the first time the combination of long short-term memory (LSTM) networks with first principles equations in a hybrid workflow to describe human embryonic kidney 293 (HEK293) culture dynamics. Experimental data of 27 extracellular state variables in 20 fed-batch HEK293 cultures were collected in a parallel high throughput 250 mL cultivation system in an industrial process development setting. The adaptive moment estimation method with stochastic regularization and cross-validation were employed for deep learning. A total of 784 hybrid models with varying deep neural network architectures, depths, layers sizes and node activation functions were compared. In most scenarios, hybrid LSTM models outperformed classical hybrid Feedforward Neural Network (FFNN) models in terms of training and testing error. Hybrid LSTM models revealed to be less sensitive to data resampling than FFNN hybrid models. As disadvantages, Hybrid LSTM models are in general more complex (higher number of parameters) and have a higher computation cost than FFNN hybrid models. The hybrid model with the highest prediction accuracy consisted in a LSTM network with seven internal states connected in series with dynamic material balance equations. This hybrid model correctly predicted the dynamics of the 27 state variables (R2 = 0.93 in the test data set), including biomass, key substrates, amino acids and metabolic by-products for around 10 cultivation days.

Asunto(s)

RESUMEN

Land subsidence is a worldwide threat. In arid and semiarid lands, groundwater depletion is the main factor that induce the subsidence resulting in environmental damages and socio-economic issues. To foresee and prevent the impact of land subsidence, it is necessary to develop accurate maps of the magnitude and evolution of the subsidences. Land subsidence susceptibility maps (LSSMs) provide one of the effective tools to manage vulnerable areas and to reduce or prevent land subsidence. In this study, we used a new approach to improve decision stump classification (DSC) performance and combine it with machine learning algorithms (MLAs) of naïve Bayes tree (NBTree), J48 decision tree, alternating decision tree (ADTree), logistic model tree (LMT), and support vector machine (SVM) in land subsidence susceptibility mapping (LSSSM). We employ data from 94 subsidence locations, among which 70% were used to train learning hybrid models and the other 30% were used for validation. In addition, the models' performance was assessed by ROC-AUC, accuracy, sensitivity, specificity, odd ratio, root-mean-square error (RMSE), kappa, frequency ratio, and F-score techniques. A comparison of the results obtained from the different models reveals that the new DSC-ADTree hybrid algorithm has the highest accuracy (AUC = 0.983) in preparing LSSSMs as compared to other learning models such as DSC-J48 (AUC = 0.976), DSC-NBTree (AUC = 0.959), DSC-LMT (AUC = 0.948), DSC-SVM (AUC = 0.939), and DSC (AUC = 0.911). The LSSSMs generated through the novel scientific approach presented in our study provide reliable tools for managing and reducing the risk of land subsidence.

Asunto(s)

RESUMEN

Molecular interaction maps (MIMs) are static graphical representations depicting complex biochemical networks that can be formalized using one of the Systems Biology Graphical Notation languages. Regardless of their extensive coverage of various biological processes, they are limited in terms of dynamic insights. However, MIMs can serve as templates for developing dynamic computational models. We present MetaLo, an open-source Python package that enables the coupling of Boolean models inferred from process description MIMs with generic core metabolic networks. MetaLo provides a framework to study the impact of signaling cascades, gene regulation processes, and metabolic flux distribution of central energy production pathways. MetaLo computes the Boolean model's asynchronous asymptotic behavior, through the identification of trap-spaces, and extracts metabolic constraints to contextualize the generic metabolic network. MetaLo is able to handle large-scale Boolean models and genome-scale metabolic models without requiring kinetic information or manual tuning. The framework behind MetaLo enables in depth analysis of the regulatory model, and may allow tackling a lack of omics data in poorly addressed biological fields to contextualize generic metabolic networks along with improper automatic reconstructions of cell- and/or disease-specific metabolic networks. MetaLo is available at https://pypi.org/project/metalo/ under the terms of the GNU General Public License v3.

Asunto(s)

RESUMEN

This article addresses reaction networks in which spatial and stochastic effects are of crucial importance. For such systems, particle-based models allow us to describe all microscopic details with high accuracy. However, they suffer from computational inefficiency if particle numbers and density get too large. Alternative coarse-grained-resolution models reduce computational effort tremendously, e.g., by replacing the particle distribution by a continuous concentration field governed by reaction-diffusion PDEs. We demonstrate how models on the different resolution levels can be combined into hybrid models that seamlessly combine the best of both worlds, describing molecular species with large copy numbers by macroscopic equations with spatial resolution while keeping the spatial-stochastic particle-based resolution level for the species with low copy numbers. To this end, we introduce a simple particle-based model for the binding dynamics of ions and vesicles at the heart of the neurotransmission process. Within this framework, we derive a novel hybrid model and present results from numerical experiments which demonstrate that the hybrid model allows for an accurate approximation of the full particle-based model in realistic scenarios.

Asunto(s)

RESUMEN

Wastewater treatment plant (WWTP) operation is usually intricate due to large variations in influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTP effluent water quality can provide valuable decision-making support to facilitate their operations and management. In this study, we developed a novel hybrid deep learning model by combining the temporal convolutional network (TCN) model with the long short-term memory (LSTM) network model to improve the simulation of hourly total nitrogen (TN) concentration in WWTP effluent. The developed model was tested in a WWTP in Jiangsu Province, China, where the prediction results of the hybrid TCN-LSTM model were compared with those of single deep learning models (TCN and LSTM) and traditional machine learning model (feedforward neural network, FFNN). The hybrid TCN-LSTM model could achieve 33.1 % higher accuracy as compared to the single TCN or LSTM model, and its performance could improve by 63.6 % comparing to the traditional FFNN model. The developed hybrid model also exhibited a higher power prediction of WWTP effluent TN for the next multiple time steps within eight hours, as compared to the standalone TCN, LSTM, and FFNN models. Finally, employing model interpretation approach of Shapley additive explanation to identify the key parameters influencing the behavior of WWTP effluent water quality, it was found that removing variables that did not contribute to the model output could further improve modeling efficiency while optimizing monitoring and management strategies.

Asunto(s)

RESUMEN

PURPOSE: Our aim was to elicit a value set for Capability-Adjusted Life Years Sweden (CALY-SWE); a capability-grounded quality of life instrument intended for use in economic evaluations of social interventions with broad consequences beyond health. METHODS: Building on methods commonly used in the quality-adjusted life years EQ-5D context, we collected time-trade off (TTO) and discrete choice experiment (DCE) data through an online survey from a general population sample of 1697 Swedish participants. We assessed data quality using a score based on the severity of inconsistencies. For generating the value set, we compared different model features, including hybrid modeling of DCE and TTO versus TTO data only, censoring of TTO answers, varying intercept, and accommodating for heteroskedasticity. We also assessed the models' DCE logit fidelity to measure agreement with potentially less-biased DCE data. To anchor the best capability state to 1 on the 0 to 1 scale, we included a multiplicative scaling factor. RESULTS: We excluded 20% of the TTO answers of participants with the largest inconsistencies to improve data quality. A hybrid model with an anchor scale and censoring was chosen to generate the value set; models with heteroskedasticity considerations or individually varying intercepts did not offer substantial improvement. The lowest capability weight was 0.114. Health, social relations, and finance and housing attributes contributed the largest capability gains, followed by occupation, security, and political and civil rights. CONCLUSION: We elicited a value set for CALY-SWE for use in economic evaluations of interventions with broad social consequences.

Asunto(s)

RESUMEN

Support ector achine (SVM) is a newer machine learning algorithm for classification, while logistic regression (LR) is an older statistical classification method. Despite the numerous studies contrasting SVM and LR, new improvements such as bagging and ensemble have been applied to them since these comparisons were made. This study proposes a new hybrid model based on SVM and LR for predicting small events per variable (EPV). The performance of the hybrid, SVM, and LR models with different EPV values was evaluated using COVID-19 data from December 2019 to May 2020 provided by the WHO. The study found that the hybrid model had better classification performance than SVM and LR in terms of accuracy, mean squared error (MSE), and root mean squared error (RMSE) for different EPV values. This hybrid model is particularly important for medical authorities and practitioners working in the face of future pandemics.

RESUMEN

Cancer-associated fibroblasts (CAFs) are amongst the key players of the tumor microenvironment (TME) and are involved in cancer initiation, progression, and resistance to therapy. They exhibit aggressive phenotypes affecting extracellular matrix remodeling, angiogenesis, immune system modulation, tumor growth, and proliferation. CAFs phenotypic changes appear to be associated with metabolic alterations, notably a reverse Warburg effect that may drive fibroblasts transformation. However, its precise molecular mechanisms and regulatory drivers are still under investigation. Deciphering the reverse Warburg effect in breast CAFs may contribute to a better understanding of the interplay between TME and tumor cells, leading to new treatment strategies. In this regard, dynamic modeling approaches able to span multiple biological layers are essential to capture the emergent properties of various biological entities when complex and intertwined pathways are involved. This work presents the first hybrid large-scale computational model for breast CAFs covering major cellular signaling, gene regulation, and metabolic processes. It was generated by combining a cell- and disease-specific asynchronous Boolean model with a generic core metabolic network leveraging both data-driven and manual curation approaches. This model reproduces the experimentally observed reverse Warburg effect in breast CAFs and further identifies Hypoxia-Inducible Factor 1 (HIF-1) as its key molecular driver. Targeting HIF-1 as part of a TME-centered therapeutic strategy may prove beneficial in the treatment of breast cancer by addressing the reverse Warburg effect. Such findings in CAFs, in light of our previously published results in rheumatoid arthritis synovial fibroblasts, point to a common HIF-1-driven metabolic reprogramming of fibroblasts in breast cancer and rheumatoid arthritis.

RESUMEN

Introduction: Hybrid modeling combining First-Principles with machine learning is becoming a pivotal methodology for Biopharma 4.0 enactment. Chinese Hamster Ovary (CHO) cells, being the workhorse for industrial glycoproteins production, have been the object of several hybrid modeling studies. Most previous studies pursued a shallow hybrid modeling approach based on three-layered Feedforward Neural Networks (FFNNs) combined with macroscopic material balance equations. Only recently, the hybrid modeling field is incorporating deep learning into its framework with significant gains in descriptive and predictive power. Methods: This study compares, for the first time, deep and shallow hybrid modeling in a CHO process development context. Data of 24 fed-batch cultivations of a CHO-K1 cell line expressing a target glycoprotein, comprising 30 measured state variables over time, were used to compare both methodologies. Hybrid models with varying FFNN depths (3-5 layers) were systematically compared using two training methodologies. The classical training is based on the Levenberg-Marquardt algorithm, indirect sensitivity equations and cross-validation. The deep learning is based on the Adaptive Moment Estimation Method (ADAM), stochastic regularization and semidirect sensitivity equations. Results and conclusion: The results point to a systematic generalization improvement of deep hybrid models over shallow hybrid models. Overall, the training and testing errors decreased by 14.0% and 23.6% respectively when applying the deep methodology. The Central Processing Unit (CPU) time for training the deep hybrid model increased by 31.6% mainly due to the higher FFNN complexity. The final deep hybrid model is shown to predict the dynamics of the 30 state variables within the error bounds in every test experiment. Notably, the deep hybrid model could predict the metabolic shifts in key metabolites (e.g., lactate, ammonium, glutamine and glutamate) in the test experiments. We expect deep hybrid modeling to accelerate the deployment of high-fidelity digital twins in the biopharma sector in the near future.

RESUMEN

Because it is associated with most multifactorial inherited diseases like heart disease, hypertension, diabetes, and other serious medical conditions, obesity is a major global health concern. Obesity is caused by hereditary, physiological, and environmental factors, as well as poor nutrition and a lack of exercise. Weight loss can be difficult for various reasons, and it is diagnosed via BMI, which is used to estimate body fat for most people. Muscular athletes, for example, may have a BMI in the obesity range even when they are not obese. Researchers from a variety of backgrounds and institutions devised different hypotheses and models for the prediction and classification of obesity using different approaches and various machine learning techniques. In this study, a majority voting-based hybrid modeling approach using a gradient boosting classifier, extreme gradient boosting, and a multilayer perceptron was developed. Seven distinct machine learning algorithms were used on open datasets from the UCI machine learning repository, and their respective accuracy levels were compared before the combined approaches were chosen. The proposed majority voting-based hybrid model for prediction and classification of obesity that was achieved has an accuracy of 97.16%, which is greater than both the individual models and the other hybrid models that have been developed.