Food Product Design: A Hybrid Machine Learning and Mechanistic Modeling Approach

CO2 corrosion remains a critical challenge for the safe and reliable operation of Carbon Capture, Utilization, and Storage (CCUS) infrastructure. This review summarizes CO2 corrosion implications from material selection, exposure time, CO2 phase behavior, flow conditions, and impurities such as H2O, O2, SOx, NOx, and H2S. CO2 corrosion modeling has, since early works by de Waard in 1975, expanded to a wide range of models and software tools, many of which have already been reviewed and compared. This work provides a historical timeline and a comparative summary of models and software tools to assist in selecting models for CCUS applications. Modeling approaches are classified into empirical, semi-empirical, and mechanistic categories, with their assumptions, strengths, and limitations. CO2 corrosion modeling has persistent challenges relating to data quality, data quantity, and parameter interactions, which reduce model accuracy, especially for machine learning approaches. The provided perspective emphasizes that machine learning and hybrid modeling approaches for CO2 corrosion prediction are gaining popularity, and their effectiveness is currently limited by the quality and quantity of available corrosion data. The provided opportunities include recommendations for standardized experimental procedures and hybrid modeling strategies that combine physics-based insights from mechanistic modeling approaches with data-driven machine learning approaches.

As pharmaceutical development moves from early-stage in vitro experimentation to later in vivo and subsequent clinical trials, data and knowledge are acquired across multiple time and length scales, from the subcellular to whole patient cohort scale. Realizing the potential of this data for informing decision making in pharmaceutical development requires the individual and combined application of machine learning (ML) and mechanistic multiscale mathematical modeling approaches. Here we outline how these two approaches, both individually and in tandem, can be applied at different stages of the drug discovery and development pipeline to inform decision making compound development. The importance of discerning between knowledge and data are highlighted in informing the initial use of ML or mechanistic quantitative systems pharmacology (QSP) models. We discuss the application of sensitivity and structural identifiability analyses of QSP models in informing future experimental studies to which ML may be applied, as well as how ML approaches can be used to inform mechanistic model development. Relevant literature studies are highlighted and we close by discussing caveats regarding the application of each approach in an age of constant data acquisition. SIGNIFICANCE STATEMENT: We consider when best to apply machine learning (ML) and mechanistic quantitative systems pharmacology (QSP) approaches in the context of the drug discovery and development pipeline. We discuss the importance of prior knowledge and data available for the system of interest and how this informs the individual and combined application of ML and QSP approaches at each stage of the pipeline.

This review explores the multifaceted landscape of renal cell carcinoma (RCC) by delving into both mechanistic and machine learning models. While machine learning models leverage patients' gene expression and clinical data through a variety of techniques to predict patients' outcomes, mechanistic models focus on investigating cells' and molecules' interactions within RCC tumors. These interactions are notably centered around immune cells, cytokines, tumor cells, and the development of lung metastases. The insights gained from both machine learning and mechanistic models encompass critical aspects such as signature gene identification, sensitive interactions in the tumors' microenvironments, metastasis development in other organs, and the assessment of survival probabilities. By reviewing the models of RCC, this study aims to shed light on opportunities for the integration of machine learning and mechanistic modeling approaches for treatment optimization and the identification of specific targets, all of which are essential for enhancing patient outcomes.

Combining mechanistic modeling with machine learning to study multiscale biological processes Biological and physiological processes occur across a broad spatiotemporal range, with processes at one level of scale (e.g., gene expression inside single cells) affecting processes at other levels of scale (e.g., coordinated migration of endothelial cells during angiogenesis and tumor growth). Deducing the cause-and-effect relationships that link biological and physiological mechanisms across scales is a major challenge that both machine learning (ML) and mechanistic modeling approaches seek to address. Mechanistic models are particularly well-suited for simulating and/or computing how abstracted, intersecting biological processes give rise to changes over time. Data-driven/machine learning (ML) approaches, such as neural networks and clustering algorithms, on the other hand, integrate massive amounts of data to identify patterns, trends, and correlations in the data. Both methodologies can be used to generate novel insights and testable hypotheses, though the means for doing so differ depending on the modeling approach. Emerging computational strategies are combining mechanistic modeling and ML in ways that capitalize on their unique attributes and compensate for the deficiencies of the other. As discussed in this Research Topic, the resulting synergy created by merging these methods more comprehensively and efficiently leverages large-scale data sets to produce new insights about what biological processes connect across spatial and temporal scales and how they intersect to drive changes in cells, tissues, and organs. Sivakumar et al. provide foundational context for the integration of mechanistic and ML models, focusing on a particular class of the former (namely, agent-based models [ABM]). The authors introduce and explain key concepts, strengths, and limitations of both classes of models, and particularly highlight applications to spatial modeling of biological processes. They note the difficulties inherent in assessing ML models and discuss multiple applications of ML in the context of ABM (e.g., defining and determining agent rules, parameter estimation/model calibration, and reducing the computational cost of ABM). Erdem and Birtwistle present another use case for integrating ML and mechanistic modeling, this time in the context of mining 'omics data to define causal interactions and then integrate these inferences into a mechanistic model. The MEMMAL (MEchanistic

In the early 1990s, the establishment of the Internet brought forth a revolutionary viewpoint of information storage, distribution, and processing: the World Wide Web is becoming an enormous and expanding distributed digital library. Along with the development of the Web, image indexing and retrieval have grown into research areas sharing a vision of intelligent agents. Far beyond Web searching, image indexing and retrieval can potentially be applied to many other areas, including biomedicine, space science, biometric identification, digital libraries, the military, education, commerce, culture and entertainment. Machine Learning and Statistical Modeling Approaches to Image Retrieval describes several approaches of integrating machine learning and statistical modeling into an image retrieval and indexing system that demonstrates promising results. The topics of this book reflect authors' experiences of machine learning and statistical modeling based image indexing and retrieval. This book contains detailed references for further reading and research in this field as well.

BackgroundThe number of COVID-19 cases continues to grow in Indonesia. This phenomenon motivates researchers to find alternative drugs that function for prevention or treatment. Due to the rich biodiversity of Indonesian medicinal plants, one alternative is to examine the potential of herbal medicines to support COVID therapy. This study aims to identify potential compound candidates in Indonesian herbal using a machine learning and pharmacophore modeling approaches.MethodsWe used three classification methods that had different decision-making processes: support vector machine (SVM), multilayer perceptron (MLP), and random forest (RF). For the pharmacophore modeling approach, we performed a structure-based analysis on the 3D structure of the main protease SARS-CoV-2 (3CLPro) and repurposed SARS, MERS, and SARS-CoV-2 drugs identified from the literature as datasets in the ligand-based method. Lastly, we used molecular docking to analyze the interactions between the 3CLpro and 14 hit compounds from the Indonesian Herbal Database (HerbalDB), with lopinavir as a positive control.ResultsFrom the molecular docking analysis, we found six potential compounds that may act as the main proteases of the SARS-CoV-2 inhibitor: hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside.ConclusionsOur layered virtual screening with machine learning and pharmacophore modeling approaches provided a more objective and optimal virtual screening and avoided subjective decision making of the results. Herbal compounds from the screening, i.e. hesperidin, kaempferol-3,4'-di-O-methyl ether (Ermanin); myricetin-3-glucoside, peonidin 3-(4’-arabinosylglucoside); quercetin 3-(2G-rhamnosylrutinoside); and rhamnetin 3-mannosyl-(1-2)-alloside are potential antiviral candidates for SARS-CoV-2. Moringa oleifera and Psidium guajava that consist of those compounds, could be an alternative option as COVID-19 herbal preventions.

For a better understanding of the Earth system we need a stronger integration of observations and (mechanistic) models. Classical model-data integration approaches start with a model structure and try to estimate states or parameters via data assimilation and inverse modelling, respectively. Sometimes, several model structures are employed and evaluated, e.g. in Bayesian model averaging, but still parametric model structures are assumed. Recently, Reichstein et al. (2019) proposed a fusion of machine learning and mechanistic modelling approaches into so-called hybrid modelling. Ideally, this combines scientific consistency with the versatility of data driven approaches and is expected to allow for better predictions and better understanding of the system, e.g. by inferring unobserved variables. In this talk we will introduce this concept and illustrate its promise with examples on biosphere-atmosphere exchange, and carbon and water cycles from the ecosystem to the global scale.Reichstein, M., G. Camps-Valls, B. Stevens, M. Jung, J. Denzler, N. Carvalhais, and Prabhat. "Deep Learning and Process Understanding for Data-Driven Earth System Science." Nature 566, no. 7743 (2019): 195-204. https://doi.org/10.1038/s41586-019-0912-1.

Both machine learning and mechanistic modelling approaches have been used independently with great success in systems biology. Machine learning excels in deriving statistical relationships and quantitative prediction from data, while mechanistic modelling is a powerful approach to capture knowledge and infer causal mechanisms underpinning biological phenomena. Importantly, the strengths of one are the weaknesses of the other, which suggests that substantial gains can be made by combining machine learning with mechanistic modelling, a field referred to as Scientific Machine Learning (SciML). In this review we discuss recent advances in combining these two approaches for systems biology, and point out future avenues for its application in the biological sciences.

Managing expectations is vital to ensuring commuter satisfaction with their public transportation service. When customers are given an estimated time for their bus and must wait way longer, they lose a sense of control over their commute and become frustrated. In this paper, we present a novel machine learning (ML) modeling approach in which we train and implement specialized models for every single segment of travel time and stop dwell time in our system to capture its uniqueness. The features for training the models include simple calendar and weather data. Most papers assume ideal operational conditions but in practice that’s almost never the case. Here, we combine our ML modeling approach with a flexible production-tested algorithm to combine model-generated dwell and travel time (or run time) predictions to produce predicted bus departure times. This algorithm is designed to handle real transit agency challenges like missing models (including those caused by changes to schedules and routes), timing points, and partially traveled segments. We also provide a reference architecture of how this algorithm can be brought to life in a scalable and cost-effective manner.

Preoperative risk assessment is crucial for cardiac surgery. Although previous studies suggested machine learning (ML) may improve in-hospital mortality predictions after cardiac surgery compared to traditional modeling approaches, the validity is doubted due to lacking external validation, limited sample sizes, and inadequate modeling considerations. We aimed to assess predictive performance between ML and traditional modelling approaches, while addressing these major limitations. Adult cardiac surgery cases (n=168565) between 2013 and 2018 in the Chinese Cardiac Surgery Registry were used to develop, validate, and compare various ML vs. logistic regression (LR) models. The dataset was split for temporal (2013-2017 for training, 2018 for testing) and spatial (geographically-stratified random selection of 83 centers for training, 22 for testing) experiments, respectively. Model performances were evaluated in testing sets for discrimination and calibration. The overall in-hospital mortality was 1.9%. In the temporal testing set (n=32184), the best-performing ML model demonstrated a similar area under the receiver operating characteristic curve (AUC) of 0.797 (95% CI 0.779-0.815) to the LR model (AUC 0.791 [95% CI 0.775-0.808]; P=0.12). In the spatial experiment (n=28323), the best ML model showed a statistically better but modest performance improvement (AUC 0.732 [95% CI 0.710-0.754]) than LR (AUC 0.713 [95% CI 0.691-0.737]; P=0.002). Varying feature selection methods had relatively smaller effects on ML models. Most ML and LR models were significantly miscalibrated. ML provided only marginal improvements over traditional modelling approaches in predicting cardiac surgery mortality with routine preoperative variables, which calls for more judicious use of ML in practice.

Hybrid Machine Learning and Language Model Approach for Monitoring and Regulating International Dark Web Transactions

This study investigates the buckling behavior of columns with variable cross-sections using analytical, numerical, and hybrid machine learning (ML) approaches. Initially, the power series method is employed to calculate the buckling loads of columns with both constant and varying cross-sections under diverse boundary conditions. Then a finite element (FE) analyses of the columns are performed to obtain the buckling loads and the results are validate by comparing them with results from power series method. Once validated, the FE model is used to generate a large dataset encompassing a wide range of cross-sections, lengths, and material properties, as per the samples obtained through the Sobol sampling method. A hybrid ML model is then developed by integrating the XGBoost algorithm with the particle swarm optimization (PSO) technique for hyperparameter tuning. This hybrid PSO-XGBoost model is trained to predict the buckling loads of columns with varying cross-sections. Its performance for input parameters outside the training dataset is evaluated using statistical metrics and scatter plots. The results demonstrate excellent agreement between the FE analysis and the power series method, confirming the reliability of both approaches. The PSO-XGBoost model achieved remarkable predictive accuracy, with R 2 values of 0.999 and 0.996 for the training and testing datasets, respectively. Furthermore, SHapley Additive exPlanations (SHAP) analysis is conducted to explore the influence and interactions of input parameters on buckling loads, providing valuable insights into the model’s interpretability and the underlying mechanics of column buckling.

Since each cancer has its own unique characteristics, each one can respond differently to the same treatments. Therefore, the creation of a digital twin (DT) of cancer can assist us in predicting the evolution of an individual's cancer through modeling each tumor's characteristics and response to treatment. Hence, we propose to take advantage of new advances in computational approaches and combine mechanistic, machine learning, and stochastic modeling approaches to create “My Virtual Cancer", a DT platform. To establish a personalized DT, we use patient-specific data for parameter estimations, sensitivity analysis, and uncertainty quantification. For each patient, we will estimate the values of parameters of their QSP model using the patient's data. We perform a multi-dimensional sensitivity analysis and uncertainty quantification on the mechanistic model to find a set of critical interactions and predict the intervals of confidence. Since this QSP model includes the data-driven mechanistic model of cells and molecules' interaction networks, one of the ultimate results of this DT would be the prediction of evolution of tumors.

A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces

Understanding the formation and evolution of geosystems as a result of coupled processes from microscale structure to core-scale samples is critically important for predicting meso- to macro-scale multi-physical behavior, thus providing effective control of subsurface energy recovery and storage activities. In this paper, we present integrated machine learning and numerical modeling approaches that we have developed to understand fundamental geosystem behavior, to predict their mesoscale behavior, and to analyze large-scale performance of such geosystems subject to multi-physical couplings. First of all, we will present a high-level summary of our developed modelling capabilities based on the numerical manifold method [1]. Then we will present theoretical comparison between machine learning and numerical modeling [2]. Using current machine learning techniques on image recognition, we make flexible use of these techniques to integrate experimental data with numerical modeling. By using a convolutional neural network, U-net, we show results of fractures recognized from rock images [3]. By using a machine learning approach referred to as neural style transfer, we will show automatic and efficient mesh generation and optimization from rock images [2]. With a microscale model for capturing dynamic contacts between geomaterials with arbitrary shapes of grains and interfaces [4], we extend this model by accounting for hydro-mechanical couplings and realistic geometry using digital representations of rocks [1]. Using different examples, we show the unique capabilities to simulate coupled processes in fractures at different scales and microscale granular systems, while applying differing physical laws, coupling priorities, and solutions for evolving geometry at multiple scales [5]. We will conclude with perspectives on solutions to bridge the gaps between fundamental and applied geosciences by integrating machine learning and numerical modeling.