Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data.

Humans are continuously exposed to a variety of toxicants and chemicals which is exacerbated during and after environmental catastrophes such as floods, earthquakes, and hurricanes. The hazardous chemical mixtures generated during these events threaten the health and safety of humans and other living organisms. This necessitates the development of rapid decision-making tools to facilitate mitigating the adverse effects of exposure on the key modulators of the endocrine system, such as the estrogen receptor alpha (ERα), for example. The mechanistic stages of the estrogenic transcriptional activity can be measured with high content/high throughput microscopy-based biosensor assays at the single-cell level, which generates millions of object-based minable data points. By combining computational modeling and experimental analysis, we built a highly accurate data-driven classification framework to assess the endocrine disrupting potential of environmental compounds. The effects of these compounds on the ERα pathway are predicted as being receptor agonists or antagonists using the principal component analysis (PCA) projections of high throughput, high content image analysis descriptors. The framework also combines rigorous preprocessing steps and nonlinear machine learning algorithms, such as the Support Vector Machines and Random Forest classifiers, to develop highly accurate mathematical representations of the separation between ERα agonists and antagonists. The results show that Support Vector Machines classify the unseen chemicals correctly with more than 96% accuracy using the proposed framework, where the preprocessing and the PCA steps play a key role in suppressing experimental noise and unraveling hidden patterns in the dataset.

An improved algorithm for flux variability analysis.

Flux balance analysis (FBA) is an optimization based approach to find the optimal steady state of a metabolic network, commonly of microorganisms such as yeast strains and Escherichia coli. However, the resulting solution from an FBA is typically not unique, as the optimization problem is, more often than not, degenerate. Flux variability analysis (FVA) is a method to determine the range of possible reaction fluxes that still satisfy, within some optimality factor, the original FBA problem. The resulting range of reaction fluxes can be utilized to determine metabolic reactions of high importance, amongst other analyses. In the literature, this has been done by solving [Formula: see text] linear programs (LPs), with n being the number of reactions in the metabolic network. However, FVA can be solved with less than [Formula: see text] LPs by utilizing the basic feasible solution property of bounded LPs to reduce the number of LPs that are needed to be solved. In this work, a new algorithm is proposed to solve FVA that requires less than [Formula: see text] LPs. The proposed algorithm is benchmarked on a problem set of 112 metabolic network models ranging from single cell organisms (iMM904, ect) to a human metabolic system (Recon3D). Showing a reduction in the number of LPs required to solve the FVA problem and thus the time to solve an FVA problem.

Data-Driven Optimization of Mixed-integer Bi-level Multi-follower Integrated Planning and Scheduling Problems Under Demand Uncertainty.

The coordination of interconnected elements across the different layers of the supply chain is essential for all industrial processes and the key to optimal decision-making. Yet, the modeling and optimization of such interdependent systems are still burdensome. In this paper, we address the simultaneous modeling and optimization of medium-term planning and short-term scheduling problems under demand uncertainty using mixed-integer bi-level multi-follower programming and data-driven optimization. Bi-level multi-follower programs model the natural hierarchy between different layers of supply chain management holistically, while scenario analysis and data-driven optimization allow us to retrieve the guaranteed feasible solutions of the integrated formulation under various demand considerations. We address the data-driven optimization of this challenging class of problems using the DOMINO framework, which was initially developed to solve single-leader single-follower bi-level optimization problems to guaranteed feasibility. This framework is extended to solve single-leader multi-follower stochastic formulations and its performance is characterized by well-known single and multi-product process scheduling case studies. Through our data-driven algorithmic approach, we present guaranteed feasible solutions to linear and nonlinear mixed-integer bi-level formulations of simultaneous planning and scheduling problems and further characterize the effects of the scheduling level complexity on the solution performance, which spans over several hundred continuous and binary variables, and thousands of constraints.

Classification of estrogenic compounds by coupling high content analysis and machine learning algorithms.

Environmental toxicants affect human health in various ways. Of the thousands of chemicals present in the environment, those with adverse effects on the endocrine system are referred to as endocrine-disrupting chemicals (EDCs). Here, we focused on a subclass of EDCs that impacts the estrogen receptor (ER), a pivotal transcriptional regulator in health and disease. Estrogenic activity of compounds can be measured by many in vitro or cell-based high throughput assays that record various endpoints from large pools of cells, and increasingly at the single-cell level. To simultaneously capture multiple mechanistic ER endpoints in individual cells that are affected by EDCs, we previously developed a sensitive high throughput/high content imaging assay that is based upon a stable cell line harboring a visible multicopy ER responsive transcription unit and expressing a green fluorescent protein (GFP) fusion of ER. High content analysis generates voluminous multiplex data comprised of minable features that describe numerous mechanistic endpoints. In this study, we present a machine learning pipeline for rapid, accurate, and sensitive assessment of the endocrine-disrupting potential of benchmark chemicals based on data generated from high content analysis. The multidimensional imaging data was used to train a classification model to ultimately predict the impact of unknown compounds on the ER, either as agonists or antagonists. To this end, both linear logistic regression and nonlinear Random Forest classifiers were benchmarked and evaluated for predicting the estrogenic activity of unknown compounds. Furthermore, through feature selection, data visualization, and model discrimination, the most informative features were identified for the classification of ER agonists/antagonists. The results of this data-driven study showed that highly accurate and generalized classification models with a minimum number of features can be constructed without loss of generality, where these machine learning models serve as a means for rapid mechanistic/phenotypic evaluation of the estrogenic potential of many chemicals.

Optimal Design of Energy Systems Using Constrained Grey-Box Multi-Objective Optimization.

The (global) optimization of energy systems, commonly characterized by high-fidelity and large-scale complex models, poses a formidable challenge partially due to the high noise and/or computational expense associated with the calculation of derivatives. This complexity is further amplified in the presence of multiple conflicting objectives, for which the goal is to generate trade-off compromise solutions, commonly known as Pareto-optimal solutions. We have previously introduced the p-ARGONAUT system, parallel AlgoRithms for Global Optimization of coNstrAined grey-box compUTational problems, which is designed to optimize general constrained single objective grey-box problems by postulating accurate and tractable surrogate formulations for all unknown equations in a computationally efficient manner. In this work, we extend p-ARGONAUT towards multi-objective optimization problems and test the performance of the framework, both in terms of accuracy and consistency, under many equality constraints. Computational results are reported for a number of benchmark multi-objective problems and a case study of an energy market design problem for a commercial building, while the performance of the framework is compared with other derivative-free optimization solvers.

Big Data Approach to Batch Process Monitoring: Simultaneous Fault Detection and Diagnosis Using Nonlinear Support Vector Machine-based Feature Selection.

This paper presents a novel data-driven framework for process monitoring in batch processes, a critical task in industry to attain a safe operability and minimize loss of productivity and profit. We exploit high dimensional process data with nonlinear Support Vector Machine-based feature selection algorithm, where we aim to retrieve the most informative process measurements for accurate and simultaneous fault detection and diagnosis. The proposed framework is applied to an extensive benchmark dataset which includes process data describing 22,200 batches with 15 faults. We train fault and time-specific models on the prealigned batch data trajectories via three distinct time horizon approaches: one-step rolling, two-step rolling, and evolving which varies the amount of data incorporation during modeling. The results show that two-step rolling and evolving time horizon approaches perform superior to the other. Regardless of the approach, proposed framework provides a promising decision support tool for online simultaneous fault detection and diagnosis for batch processes.

Cyclin and DNA distributed cell cycle model for GS-NS0 cells.

Mammalian cell cultures are intrinsically heterogeneous at different scales (molecular to bioreactor). The cell cycle is at the centre of capturing heterogeneity since it plays a critical role in the growth, death, and productivity of mammalian cell cultures. Current cell cycle models use biological variables (mass/volume/age) that are non-mechanistic, and difficult to experimentally determine, to describe cell cycle transition and capture culture heterogeneity. To address this problem, cyclins-key molecules that regulate cell cycle transition-have been utilized. Herein, a novel integrated experimental-modelling platform is presented whereby experimental quantification of key cell cycle metrics (cell cycle timings, cell cycle fractions, and cyclin expression determined by flow cytometry) is used to develop a cyclin and DNA distributed model for the industrially relevant cell line, GS-NS0. Cyclins/DNA synthesis rates were linked to stimulatory/inhibitory factors in the culture medium, which ultimately affect cell growth. Cell antibody productivity was characterized using cell cycle-specific production rates. The solution method delivered fast computational time that renders the model's use suitable for model-based applications. Model structure was studied by global sensitivity analysis (GSA), which identified parameters with a significant effect on the model output, followed by re-estimation of its significant parameters from a control set of batch experiments. A good model fit to the experimental data, both at the cell cycle and viable cell density levels, was observed. The cell population heterogeneity of disturbed (after cell arrest) and undisturbed cell growth was captured proving the versatility of the modelling approach. Cell cycle models able to capture population heterogeneity facilitate in depth understanding of these complex systems and enable systematic formulation of culture strategies to improve growth and productivity. It is envisaged that this modelling approach will pave the model-based development of industrial cell lines and clinical studies.

Towards unravelling the kinetics of an acute myeloid leukaemia model system under oxidative and starvation stress: a comparison between two- and three-dimensional cultures.

A great challenge when conducting ex vivo studies of leukaemia is the construction of an appropriate experimental platform that would recapitulate the bone marrow (BM) environment. Such a 3D scaffold system has been previously developed in our group [1]. Additionally to the BM architectural characteristics, parameters such as oxygen and glucose concentration are crucial as their value could differ between patients as well as within the same patient at different stages of treatment, consequently affecting the resistance of leukaemia to chemotherapy. The effect of oxidative and glucose stress-at levels close to human physiologic ones-on the proliferation and metabolic evolution of an AML model system (K-562 cell line) in conventional 2D cultures as well as in 3D scaffolds were studied. We observed that the K-562 cell line can proliferate and remain alive for 2 weeks in medium with glucose close to physiological levels both in 20 and 5% O2. We report interesting differences on the cellular response to the environmental, i.e., oxidative and/or nutritional stress stimuli in 2D and 3D. Higher adaptation to oxidative stress under non-starving conditions is observed in the 3D system. The glucose level in the medium has more impact on the cellular proliferation in the 3D compared to the 2D system. These differences can be of significant importance both when applying chemotherapy in vitro and also when constructing mathematical tools for optimisation of disease treatment.

Free energy predictions of ligand binding to an α-helix using steered molecular dynamics and umbrella sampling simulations.

Free energy prediction of ligand binding to macromolecules using explicit solvent molecular dynamics (MD) simulations is computationally very expensive. Recently, we reported a linear correlation between the binding free energy obtained via umbrella sampling (US) versus the rupture force from steered molecular dynamics (SMD) simulations for epigallocatechin-3-gallate (EGCG) binding to α-helical-rich keratin. This linear correlation suggests a potential route for fast free energy predictions using SMD alone. In this work, the generality of the linear correlation is further tested for several ligands interacting with the α-helical motif of keratin. These molecules have significantly varying properties, i.e., octanol/water partition coefficient (log P), and/or overall charges (oleic acid, catechin, Fe(2+), citric acid, hydrogen citrate, dihydrogen citrate, and citrate). Using the constant loading rate of our previous study of the keratin-EGCG system, we observe that the linear correlation for keratin-EGCG can be extended to other uncharged molecules where interactions are governed by hydrogen bonds and/or a combination of hydrogen bonds and hydrophobic forces. For molecules where interactions with the keratin helix are governed primarily by electrostatics between charged molecules, a second, alternative linear correlation model is derived. While further investigations are needed to expand the molecular space and build a fully predictive model, the current approach represents a promising methodology for fast free energy predictions based on short SMD simulations (requiring picoseconds to nanoseconds of sampling) for defined biomolecular systems.

Advanced Modeling and Optimization Strategies for Process Synthesis.

This article provides a systematic review of recent progress in optimization-based process synthesis. First, we discuss multiscale modeling frameworks featuring targeting approaches, phenomena-based modeling, unit operation-based modeling, and hybrid modeling. Next, we present the expanded scope of process synthesis objectives, highlighting the considerations of sustainability and operability to assure cost-competitive production in an increasingly dynamic market with growing environmental awareness. Then, we review advances in optimization algorithms and tools, including emerging machine learning-and quantum computing-assisted approaches. We conclude by summarizing the advances in and perspectives for process synthesis strategies.

Optimal Operation of an Industrial Dividing Wall Column through Multiparametric Programming.

In this contribution, we present a high-fidelity dynamic model of an industrial dividing wall column and the application of explicit model predictive control for its regulation. Our study involves the separation of methyl methacrylate from a quaternary mixture. The process includes a dividing wall column coupled with a decanter, which results in highly concentrated methyl methacrylate and water streams from the middle side draw of the column and the decanter, respectively. An equation-oriented mathematical model of the process is developed and presented in detail, where non-ideal thermodynamic calculations are adopted to describe the complex nature of the component interactions. The operability of the process is enhanced by the synthesis and application of an explicit model predictive controller, which is used to track the purity specifications of the product. Our results demonstrate that the proposed modeling and control approach can be utilized for the optimal online operation of the studied system.

Binary Classification of the Endocrine Disrupting Chemicals by Artificial Neural Networks.

We develop a machine learning framework that integrates high content/high throughput image analysis and artificial neural networks (ANNs) to model the separation between chemical compounds based on their estrogenic receptor activity. Natural and man-made chemicals have the potential to disrupt the endocrine system by interfering with hormone actions in people and wildlife. Although numerous studies have revealed new knowledge on the mechanism through which these compounds interfere with various hormone receptors, it is still a very challenging task to comprehensively evaluate the endocrine disrupting potential of all existing chemicals and their mixtures by pure in vitro or in vivo approaches. Machine learning offers a unique advantage in the rapid evaluation of chemical toxicity through learning the underlying patterns in the experimental biological activity data. Motivated by this, we train and test ANN classifiers for modeling the activity of estrogen receptor-α agonists and antagonists at the single-cell level by using high throughput/high content microscopy descriptors. Our framework preprocesses the experimental data by cleaning, scaling, and feature engineering where only the middle 50% of the values from each sample with detectable receptor-DNA binding is considered in the dataset. Principal component analysis is also used to minimize the effects of experimental noise in modeling where these projected features are used in classification model building. The results show that our ANN-based nonlinear data-driven framework classifies the benchmark agonist and antagonist chemicals with 98.41% accuracy.

A Neural Network Based Superstructure Optimization Approach to Reverse Osmosis Desalination Plants.

An ever-growing population together with globally depleting water resources pose immense stresses for water supply systems. Desalination technologies can reduce these stresses by generating fresh water from saline water sources. Reverse osmosis (RO), as the industry leading desalination technology, typically involves a complex network of membrane modules that separate unwanted particles from water. The optimal design and operation of these complex RO systems can be computationally expensive. In this work, we present a modeling and optimization strategy for addressing the optimal operation of an industrial-scale RO plant. We employ a feed-forward artificial neural network (ANN) surrogate modeling representation with rectified linear units as activation functions to capture the membrane behavior accurately. Several ANN set-ups and surrogate models are presented and evaluated, based on collected data from the H2Oaks RO desalination plant in South-Central Texas. The developed ANN is then transformed into a mixed-integer linear programming formulation for the purpose of minimizing energy consumption while maximizing water utilization. Trade-offs between the two competing objectives are visualized in a Pareto front, where indirect savings can be uncovered by comparing energy consumption for an array of water recoveries and feed flows.

Continuous-Time Surrogate Models for Data-Driven Dynamic Optimization.

This work addresses the control optimization of time-varying systems without the full discretization of the underlying high-fidelity models and derives optimal control trajectories using surrogate modeling and data-driven optimization. Time-varying systems are ubiquitous in the chemical process industry and their systematic control is essential for ensuring each system to be operated at the desired settings. To this end, we postulate nonlinear continuous-time control action trajectories using time-varying surrogate models and derive the parameters of these functional forms using data-driven optimization. Data-driven optimization allows us to collect data from the high-fidelity model without pursuing any discretization and fine-tune candidate control trajectories based on the retrieved input-output information from the nonlinear system. We test exponential and polynomial surrogate forms for the control trajectories and explore various data-driven optimization strategies (local vs. global and sample-based vs. model-based) to test the consistency of each approach for controlling dynamic systems. The applicability of our approach is demonstrated on a motivating example and a CSTR control case study with favorable results.

A decision-making framework for the optimal design of renewable energy systems under energy-water-land nexus considerations.

The optimal allocation of land for energy generation is of emergent concern due to an increasing demand for renewable power capacity, land scarcity, and the diminishing supply of water. Therefore, economically, socially and environmentally optimal design of new energy infrastructure systems require the holistic consideration of water, food and land resources. Despite huge efforts on the modeling and optimization of renewable energy systems, studies navigating the multi-faceted and interconnected food-energy-water-land nexus space, identifying opportunities for beneficial improvement, and systematically exploring interactions and trade-offs are still limited. In this work we present the foundations of a systems engineering decision-making framework for the trade-off analysis and optimization of water and land stressed renewable energy systems. The developed framework combines mathematical modeling, optimization, and data analytics to capture the interdependencies of the nexus elements and therefore facilitate informed decision making. The proposed framework has been adopted for a water-stressed region in south-central Texas. The optimal solutions of this case study highlight the significance of geographic factors and resource availability on the transition towards renewable energy generation.

Linking genes to microbial growth kinetics: an integrated biochemical systems engineering approach.

The majority of models describing the kinetic properties of a microorganism for a given substrate are unstructured and empirical. They are formulated in this manner so that the complex mechanism of cell growth is simplified. Herein, a novel approach for modelling microbial growth kinetics is proposed, linking biomass growth and substrate consumption rates to the gene regulatory programmes that control these processes. A dynamic model of the TOL (pWW0) plasmid of Pseudomonas putida mt-2 has been developed, describing the molecular interactions that lead to the transcription of the upper and meta operons, known to produce the enzymes for the oxidative catabolism of m-xylene. The genetic circuit model was combined with a growth kinetic model decoupling biomass growth and substrate consumption rates, which are expressed as independent functions of the rate-limiting enzymes produced by the operons. Estimation of model parameters and validation of the model's predictive capability were successfully performed in batch cultures of mt-2 fed with different concentrations of m-xylene, as confirmed by relative mRNA concentration measurements of the promoters encoded in TOL. The growth formation and substrate utilisation patterns could not be accurately described by traditional Monod-type models for a wide range of conditions, demonstrating the critical importance of gene regulation for the development of advanced models closely predicting complex bioprocesses. In contrast, the proposed strategy, which utilises quantitative information pertaining to upstream molecular events that control the production of rate-limiting enzymes, predicts the catabolism of a substrate and biomass formation and could be of central importance for the design of optimal bioprocesses.

A systems engineering framework for the optimization of food supply chains under circular economy considerations.

The current linear "take-make-waste-extractive" model leads to the depletion of natural resources and environmental degradation. Circular Economy (CE) aims to address these impacts by building supply chains that are restorative, regenerative, and environmentally benign. This can be achieved through the re-utilization of products and materials, the extensive usage of renewable energy sources, and ultimately by closing any open material loops. Such a transition towards environmental, economic and social advancements requires analytical tools for quantitative evaluation of the alternative pathways. Here, we present a novel CE system engineering framework and decision-making tool for the modeling and optimization of food supply chains. First, the alternative pathways for the production of the desired product and the valorization of wastes and by-products are identified. Then, a Resource-Task-Network representation that captures all these pathways is utilized, based on which a mixed-integer linear programming model is developed. This approach allows the holistic modeling and optimization of the entire food supply chain, taking into account any of its special characteristics, potential constraints as well as different objectives. Considering that typically CE introduces multiple, often conflicting objectives, we deploy here a multi-objective optimization strategy for trade-off analysis. A representative case study for the supply chain of coffee is discussed, illustrating the steps and the applicability of the framework. Single and multi-objective optimization formulations under five different coffee-product demand scenarios are presented. The production of instant coffee as the only final product is shown to be the least energy and environmental efficient scenario. On the contrary, the production solely of whole beans sets a hypothetical upper bound on the optimal energy and environmental utilization. In both problems presented, the amount of energy generated is significant due to the utilization of waste generated for the production of excess energy.

Bi-level Mixed-Integer Data-Driven Optimization of Integrated Planning and Scheduling Problems.

Supply chain management is an interconnected problem that requires the coordination of various decisions and elements across long-term (i.e., supply chain structure), medium-term (i.e., production planning), and short-term (i.e., production scheduling) operations. Traditionally, decision-making strategies for such problems follow a sequential approach where longer-term decisions are made first and implemented at lower levels, accordingly. However, there are shared variables across different decision layers of the supply chain that are dictating the feasibility and optimality of the overall supply chain performance. Multi-level programming offers a holistic approach that explicitly accounts for this inherent hierarchy and interconnectivity between supply chain elements, however, requires more rigorous solution strategies as they are strongly NP-hard. In this work, we use the DOMINO framework, a data-driven optimization algorithm initially developed to solve single-leader single-follower bi-level mixed-integer optimization problems, and further develop it to address integrated planning and scheduling formulations with multiple follower lower-level problems, which has not received extensive attention in the open literature. By sampling for the production targets over a pre-specified planning horizon, DOMINO deterministically solves the scheduling problem at each planning period per sample, while accounting for the total cost of planning, inventories, and demand satisfaction. This input-output data is then passed onto a data-driven optimizer to recover a guaranteed feasible, near-optimal solution to the integrated planning and scheduling problem. We show the applicability of the proposed approach for the solution of a two-product planning and scheduling case study.

Multiobjective Optimization of Mixed-Integer Linear Programming Problems: A Multiparametric Optimization Approach.

Industrial process systems need to be optimized, simultaneously satisfying financial, quality and safety criteria. To meet all those potentially conflicting optimization objectives, multiobjective optimization formulations can be used to derive optimal trade-off solutions. In this work, we present a framework that provides the exact Pareto front of multiobjective mixed-integer linear optimization problems through multiparametric programming. The original multiobjective optimization program is reformulated through the well-established ϵ-constraint scalarization method, in which the vector of scalarization parameters is treated as a right-hand side uncertainty for the multiparametric program. The algorithmic procedure then derives the optimal solution of the resulting multiparametric mixed-integer linear programming problem as an affine function of the ϵ parameters, which explicitly generates the Pareto front of the multiobjective problem. The solution of a numerical example is analytically presented to exhibit the steps of the approach, while its practicality is shown through a simultaneous process and product design problem case study. Finally, the computational performance is benchmarked with case studies of varying dimensionality with respect to the number of objective functions and decision variables.

Combining Experimental Isotherms, Minimalistic Simulations, and a Model to Understand and Predict Chemical Adsorption onto Montmorillonite Clays.

An attractive approach to minimize human and animal exposures to toxic environmental contaminants is the use of safe and effective sorbent materials to sequester them. Montmorillonite clays have been shown to tightly bind diverse toxic chemicals. Due to their promise as sorbents to mitigate chemical exposures, it is important to understand their function and rapidly screen and predict optimal clay-chemical combinations for further testing. We derived adsorption free-energy values for a structurally and physicochemically diverse set of toxic chemicals using experimental adsorption isotherms performed in the current and previous studies. We studied the diverse set of chemicals using minimalistic MD simulations and showed that their interaction energies with calcium montmorillonite clays calculated using simulation snapshots in combination with their net charge and their corresponding solvent's dielectric constant can be used as inputs to a minimalistic model to predict adsorption free energies in agreement with experiments. Additionally, experiments and computations were used to reveal structural and physicochemical properties associated with chemicals that can be adsorbed to calcium montmorillonite clay. These properties include positively charged groups, phosphine groups, halide-rich moieties, hydrogen bond donor/acceptors, and large, rigid structures. The combined experimental and computational approaches used in this study highlight the importance and potential applicability of analogous methods to study and design novel advanced sorbent systems in the future, broadening their applicability for environmental contaminants.