Prediction Results Research Articles

Real-Time Evaluation of the Credibility of Remaining Useful Life Prediction Result

Real-Time Evaluation of the Credibility of Remaining Useful Life Prediction Result

Multiaxial fatigue life assessment of dental implants

As screwed joints, dental restorations may suffer mechanical failures such as screw loosening and implant or prosthetic screw failure due to fatigue. This work is focused on the failure of the implant and develops a numerical methodology to predict its fatigue life under cyclic loading conditions. This methodology is based on the combination of Critical Plane Methods and the Theory of Critical Distances to account for stress multiaxiality and notch effects. The obtained predictions were validated experimentally, which can be used to identify the main geometrical, assembly and operational factors affecting the fatigue behavior of dental implants. As a result, a powerful and efficient design tool for fatigue life prediction of dental implants is presented. This methodology complements a previously presented one focused on the fatigue life prediction of the prosthetic screw, thereby, offering now a complete design tool package regardless the critical component of the dental restoration, predicting accurately the fatigue response of the restoration, with no need for long-term fatigue test campaigns. This is a pioneering work since no other fatigue design methodology for dental implants with such a solid foundation and experimental validation has been published to date.

Computational fluid dynamics simulating of the FDA benchmark blood pump with different coefficient sets and scaler shear stress models used in the power-law hemolysis model.

Hemolysis is the most important issue to consider in the design and optimization of blood-contacting devices. Although the use of Computational Fluid Dynamics (CFD) in hemolysis prediction studies provides convenience and has promising potential, it is an extremely challenging process. Hemolysis predictions with CFD depend on the mesh, implementation method, coefficient set, and scalar-shear-stress model. To this end, an attempt was made to find the combination that would provide the most accurate result in hemolysis prediction with the commonly cited power-law based hemolysis model. In the hemolysis predictions conducted using CFD on the Food and Drug Administration (FDA) benchmark blood pump, 3 different scalar-shear-stress models, and 5 different coefficient sets with the power-law based hemolysis model were used. Also, a mesh independence test based on hemolysis and pressure head was performed. The pressure head results of CFD simulations were compared with published pressure head of the FDA benchmark blood pump and a good agreement was observed. In addition, results of CFD-hemolysis predictions which are conducted with scalar-shear-stress model and coefficient set combinations were compared with experimental hemolysis data at three operating conditions such as 6-7L/min flow rates at 3500rpm rotational speeds and 6L/min at 2500rpm. One of the combinations of the scalar-shear-stress model and the coefficient set was found to be within the error limits of the experimental measurements, while all other combinations overestimated hemolysis.

Stacking-Kcr: A Stacking Model for Predicting the Crotonylation Sites of Lysine by Fusing Serial and Automatic Encoder

Background: Protein lysine crotonylation (Kcr), a newly discovered important posttranslational modification (PTM), is typically localized at the transcription start site and regulates gene expression, which is associated with a variety of pathological conditions such as developmental defects and malignant transformation. Objective: Identifying Kcr sites is advantageous for the discovery of its biological mechanism and the development of new drugs for related diseases. However, traditional experimental methods for identifying Kcr sites are expensive and inefficient, necessitating the development of new computational techniques. Methods: In this work, to accurately identify Kcr sites, we propose a model for ensemble learning called Stacking-Kcr. Firstly, extract features from sequence information, physicochemical properties, and sequence fragment similarity. Then, the two characteristics of sequence information and physicochemical properties are fused using automatic encoder and serial, respectively. Finally, the fused two features and sequence fragment similarity features are then respectively input into the four base classifiers, a meta classifier is constructed using the first level prediction results, and the final forecasting results are obtained. Results: The five-fold cross-validation of this model has achieved an accuracy of 0.828 and an AUC of 0.910. This shows that the Stacking-Kcr method has obvious advantages over traditional machine learning methods. On independent test sets, Stacking-Kcr achieved an accuracy of 84.89% and an AUC of 92.21%, which was higher than 1.7% and 0.8% of other state-of-the-art tools. Additionally, we trained Stacking-Kcr on the phosphorylation site, and the result is superior to the current model. Conclusion: These outcomes are additional evidence that Stacking-Kcr has strong application potential and generalization performance.

Tensor Completion for Alzheimer's Disease Prediction From Diffusion Tensor Imaging.

Alzheimer's disease (AD) is a slowly progressive neurodegenerative disorder with insidious onset. Accurate prediction of the disease progression has received increasing attention. Cognitive scores that reflect patients' cognitive status have become important criteria for predicting AD. Most existing methods consider the relationship between neuroimages and cognitive scores to improve prediction results. However, the inherent structure information in interrelated cognitive scores is rarely considered. In this article, we propose a relation-aware tensor completion multitask learning method (RATC-MTL), in which the cognitive scores are represented as a third-order tensor to preserve the global structure information in clinical scores. We combine both tensor completion and linear regression into a unified framework, which allows us to capture both inter and intra modes correlations in cognitive tensor with a low-rank constraint, as well as incorporate the relationship between biological features and cognitive status by imposing a regression model on multiple cognitive scores. Compared to the single-task and state-of-the-art multi-task algorithms, our proposed method obtains the best results for predicting cognitive scores in terms of four commonly used metrics. Furthermore, the overall performance of our method in classifying AD progress is also the best. Our results demonstrate the effectiveness of the proposed framework in fully exploring the global structure information in cognitive scores. This study introduces a novel concept of leveraging tensor completion to assist in disease diagnoses, potentially offering a solution to the issue of data scarcity encountered in prolonged monitoring scenarios.

Head-to-Head Comparison: P-POSSUM and ACS-NSQIP® in Predicting Perioperative Risk in Robotic Surgery for Gynaecological Cancers.

Purpose: In this retrospective pilot study, we aim to evaluate the accuracy and reliability of the P-POSSUM and ACS-NSQIP surgical risk calculators in predicting postoperative complications in gynaecological-oncological (GO) robotic surgery (RS). Methods: Retrospective data collection undertaken through a dedicated GO database and patient notes at a tertiary referral cancer centre. Following data lock with the actual post-op event/complication, the risk calculators were used to measure predictive scores for each patient. Baseline analysis of 153 patients, based on statistician advice, was undertaken to evaluate P-POSSUM and ACS-NSQIP validity and relevance in GO patients undergoing RS performed. Results: P-POSSUM reports on mortality and morbidity only; ACS-NSQIP reports some individual complications as well. ACS-NSQIP risk prediction was most accurate for venous thromboembolism (VTE) (area under the curve (AUC)-0.793) and pneumonia (AUC-0.657) and it showed 90% accuracy in prediction of five major complications (Brier score 0.01). Morbidity was much better predicted by ACS-NSQIP than by P-POSSUM (AUC-0.608 vs. AUC-0.551) with the same result in mortality prediction (Brier score 0.0000). Moreover, a statistically significant overestimation of morbidity has been shown by the P-POSSUM calculator (p = 0.018). Conclusions: Despite the limitations of this pilot study, the ACS-NSQIP risk calculator appears to be a better predictor of major complications and mortality, making it suitable for use by GO surgeons as an informed consent tool. Larger data collection and analyses are ongoing to validate this further.

Prediction of Plant Ubiquitylation Proteins and Sites by Fusing Multiple Features

Introduction: Protein ubiquitylation is an important post-translational modification (PTM), which is considered to be one of the most important processes regulating cell function and various diseases. Therefore, accurate prediction of ubiquitylation proteins and their PTM sites is of great significance for the study of basic biological processes and the development of related drugs. Researchers have developed some large-scale computational methods to predict ubiquitylation sites, but there is still much room for improvement. Much of the research related to ubiquitylation is cross-species while the life pattern is diversified, and the prediction method always shows its specificity in practical application. This study just aims at the issue of plants and has constructed computational methods for identifying ubiquitylation protein and ubiquitylation sites. Method: In this work, we constructed two predictive models to identify plant ubiquitylation proteins and sites. First, in the ubiquitylation proteins prediction model, in order to better reflect protein sequence information and obtain better prediction results, the KNN scoring matrix model based on functional domain Gene Ontology (GO) annotation and word embedding model, i.e. Skip-Gram and Continuous Bag of Words (CBOW), are used to extract the features, and the light gradient boosting machine (LGBM) is selected as the ubiquitylation proteins prediction engine. Results: As a result, accuracy (ACC), Precision, recall rate (Recall), F1_score and AUC are respectively 85.12%, 80.96%, 72.80%, 76.37% and 0.9193 in the 10-fold cross-validations on independent dataset. In the ubiquitylation sites prediction model, Skip-Gram, CBOW and enhanced amino acid composition (EAAC) feature extraction codes were used to extract protein sequence fragment features, and the predicted results on training and independent test data have also achieved good performance. Conclusion: In a word, the comparison results demonstrate that our models have a decided advantage in predicting ubiquitylation proteins and sites, and it may provide useful insights for studying the mechanisms and modulation of ubiquitination pathways

Serum Uric Acid Combined with Homocysteine as a Predictive Biomarker of Lupus Nephritis.

Serum uric acid (UA) and homocysteine (Hcy) are potential biomarkers of systemic lupus erythematosus (SLE). In this study, the expressions of UA and Hcy in SLE patients and the predictive value of these two parameters for lupus nephritis (LN) were studied. A total of 476 SLE patients were recruited to this case-control study, of which 176 SLE patients diagnosed with LN and 300 without LN. Serum UA and Hcy levels were analyzed. Multivariate logistic regression analysis was used to evaluate the relationship between serum UA and Hcy and LN. The receiver operating characteristic (ROC) curves were used to predict the role of combination of serum UA and Hcy in LN. We found that serum UA and Hcy levels in SLE patients with LN were significantly higher than those in controls (p<0.05). Multivariate logistic regressions showed that serum UA (OR+=+1.003, 95+% CI: 1.001-1.006, p+=+0.003), apolipoprotein B (Apo B) (OR+=+21.361, 95+% CI: 2.312-195.373, p+=+0.007) and Hcy (OR+=+1.042, 95+% CI: 1.011-1.080, p+=+0.014) were independent markers of LN. Combined serum UA and Hcy revealed a better result (AUC+=+0.718, 95+% CI: 0.670-0.676, p<0.001) in prediction of LN compared to that of the serum UA (AUC+=+0.710) and Hcy (AUC+=+0.657) independently. In conclusion, serum UA and Hcy could be predictive biomarkers of LN, and joint detection of serum UA and Hcy might be useful in the clinical setting.

QLDTI: A Novel Reinforcement Learning-based Prediction Model for Drug-Target Interaction

Background: Predicting drug-target interaction (DTI) plays a crucial role in drug research and development. More and more researchers pay attention to the problem of developing more powerful prediction methods. Traditional DTI prediction methods are basically realized by biochemical experiments, which are time-consuming, risky, and costly. Nowadays, DTI prediction is often solved by using a single information source and a single model, or by combining some models, but the prediction results are still not accurate enough. Objective: The study aimed to utilize existing data and machine learning models to integrate heterogeneous data sources and different models, further improving the accuracy of DTI prediction. Methods: This paper has proposed a novel prediction method based on reinforcement learning, called QLDTI (predicting drug-target interaction based on Q-learning), which can be mainly divided into two parts: data fusion and model fusion. Firstly, it fuses the drug and target similarity matrices calculated by different calculation methods through Q-learning. Secondly, the new similarity matrices are inputted into five models, NRLMF, CMF, BLM-NII, NetLapRLS, and WNN-GIP, for further training. Then, all sub-model weights are continuously optimized again by Q-learning, which can be used to linearly weight all sub-model prediction results to output the final prediction result. Results: QLDTI achieved AUC accuracy of 99.04%, 99.12%, 98.28%, and 98.35% on E, NR, IC, and GPCR datasets, respectively. Compared to the existing five models NRLMF, CMF, BLM-NII, NetLapRLS, and WNN-GIP, the QLDTI method has achieved better results on four benchmark datasets of E, NR, IC, and GPCR. Conclusion: Data fusion and model fusion have been proven effective for DTI prediction, further improving the prediction accuracy of DTI.

Naringin ameliorates H2O2-induced oxidative damage in cells and prolongs the lifespan of female Drosophila melanogaster via the insulin signaling pathway

Naringin exists in a wide range of Chinese herbal medicine and has proven to possess several pharmacological properties. In this study, PC12, HepG2 cells, and female Drosophila melanogaster were used to investigate the antioxidative and anti-aging effects of naringin and explore the underlying mechanisms. The results showed that naringin inhibited H2O2-induced decline in cell viability and decreased the content of reactive oxygen species in cells. Meanwhile, naringin prolonged the lifespan of flies, enhanced the abilities of climbing and the resistance to stress, improved the activities of antioxidant enzymes, and decreased malondialdehyde content. Naringin also improved intestinal barrier dysfunction and reduced abnormal proliferation of intestinal stem cells. Moreover, naringin down-regulated the mRNA expressions of inr, chico, pi3k, and akt-1, and up-regulated the mRNA expressions of dilp2, dilp3, dilp5, and foxo, thereby activating autophagy-related genes and increasing the number of lysosomes. Furthermore, the mutant stocks assays and computer molecular simulation results further indicated that naringin delayed aging by inhibiting the insulin signaling (IIS) pathway and activating the autophagy pathway, which was consistent with the result of network pharmacological predictions.

DLformer: A Dynamic Length Transformer-Based Network for Efficient Feature Representation in Remaining Useful Life Prediction.

Representation learning-based remaining useful life (RUL) prediction plays a crucial role in improving the security and reducing the maintenance cost of complex systems. Despite the superior performance, the high computational cost of deep networks hinders deploying the models on low-compute platforms. A significant reason for the high cost is the computation of representing long sequences. In contrast to most RUL prediction methods that learn features of the same sequence length, we consider that each time series has its characteristics and the sequence length should be adjusted adaptively. Our motivation is that an "easy" sample with representative characteristics can be correctly predicted even when short feature representation is provided, while "hard" samples need complete feature representation. Therefore, we focus on sequence length and propose a dynamic length transformer (DLformer) that can adaptively learn sequence representation of different lengths. Then, a feature reuse mechanism is developed to utilize previously learned features to reduce redundant computation. Finally, in order to achieve dynamic feature representation, a particular confidence strategy is designed to calculate the confidence level for the prediction results. Regarding interpretability, the dynamic architecture can help human understand which part of the model is activated. Experiments on multiple datasets show that DLformer can increase up to 90% inference speed, with less than 5% degradation in model accuracy.

Co-Pyrolysis of biomass and plastic waste: Process prediction and optimization based on Artificial Intelligence and response optimizer surrogate model

Co-pyrolysis process prediction and optimization has been done through different artificial intelligence processes and response optimizer surrogate model. Neural network and machine learning-based different prediction models have been evaluated to predict the co-pyrolysis output based on the experimental data from literature. While multi-objective optimization has been done through response optimizer. According to prediction models results, CatBoost Regressor (CatB) and Extreme Gradient Boosting (XGB) models’ performance is better than other (seven) models with CatB co-efficient of determinant (R2) 0.92–0.98 while it is 0.91–0.98 for XGB in different scenarios. Therefore, CatB and XGB both models can provide an optimal result for co-pyrolysis prediction. Surrogate-model for multi-objective optimization results concluded that lower portion of biomass waste and higher plastic waste in the feedstock has the optimum co-pyrolysis process output around 550 °C and 60 min of resident time for higher portion of liquid yield with lower gases production. Overall higher portion of the plastic waste in feedstock at high temperature and low resident time promotes more liquid yield. While solid (biochar) production is optimal when there is a higher amount of biomass waste in the feedstock at lower temperature, and longer resident time.

Research on the impact of sliding window and differencing procedures on the support vector regression model for load forecasting

Load forecasting is a critical aspect of energy management and grid operations. Machine learning techniques as support vector regression (SVR), have been widely used for load forecasting. However, the effectiveness of SVR is highly dependent on its hyperparameters, including the error sensitivity parameter, penalty factor, and kernel function. Furthermore, as the load data follows a time series pattern, the accuracy of the SVR model is influenced by the data's characteristics. In this regard, the present study aims to investigate the impact of combining the sliding window procedure and differencing the input data on the prediction accuracy of the SVR model. The study utilizes daily maximum load data from the Queensland and Victoria states in Australia. The analyses revealed that while the sliding window procedure had a minimal impact on the prediction results, the differencing of the input data significantly improved the accuracy of the predictions.

TBCA: Prediction of transcription factor binding sites using a deep neural network with lightweight attention mechanism.

The identification of transcription factor binding sites (TFBSs) is crucial for understanding the regulatory mechanisms of gene expression, which contributes to unraveling cellular functions and disease development. Currently, the most common approach involves the use of deep learning techniques to predict TFBSs by combining sequence and shape features. Although significant progress has been made with these methods, the integration of local features extracted from DNA sequences and shapes with global features has not yet reached a sufficient level, and there is still significant room for improvement in the accuracy of prediction results. In this paper, we propose a novel framework based on convolution and attention mechanisms, referred to as TBCA, which combines DNA sequence information and shape information for predicting transcription factor binding sites. In this work, we employ a two-layer convolutional neural network (CNNs) and self-attention mechanism to extract complex sequence features from DNA. What's more, we utilize a Fourier-transform-enhanced multi-head attention along with channel attention to extract high-order shape features of DNA. Finally, these high-order sequence and shape features are integrated into the channel dimension to achieve accurate TFBSs prediction. Our research results demonstrate that TBCA exhibits superior predictive performance in 165 validated ChIP-seq datasets. Furthermore, the employed attention mechanisms can automatically learn important features at different positions and scales, enhancing the accuracy and robustness of feature representation. We also conduct an in-depth analysis of the contributions of five different shapes to site prediction, revealing that shape features can enhance the prediction of transcription factor DNA binding.

Prediction-Based Power Consumption Monitoring of Industrial Equipment Using Interpretable Data-Driven Models

Efficient energy optimization and scheduling in industrial factories depend on accurate, reasonable, and real-time monitoring of equipment power consumption. However, the power prediction of industrial equipment requires a large number of process data, which could be inevitably contaminated by some imperfect data, due to the harsh environments. Monitoring or predicting equipment power consumption is usually not feasible using data-driven black-box models with imperfect data. This paper proposes a prediction-based approach for power consumption monitoring using an interpretable data-driven model. First, a data preprocessing method is used to remove outliers and fill in missing values. Then, a Volterra polynomial basis function (VPBF) model is built to predict equipment power consumption. This model decomposes power values into a series of basis functions consisting of input parameters. Moreover, to compensate for data dropouts during the power consumption monitoring process, a networked predictive monitoring system is also proposed. Finally, this paper presents two case studies based on actual production equipment in an industrial manufacturing factory. The results demonstrate that the proposed approach can achieve satisfactory monitoring accuracy and adaptation ability. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the problem of power consumption monitoring of industrial equipment in harsh production environments. A conventional solution is to predict the power consumption using data-driven black-box models, with limited feasibility and interpretability. This paper proposes a new power consumption monitoring approach, utilizing an interpretable data-driven model and a networked predictive method. This approach accurately reveals the transparent relationships between the output and input parameters. The power prediction result is consequently interpretable and more reasonable. Meanwhile, this approach actively compensates for data dropouts in the network, which can help operators real-time grasp the power consumption of equipment. Furthermore, this approach can be integrated into energy optimization systems as a basis of optimization and decision-making. Practical applications in an aluminum manufacturing company located in Guangdong Province demonstrate that this approach is feasible and applicable. Future research is to expand this approach further for energy optimization and scheduling.

Prediction of LncRNA-Protein Interactions Based on Kernel Combinations and Graph Convolutional Networks.

The complexes of long non-coding RNAs bound to proteins can be involved in regulating life activities at various stages of organisms. However, in the face of the growing number of lncRNAs and proteins, verifying LncRNA-Protein Interactions(LPI) based on traditional biological experiments is time-consuming and laborious. Therefore, with the improvement of computing power, predicting LPI has met new development opportunity. In virtue of the state-of-the-art works, a framework called LncRNA-Protein Interactions based on Kernel Combinations and Graph Convolutional Networks (LPI-KCGCN) has been proposed in this article. We first construct kernel matrices by taking advantage of extracting both the lncRNAs and protein concerning the sequence features, sequence similarity features, expression features, and gene ontology. Then reconstruct the existent kernel matrices as the input of the next step. Combined with known LPI interactions, the generated similarity matrices, which can be used as features of the topology map of the LPI network, are exploited in extracting potential representations in the lncRNA and protein space using a two-layer Graph Convolutional Network. The predicted matrix can be finally obtained by training the network to produce scoring matrices w.r.t. lncRNAs and proteins. Different LPI-KCGCN variants are ensemble to derive the final prediction results and testify on balanced and unbalanced datasets. The 5-fold cross-validation shows that the optimal feature information combination on a dataset with 15.5% positive samples has an AUC value of 0.9714 and an AUPR value of 0.9216. On another highly unbalanced dataset with only 5% positive samples, LPI-KCGCN also has outperformed the state-of-the-art works, which achieved an AUC value of 0.9907 and an AUPR value of 0.9267. The code and dataset can be downloaded from https://github.com/6gbluewind/LPI-KCGCN.

An investigation on implementation of generating adversarial network-based surrogate models for prediction of turbine endwall film cooling effectiveness

Film cooling is an essential cooling technique for turbine blade, which guides coolant to cover the turbine blades surface by arranging discrete film holes on it. For the newly designed cooling units, the process of predicting film cooling effectiveness is really complex and time-consuming. For the purpose of accelerating the design procedure, the U-Net which is a very popular algorithm in the field of deep learning was improved with the basic layer structure, then it was adopted as the proxy function for the film cooling effectiveness prediction. The basic samples were generated by Latin hypercube sampling method and calculated by commercial software. The results were verified by experiment in a linear cascade. The training and testing samples were calculated at experimental conditions (inlet Mach number values 0.12). The results showed that comparing with the basic U-Net network, the novel U-Net network has a great better accuracy on the prediction of contour results. Both of the improved U-Net networks had higher prediction accuracy than original models. The correlation index reached more than 99.5% and the first order error was lower than 0.3%. The number of basic neural layers is not positively correlated with the network prediction accuracy which exists an optimal ratio. The experimental verification shows that the generating adversarial network prediction results are consistent with the experimental results. The final prediction results showed that the U-Net model can be used as a surrogate model and meets the requirements for accuracy of film cooling effectiveness prediction.

Microscopic mechanism of plastic heterogeneous deformation of columnar-grained polycrystalline ice

Studying ice deformation starting from crystal scale can provide insight into the microscopic mechanisms of ice deformation. In this paper, a crystal plasticity constitutive model of ice considering the dislocation slip mechanism and grain-size dependence was implemented within the finite element framework, and a modeling approach starting from ice single crystals based on the crystal plasticity finite element method (CPFEM) was proposed to study the elastic-viscoplastic deformation of polycrystalline ice samples. Finite element models of ice single crystals and columnar-grained polycrystalline ice characterizing the microstructure were established successively, and the proposed method was validated by comparing the uniaxial compression prediction results of ice single crystals and columnar-grained polycrystalline ice with the existing experimental data. Finally, the microscopic mechanism of plastic heterogeneous deformation of columnar-grained polycrystalline ice under constant strain rate compression conditions was analyzed. The results indicate that the modeling approach from ice single crystals to polycrystalline ice samples based on CPFEM can reasonably describe the mechanical properties of ice deformation. The deformation of columnar-grained polycrystalline ice globally exhibits apparent slip bands around 30° - 60° relative to the loading direction and locally presents intragranular localization bands parallel or perpendicular to the C-axis. This plastic heterogeneous deformation phenomenon is related to the elastic-viscoplastic anisotropy of ice single crystals and the interaction of neighboring grains at grain boundaries (GBs).

Dynamic analysis of a drilling string for deepwater riserless drilling with vortex-induced vibration considered

Riserless drilling will become the mainstream technology for deepwater drilling in the future owing to its operational characteristics. At present, researchers only analyze the seawater section or formation section but do not analyze the whole drill string to study the dynamics of riserless drilling. In fact, the ocean load affects not only the vortex-induced vibration characteristics of the drill string in seawater but also the load distribution of the drill string in the formation. Ignoring the formation or ocean load will lead to inaccurate prediction results. On this basis, in addition to the traditional drilling string boundary condition of seawater and formation, a new boundary condition of drilling string at mud line for riserless drilling is proposed. Considering vortex-induced vibration, a full-well drilling string dynamic model without riser drilling is established by the finite element method, and the dynamic characteristics of the full-well drilling string under multiple loads are analyzed. In addition, the effects of WOB, surface flow rate, and drilling fluid density on the dynamics of riserless drilling string in seawater and formation sections are discussed. This study provides theoretical guidance for the safety of riserless drilling in complex marine environments.

Solubility evaluation of palm-based Mono-diacylglycerols (MDAGs) in food grade solvent (hexane, ethanol, acetone, water) using QSPR model approach

Mono-diacylglycerols (MDAGs) are emulsifiers widely used in the food industry. MDAGs based on refined bleached deodorized palm stearin (RBDPS) have not been widely developed. MDAGs have been synthesized using glicerolysis between RBDPS and glycerols. Due to their low solubility in food-grade solvents (hexane, ethanol, acetone, and water), it has been difficult to purify or fractionate MDAGs only by a simple method. This research attempted to develop a model of MDAGs solubility in food-grade solvents and understand the parameters that influence the solubility of MDAGs in food-grade solvents. The process used a combination of experimental data collection and quantitative structure–property relationship (QSPR) models. The QSPR model for MDAGs solubility in a single and binary solvent demonstrated that the descriptors of Δ dipole moment (Δµ), E HOMO, E LUMO, electronic energy, gap energy HOMO-LUMO (ΔE1, ΔE2) softness (S), electrophilicity index (ω), and electron transfer (ΔN) have a significant impact in determining the solubility of MDAGs. Both the single and the binary solvents solubility models can give satisfactory prediction results: the square of the correlation coefficient (R2pred) was 0.933 and 0.948, and the root-mean-square error (RMSE) was 0.075 and 0.031, respectively, for the whole data set. In addition, this paper provided a new and effective method for predicting the solubility of MDAGs in single and binary food-grade solvent systems.