A comparison of simulated annealing algorithms for variable selection in principal component analysis and discriminant analysis

Identification of altered metabolic functional components using metabolomics to analyze the different ages of fruiting bodies of Sanghuangporus vaninii cultivated on cut log substrates

Sanghuangporus vaninii is a profitable traditional and medicinal edible fungus with uncommon therapeutic properties and medicinal value. The accumulation of active ingredients in this fungus that is used in traditional Chinese medicine is affected by its years of growth, and their pharmacological activities are also affected. However, the effects of age on the medicinal value of fruiting bodies of S. vaninii cultivated on cut log substrate remain unclear. In this study, an untargeted liquid chromatography mass spectrometry (LC-MS)-based metabolomics approach was performed to characterize the profiles of metabolites from 1-, 2- and 3-year-old fruiting bodies of S. vaninii. A total of, 156 differentially accumulated metabolites (DAMs) were screened based on the criterion of a variable importance projection greater than 1.0 and p < 0.01, including 75% up regulated and 25% down regulated. The results of enrichment of metabolic pathways showed that the metabolites involved the biosynthesis of plant secondary metabolites, biosynthesis of amino acids, central carbon metabolism in cancer, steroid hormone biosynthesis, linoleic acid metabolism, prolactin signaling pathway, and arginine biosynthesis, and so on. The biosynthesis of plant secondary metabolites pathway was significantly activated. Five metabolites were significantly elevated within the growth of fruiting bodies, including 15-keto-prostaglandin F2a, (4S, 5R)-4,5,6-trihydroxy-2-iminohexanoate, adenylsuccinic acid, piplartine, and chenodeoxycholic acid. 15-keto-prostaglandin F2a is related to the pathway of arachidonic acid metabolism and was significantly increased up to 1,320- and 535-fold in the 2- and 3-year-old fruiting bodies, respectively, compared with those in the 1-year-old group. The presence of these bioactive natural products in S. vaninii is consistent with the traditional use of Sanghuang, which prompted an exploration of its use as a source of natural prostaglandin in the form of foods and nutraceuticals. These findings may provide insight into the functional components of S. vaninii to develop therapeutic strategies.

New insights into metabolomics profile generation in fermented tea: the relevance of bacteria and metabolites in Fuzhuan brick tea

BACKGROUND

The contribution of bacteria to fermented tea is not clear and the associated research is relatively limited. To reveal the role of microorganisms in fermented tea processing, the microbial community and metabolites of Fuzhuan brick tea (FBT), a Chinese traditional fermented tea, were revealed via high-throughput sequencing and liquid chromatography-mass spectrometry (LC-MS).

RESULTS

In FBT, bacterial communities had a higher abundance and diversity, Lactococcus and Bacillus were the main bacteria, and Eurotium was the predominant fungus. The predictive metabolic function indicated the pathways of cellular growth, environmental information, genetics and material metabolism of bacterial communities were abundant, whereas the fungal community predictive metabolic function was almost saprotroph. Using LC-MS, 1143 and 536 metabolites were defined in positive and negative ion mode, respectively. There were essential correlations between bacterial populations and metabolites, such that Bacillus was correlated significantly with 44 metabolites (P < 0.05) and Enterococcus was significantly associated with 15 metabolites (P < 0.05). Some of the main active components were significantly correlated with the bacteria, such as Enterococcus, Lactococcus and Carnobacterium.

CONCLUSION

Not only Eurotium, but also the bacteria were involved in the changes of metabolomics profile in fermented FBT. The present study assists in providing new insights into metabolomics profile generation in fermented tea. The present research lays a foundation for controlling the FBT fermentation by artificial inoculation to improve quality. © 2021 Society of Chemical Industry.

Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

Review of Voltage and Reactive Power Control Algorithms in Electrical Distribution Networks

The traditional unidirectional, passive distribution power grids are rapidly developing into bidirectional, interactive, multi-coordinated smart grids that cover distributed power generation along with advanced information communications and electronic power technologies. To better integrate the use of renewable energy resources into the grid, to improve the voltage stability of distribution grids, to improve the grid protection and to reduce harmonics, one needs to select and control devices with adjustable reactive power (capacitor batteries, transformers, and reactors) and provide certain solutions so that the photovoltaic (PV) converters maintain due to voltage. Conventional compensation methods are no longer appropriate, thus developing measures are necessary that would ensure local reactive and harmonic compensation in case an energy quality problem happens in the low voltage distribution grid. Compared to the centralized methods, artificial intelligence (heuristic) methods are able to distribute computing and communication tasks among control devices.

Metabolic Profiling of Pleurotus tuoliensis During Mycelium Physiological Maturation and Exploration on a Potential Indicator of Mycelial Maturation

Pleurotus tuoliensis is a valuable and rare edible fungus with extremely high nutritional and medicinal value. However, the relative immaturity of P. tuoliensis cultivation technology leads to fluctuating yields and quality. The main difficulty in P. tuoliensis cultivation is estimate of mycelial maturity. There is currently no measurable indicator that clearly characterizes the physiological maturation of mycelia. The aim of this study was to identify potential indicators of physiological maturation for P. tuoliensis mycelia by using metabolomics approach. A metabolite profiling strategy involving gas chromatography-mass spectrometry (GC/MS) was used to analyze changes to extracellular metabolites in mycelia collected at mycelium physiological maturation period (MPMP) day 0, MPMP day 35 at 17°C and MPMP day 35 at 29°C. 72 differential metabolites (37.8% up-regulated and 62.2% down-regulated) were identified based on the selected criteria [variable important in projection (VIP) greater than 1.0 and p < 0.01]. Metabolic pathways enrichment analysis showed that these metabolites are involved in glycolysis, organic acid metabolism, amino acid metabolism, tricarboxylic acid cycle (TCA), sugar metabolism, nicotinate and nicotinamide metabolism, and oxidative phosphorylation. In addition, the pyrimidine synthesis pathway was significantly activated during mycelium physiological maturation of P. tuoliensis. The abundance of N-carbamoyl-L-aspartate (CA-asp), a component of this pathway, was significantly increased at MPMP day 35, which motivated us to explore its potential as an indicator for physiological maturation of mycelia. The content of CA-asp in mycelia changed in a consistent manner during physiological maturation. The feasibility of using CA-asp as an indicator for mycelial maturation requires further investigation.

High-Temperature Induced Changes of Extracellular Metabolites in Pleurotus ostreatus and Their Positive Effects on the Growth of Trichoderma asperellum

Pleurotus ostreatus is a widely cultivated edible fungus in China. Green mold disease of P. ostreatus which can seriously affect yield is a common disease during cultivation. It occurs mostly after P. ostreatus mycelia have been subjected to high temperatures. However, little information is available on the relationship between high temperature and green mold disease. The aim of this study is to prove that extracellular metabolites of P. ostreatus affected by high temperature can promote the growth of Trichoderma asperellum. After P. ostreatus mycelia was subjected to high temperature, the extracellular fluid of P. ostreatus showed a higher promoting effect on mycelial growth and conidial germination of T. asperellum. The thiobarbituric acid reactive substance (TBARS) content reached the maximum after 48 h at 36°C. A comprehensive metabolite profiling strategy involving gas chromatography-mass spectrometry (GC/MS) combined with liquid chromatography-mass spectrometry (LC/MS) was used to analyze the changes of extracellular metabolites in response to high temperature. A total of 141 differential metabolites were identified, including 84.4% up-regulated and 15.6% down-regulated. Exogenous metabolites whose concentrations were increased after high temperature were randomly selected, and nearly all of them were able to promote the mycelial growth and conidial germination of T. asperellum. The combination of all selected exogenous metabolites also has the promotion effects on the mycelial growth and conidial germination of T. asperellum in a given concentration range in vitro. Overall, these results provide a first view that high temperature affects the extracellular metabolites of P. ostreatus, and the extensive change in metabolites promotes T. asperellum growth.

Application of variable selection in the origin discrimination of Wolfiporia cocos (F.A. Wolf) Ryvarden & Gilb. based on near infrared spectroscopy

Dried sclerotium of Wolfiporia cocos (F.A. Wolf) Ryvarden & Gilb. is a traditional Chinese medicine. Its chemical components showed difference among geographical origins, which made it difficult to keep therapeutic potency consistent. The identification of the geographical origin of W. cocos is the fundamental prerequisite for its worldwide recognition and acceptance. Four variable selection methods were employed for near infrared spectroscopy (NIR) variable selection and the characteristic variables were screened for the establishment of Fisher function models in further identification of the origin of W. cocos from Yunnan, China. For the obvious differences between poriae cutis (fu-ling-pi in Chinese, or FLP) and the inner part (bai-fu-ling in Chinese, or BFL) of the sclerotia of W. cocos in the pattern space of principal component analysis (PCA), we established discriminant models for FLP and BFL separately. Through variable selection, the models were significant improved and also the models were simplified by using only a small part of the variables. The characteristic variables were screened (13 for BFL and 10 for FLP) to build Fisher discriminant function models and the validation results showed the models were reliable and effective. Additionally, the characteristic variables were interpreted.

A simulated annealing heuristic for maximum correlation core/periphery partitioning of binary networks

A popular objective criterion for partitioning a set of actors into core and periphery subsets is the maximization of the correlation between an ideal and observed structure associated with intra-core and intra-periphery ties. The resulting optimization problem has commonly been tackled using heuristic procedures such as relocation algorithms, genetic algorithms, and simulated annealing. In this paper, we present a computationally efficient simulated annealing algorithm for maximum correlation core/periphery partitioning of binary networks. The algorithm is evaluated using simulated networks consisting of up to 2000 actors and spanning a variety of densities for the intra-core, intra-periphery, and inter-core-periphery components of the network. Core/periphery analyses of problem solving, trust, and information sharing networks for the frontline employees and managers of a consumer packaged goods manufacturer are provided to illustrate the use of the model.

Genetic Particle Swarm Optimization-Based Feature Selection for Very-High-Resolution Remotely Sensed Imagery Object Change Detection

In the field of multiple features Object-Based Change Detection (OBCD) for very-high-resolution remotely sensed images, image objects have abundant features and feature selection affects the precision and efficiency of OBCD. Through object-based image analysis, this paper proposes a Genetic Particle Swarm Optimization (GPSO)-based feature selection algorithm to solve the optimization problem of feature selection in multiple features OBCD. We select the Ratio of Mean to Variance (RMV) as the fitness function of GPSO, and apply the proposed algorithm to the object-based hybrid multivariate alternative detection model. Two experiment cases on Worldview-2/3 images confirm that GPSO can significantly improve the speed of convergence, and effectively avoid the problem of premature convergence, relative to other feature selection algorithms. According to the accuracy evaluation of OBCD, GPSO is superior at overall accuracy (84.17% and 83.59%) and Kappa coefficient (0.6771 and 0.6314) than other algorithms. Moreover, the sensitivity analysis results show that the proposed algorithm is not easily influenced by the initial parameters, but the number of features to be selected and the size of the particle swarm would affect the algorithm. The comparison experiment results reveal that RMV is more suitable than other functions as the fitness function of GPSO-based feature selection algorithm.

Detection and Classification of Measurement Errors in Bioimpedance Spectroscopy

Bioimpedance spectroscopy (BIS) measurement errors may be caused by parasitic stray capacitance, impedance mismatch, cross-talking or their very likely combination. An accurate detection and identification is of extreme importance for further analysis because in some cases and for some applications, certain measurement artifacts can be corrected, minimized or even avoided. In this paper we present a robust method to detect the presence of measurement artifacts and identify what kind of measurement error is present in BIS measurements. The method is based on supervised machine learning and uses a novel set of generalist features for measurement characterization in different immittance planes. Experimental validation has been carried out using a database of complex spectra BIS measurements obtained from different BIS applications and containing six different types of errors, as well as error-free measurements. The method obtained a low classification error (0.33%) and has shown good generalization. Since both the features and the classification schema are relatively simple, the implementation of this pre-processing task in the current hardware of bioimpedance spectrometers is possible.

Investigation on biochemical compositional changes during the microbial fermentation process of Fu brick tea by LC-MS based metabolomics

Fu brick tea (FBT) is a unique post-fermented tea product which is fermented with fungi during the manufacturing process. In this study, we investigated the biochemical compositional changes occurring during the microbial fermentation process (MFP) of FBT based on non-targeted LC-MS, which was a comprehensive and unbiased methodology. Our data analysis took a two-phase approach: (1) comparison of FBT with other tea products using PCA analysis to exhibit the characteristic effect of MFP on the formation of Fu brick tea and (2) comparison of tea samples throughout the MFP of FBT to elucidate the possible key metabolic pathways produced by the fungi. Non-targeted LC-MS analysis clearly distinguished FBT with other tea samples and highlighted some interesting metabolic pathways during the MFP including B ring fission catechin. Our study demonstrated that those fungi had a significant influence on the biochemical profiles in the FBT and consequently contributed to its unique quality.