Metaheuristic-Based Feature Selection Methods for Diagnosing Sarcopenia with Machine Learning Algorithms.

This study explores the efficacy of metaheuristic-based feature selection in improving machine learning performance for diagnosing sarcopenia. Extraction and utilization of features significantly impacting diagnosis efficacy emerge as a critical facet when applying machine learning for sarcopenia diagnosis. Using data from the 8th Korean Longitudinal Study on Aging (KLoSA), this study examines harmony search (HS) and the genetic algorithm (GA) for feature selection. Evaluation of the resulting feature set involves a decision tree, a random forest, a support vector machine, and naïve bayes algorithms. As a result, the HS-derived feature set trained with a support vector machine yielded an accuracy of 0.785 and a weighted F1 score of 0.782, which outperformed traditional methods. These findings underscore the competitive edge of metaheuristic-based selection, demonstrating its potential in advancing sarcopenia diagnosis. This study advocates for further exploration of metaheuristic-based feature selection's pivotal role in future sarcopenia research.

Identification of TRPC6 as a Novel Diagnostic Biomarker of PM-Induced Chronic Obstructive Pulmonary Disease Using Machine Learning Models.

Chronic obstructive pulmonary disease (COPD) was the third most prevalent cause of mortality worldwide in 2010; it results from a progressive and fatal deterioration of lung function because of cigarette smoking and particulate matter (PM). Therefore, it is important to identify molecular biomarkers that can diagnose the COPD phenotype to plan therapeutic efficacy. To identify potential novel biomarkers of COPD, we first obtained COPD and the normal lung tissue gene expression dataset GSE151052 from the NCBI Gene Expression Omnibus (GEO). A total of 250 differentially expressed genes (DEGs) were investigated and analyzed using GEO2R, gene ontology (GO) functional annotation, and Kyoto Encyclopedia of Genes and Genomes (KEGG) identification. The GEO2R analysis revealed that TRPC6 was the sixth most highly expressed gene in patients with COPD. The GO analysis indicated that the upregulated DEGs were mainly concentrated in the plasma membrane, transcription, and DNA binding. The KEGG pathway analysis indicated that the upregulated DEGs were mainly involved in pathways related to cancer and axon guidance. TRPC6, one of the most abundant genes among the top 10 differentially expressed total RNAs (fold change ≥ 1.5) between the COPD and normal groups, was selected as a novel COPD biomarker based on the results of the GEO dataset and analysis using machine learning models. The upregulation of TRPC6 was verified in PM-stimulated RAW264.7 cells, which mimicked COPD conditions, compared to untreated RAW264.7 cells by a quantitative reverse transcription polymerase chain reaction. In conclusion, our study suggests that TRPC6 can be regarded as a potential novel biomarker for COPD pathogenesis.

Comparative Study of Classification Algorithms for Various DNA Microarray Data.

Microarrays are applications of electrical engineering and technology in biology that allow simultaneous measurement of expression of numerous genes, and they can be used to analyze specific diseases. This study undertakes classification analyses of various microarrays to compare the performances of classification algorithms over different data traits. The datasets were classified into test and control groups based on five utilized machine learning methods, including MultiLayer Perceptron (MLP), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and k-Nearest Neighbors (KNN), and the resulting accuracies were compared. k-fold cross-validation was used in evaluating the performance and the result was analyzed by comparing the performances of the five machine learning methods. Through the experiments, it was observed that the two tree-based methods, DT and RF, showed similar trends in results and the remaining three methods, MLP, SVM, and DT, showed similar trends. DT and RF generally showed worse performance than other methods except for one dataset. This suggests that, for the effective classification of microarray data, selecting a classification algorithm that is suitable for data traits is crucial to ensure optimum performance.

Maximizing the Coverage of Sensor Deployments Using a Memetic Algorithm and Fast Coverage Estimation.

We derive the upper and lower bounds on the coverage of a 2-D deployment of static sensors. We use these bounds in constructing a method of estimating the coverage of deployment by assuming that there are only pairwise intersections between the disks representing the range of each sensor. The speed of this approximation allows it to be built into a local search technique, as part of a memetic algorithm (MA) that tries to deploy a given set of sensors with maximum coverage. We show that this MA outperforms the previous techniques in terms of both speed and coverage achieved.

Optimizing taxon addition order and branch lengths in the construction of phylogenetic trees using maximum likelihood.

Taxon addition order and branch lengths are optimized by genetic algorithms (GAS) within the fastDNAml algorithm for constructing phylogenetic trees of high likelihood. Results suggest that optimizing the order in which taxa are added improves the likelihood of the resulting trees.

Improved Correction of Atmospheric Pressure Data Obtained by Smartphones through Machine Learning.

A correction method using machine learning aims to improve the conventional linear regression (LR) based method for correction of atmospheric pressure data obtained by smartphones. The method proposed in this study conducts clustering and regression analysis with time domain classification. Data obtained in Gyeonggi-do, one of the most populous provinces in South Korea surrounding Seoul with the size of 10,000 km(2), from July 2014 through December 2014, using smartphones were classified with respect to time of day (daytime or nighttime) as well as day of the week (weekday or weekend) and the user's mobility, prior to the expectation-maximization (EM) clustering. Subsequently, the results were analyzed for comparison by applying machine learning methods such as multilayer perceptron (MLP) and support vector regression (SVR). The results showed a mean absolute error (MAE) 26% lower on average when regression analysis was performed through EM clustering compared to that obtained without EM clustering. For machine learning methods, the MAE for SVR was around 31% lower for LR and about 19% lower for MLP. It is concluded that pressure data from smartphones are as good as the ones from national automatic weather station (AWS) network.

A genetic filter for cancer classification on gene expression data.

We present a new genetic filter to identify a predictive gene subset for cancer-type classification on gene expression profiles. This approach pursues to not only maximize correlation between selected genes and cancer types but also minimize inter-correlation among selected genes. The proposed genetic filter was tested on well-known leukemia datasets, and significant improvement over previous work was obtained.

Charge scheduling of an energy storage system under time-of-use pricing and a demand charge.

A real-coded genetic algorithm is used to schedule the charging of an energy storage system (ESS), operated in tandem with renewable power by an electricity consumer who is subject to time-of-use pricing and a demand charge. Simulations based on load and generation profiles of typical residential customers show that an ESS scheduled by our algorithm can reduce electricity costs by approximately 17%, compared to a system without an ESS and by 8% compared to a scheduling algorithm based on net power.

An efficient genetic algorithm for maximum coverage deployment in wireless sensor networks.

Sensor networks have a lot of applications such as battlefield surveillance, environmental monitoring, and industrial diagnostics. Coverage is one of the most important performance metrics for sensor networks since it reflects how well a sensor field is monitored. In this paper, we introduce the maximum coverage deployment problem in wireless sensor networks and analyze the properties of the problem and its solution space. Random deployment is the simplest way to deploy sensor nodes but may cause unbalanced deployment and therefore, we need a more intelligent way for sensor deployment. We found that the phenotype space of the problem is a quotient space of the genotype space in a mathematical view. Based on this property, we propose an efficient genetic algorithm using a novel normalization method. A Monte Carlo method is adopted to design an efficient evaluation function, and its computation time is decreased without loss of solution quality using a method that starts from a small number of random samples and gradually increases the number for subsequent generations. The proposed genetic algorithms could be further improved by combining with a well-designed local search. The performance of the proposed genetic algorithm is shown by a comparative experimental study. When compared with random deployment and existing methods, our genetic algorithm was not only about twice faster, but also showed significant performance improvement in quality.

Designer nanorings with functional cavities from self-assembling ß-sheet peptides.

ß-Barrel proteins that take the shape of a ring are common in many types of water-soluble enzymes and water-insoluble transmembrane pore-forming proteins. Since ß-barrel proteins perform diverse functions in the cell, it would be a great step towards developing artificial proteins if we can control the polarity of artificial ß-barrel proteins at will. Here, we describe a rational approach to construct ß-barrel protein mimics from the self-assembly of peptide-based building blocks. With this approach, the direction of the self-assembly process toward the formation of water-soluble ß-barrel nanorings or water-insoluble transmembrane ß-barrel pores could be controlled by the simple but versatile molecular manipulation of supramolecular building blocks. This study not only delineates the basic driving force that underlies the folding of ß-barrel proteins, but also lays the foundation for the facile fabrication of ß-barrel protein mimics, which can be developed as nanoreactors, ion- and small-molecule-selective pores, and novel antibiotics.

Self-assembly of a peptide rod-coil: a polyproline rod and a cell-penetrating peptide Tat coil.

Peptide rod-coil molecules, composed of a stiff polyproline rod and a hydrophilic cell-penetrating peptide Tat coil, self-assemble into nanocapsules and mediate efficient intracellular delivery of entrapped hydrophilic molecules.

Geometric crossovers for multiway graph partitioning.

Geometric crossover is a representation-independent generalization of the traditional crossover defined using the distance of the solution space. By choosing a distance firmly rooted in the syntax of the solution representation as a basis for geometric crossover, one can design new crossovers for any representation. Using a distance tailored to the problem at hand, the formal definition of geometric crossover allows us to design new problem-specific crossovers that embed problem-knowledge in the search. The standard encoding for multiway graph partitioning is highly redundant: each solution has a number of representations, one for each way of labeling the represented partition. Traditional crossover does not perform well on redundant encodings. We propose a new geometric crossover for graph partitioning based on a labeling-independent distance that filters out the redundancy of the encoding. A correlation analysis of the fitness landscape based on this distance shows that it is well suited to graph partitioning. A second difficulty with designing a crossover for multiway graph partitioning is that of feasibility: in general recombining feasible partitions does not lead to feasible offspring partitions. We design a new geometric crossover for permutations with repetitions that naturally suits partition problems and we test it on the graph partitioning problem. We then combine it with the labeling-independent crossover and obtain a much superior geometric crossover inheriting both advantages.

Tunable bacterial agglutination and motility inhibition by self-assembled glyco-nanoribbons.

We explored a method of controlling bacterial motility and agglutination by using self-assembled carbohydrate-coated beta-sheet nanoribbons. To this aim, we synthesized triblock peptides that consist of a carbohydrate, a polyethylene glycol (PEG) spacer, and a beta-sheet-forming peptide. An investigation into the effect of PEG-spacer length on the self-assembly of the triblock peptides showed that the PEG should be of sufficiently length to stabilize the beta-sheet nanoribbon structure. It was found that the stabilization of the nanoribbon led to stronger activity in bacterial motility inhibition and agglutination, thus suggesting that antibacterial activity can be controlled by the stabilization strategy. Furthermore, another level of control over bacterial motility and agglutination was attained by co-assembly of bacteria-specific and -nonspecific supramolecular building blocks. The nanoribbon specifically detected bacteria after the encapsulation of a fluorescent probe. Moreover, the detection sensitivity was enhanced by the formation of bacterial clusters. All these results suggest that the carbohydrate-coated beta-sheet nanoribbons can be developed as promising agents for pathogen capture, inactivation, and detection, and that the activity can be controlled at will.