Optimal Number Of Principal Components Research Articles

The 3D-QSAR Study, Molecular Docking, and ADMET Analysis of Darunavir Derivatives of HIV-1 Protease Inhibitors

Background: Acquired Immunodeficiency Syndrome (AIDS) is one of most prevalent infectious diseases in the world , and HIV-1 protease (PR) is a vital target of drug design. Nowadays, three-dimensional quantitative structure-activity relationships (3D-QSAR) are applied to help design new protease inhibitions (PIs). Objective: The primary objective of this study is to apply the 3D-QSAR study to a series of 42 derivatives of Darunavir (DRV) and to design new molecules possessing high antivirus activity. Methods: Partial Least Squares (PLS) were used to cross-validate the dataset of compounds, and the optimal number of principal components (ONC), cross-validate coefficient (q²), standard error of estimate (SEE), non-cross-validated correlation coefficient (R²) and fisher test value (F) were calculated to assess model robustness. In this study, the CoMSIA-DAH model (q²=0.754, r²= 0.988, rpred2=0.57) possessed the highest predicted activity. Newly designed molecules were analyzed by docking studies with compound 25 taken as a template. Results: Within eight newly designed drugs, compound N02 possessed the highest antivirus activity (IC50=0.00461 nM) predicted by the CoMSIA-DAH model. The Surflex-Dock module of SYBYL-X 2.0 was used to affirm the predicted anti-PR activity of the newly designed compounds and the results of docking complex structure could be visualized. All newly designed molecules were in agreement with CSore above four and the docking study revealed that Asp29, Asp30, Ile50, Asp124, Asp128, Asp129 and Ile149 were critical residues in the process of inhibiting PR. Conclusion: One of the main aspects of this study is the successful design of a series of molecules with excellent investigatory values, which elucidates explicit quantitative structure-activity relationships of DRV derivatives and will provide significant suggestions for future pharmaceutical research.

Investigation of Seasonal Variation in Fatty Acid and Mineral Concentrations of Pecorino Romano PDO Cheese: Imputation of Missing Values for Enhanced Classification and Metabolic Profile Reconstruction.

Seasonal variation in fatty acids and minerals concentrations was investigated through the analysis of Pecorino Romano cheese samples collected in January, April, and June. A fraction of samples contained missing values in their fatty acid profiles. Probabilistic principal component analysis, coupled with Linear Discriminant Analysis, was employed to classify cheese samples on a production season basis while accounting for missing data and quantifying the missing fatty acid concentrations for the samples in which they were absent. The levels of rumenic acid, vaccenic acid, and omega-3 compounds were positively correlated with the spring season, while the length of the saturated fatty acids increased throughout the production seasons. Concerning the classification performances, the optimal number of principal components (i.e., 5) achieved an accuracy in cross-validation equal to 98%. Then, when the model was tasked with imputing the lacking fatty acid concentration values, the optimal number of principal components resulted in an R2 value in cross-validation of 99.53%.

Identification of procymidone in rapeseed oils based on olfactory visualization technology

A new method for qualitative identification of pesticide residues in edible oil based on olfactory visualization technology is proposed. Firstly, according to the pre-experimental experience, 12 suitable chemical dyes were selected to prepare sensor arrays to form an olfactory visualization system. The system was used to gather volatile odor information in rapeseed oil samples that had different levels of procymidone residues. Subsequently, the olfactory information was translated into a visual representation. Then, the visual data, i.e. color features, were preprocessed and underwent principal component analysis to extract and reduce the dimensionality of sensor image information, resulting in the optimal number of principal components (PCs). Finally, three different models based on the sensor image features were constructed for analysis. These models included the support vector machine (SVM), the random forest (RF) and the kernel based extreme learning machine (KELM). In process of model correction, the parameters of the three models were optimized by dung beetle optimizer (DBO) algorithm, resulting in the identification of the optimal parameters. The results show that the cumulative variance contribution increases slowly when the number of PCs starts from 6, and the three models (i.e. DBO-SVM, DBO-RF, and DBO-KELM) have the best prediction results when PCs = 6. Compared to the DBO-RF and DBO-KELM models, the training and prediction performance of the SVM model based on the DBO optimization algorithm is more stable and has the higher recognition accuracy of the samples, reaching 100%. The results show that it is feasible to use olfactory visualization technology to achieve high-precision qualitative identification of edible oil pesticide residues.

QSAR Study on the Antitumor Activity of Novel 1,2, 3-Triazole Compounds based on Topomer Comfa Method

Background: The high mortality rate of cancer is endangering human health, and the research and development of new anticancer drugs have the attention of scientists worldwide. Sulfonamides have become the focus of anticancer drug research. 1,2,3-triazole compounds can inhibit the formation of a variety of tumor cells. Based on the excellent antitumor activity exhibited by the 1,2,3-triazole compound skeleton, the sulfonamide moiety in the sulfonamide structure can be introduced into the triazole compound skeleton to obtain highly active anticancer drugs. Methods: The Topomer CoMFA method was used to study the three-dimensional quantitative structureactivity relationship of 58 new 1,2,3-triazole compounds with sulfa groups, and a 3D-QSAR model was obtained. Results: The cross-validation coefficient q2 is 0.545, the non-cross-correlation coefficient r2 is 0. 754, r_pred2 is 0.930, the optimal number of principal components N is 4, and the standard estimation error SEE is 0.319. These results show that the model has good internal and external forecasting capabilities. By searching for the R group in the Topomer search module and combining with the more active groups in the existing molecules, 6 new compounds with theoretically higher anti-HL-60 (leukemia cell line) activity are obtained. Conclusion: The prediction result of the Topomer CoMFA model is good, and the statistical verification is effective. The prediction results of ADMET show that the 6 new compounds meet the drug requirements and are expected to become potential anti-HL-60 inhibitors, providing guidance for the synthesis of anti-tumor drugs.

Compressed Machine Learning-Based Inverse Model for Design Optimization of Microwave Components

This article presents a new noniterative inverse modeling technique based on machine learning regression and its applications to microwave design optimization. The proposed inverse model accepts the high-dimensional S-parameters computed at many frequency points as the input and estimates the optimal geometrical/physical parameters of the microwave component as its output. The least-squares support vector machine regression is combined with the principal component analysis to simultaneously overcome both the high-dimensional input space and ill-posed challenges of the inverse modeling. We also propose a new empirical method to find the optimum number of principal components (i.e., the compression level) for each example in an automated way. This makes our proposed model general and easy to use compared with the existing data-driven inverse modeling techniques. The inverse model is trained by a set of scattering parameters computed via a 2-D/3-D solver for few configurations of the geometrical parameters. The feasibility and the accuracy of the proposed optimization scheme are investigated by comparing its predictions with the corresponding optimal configuration estimated via a commercial solver.

FindPC: An R package to automatically select the number of principal components in single-cell analysis.

Principal component analysis is widely used in analyzing single-cell genomic data. Selecting the optimal number of principal components (PCs) is a crucial step for downstream analyses. The elbow method is most commonly used for this task, but it requires one to visually inspect the elbow plot and manually choose the elbow point. To address this limitation, we developed six methods to automatically select the optimal number of PCs based on the elbow method. We evaluated the performance of these methods on real single-cell RNA-seq data from multiple human and mouse tissues and cell types. The perpendicular line method with 30 PCs has the best overall performance, and its results are highly consistent with the numbers of PCs identified manually. We implemented the six methods in an R package, findPC, that objectively selects the number of PCs and can be easily incorporated into any automatic analysis pipeline. findPC R package is freely available at https://github.com/haotian-zhuang/findPC. Supplementary data are available at Bioinformatics online.

Mineral Content Estimation of Lunar Soil of Lunar Highland and Lunar Mare Based on Diagnostic Spectral Characteristic and Partial Least Squares Method

Extraction of mineral and rock information of lunar regolith is of far-reaching significance to the study of material composition, geological structure and historical evolution of lunar regolith. Visible and near-infrared spectra can reflect mineral composition information, and can be used to extract mineral composition and distribution characteristics of lunar regolith. In this paper, the LSCC (Lunar Soil Characterization Consortium) data of lunar regolith is taken as the research object. The partial least squares (PLS) regression model is used to estimate the spectra of lunar regolith measured in RELAB laboratory of Brown University. The mineral contents of plagioclase, pyroxene, olivine, ilmenite, agglutinate and volcanic glass in lunar regolith have been optimized and retrieved. The LSCC spectra of lunar regolith have been pre-processed by multivariate scattering correction (MSC), which highlight the spectral features of lunar regolith. The optimal number of principal components has been selected by cross-validation test. The PLS regression have been established for samples from lunar highland and lunar mare respectively. Two-thirds of samples have been randomly selected as experimental group to establish the prediction relationship between the spectra of lunar regolith and mineral content. The remaining one-third of samples have been used as verification group to further validate the prediction relationship. The results show that the partial least squares regression model has high accuracy and good stability. It is of theoretical and practical significance to optimize the inversion of mineral content in lunar regolith using spectral data of lunar regolith.

OCEM: Automatic detection and analysis of overlapping co-expressed gene modules

BackgroundWhen it comes to the co-expressed gene module detection, its typical challenges consist of overlap between identified modules and local co-expression in a subset of biological samples. The nature of module detection is the use of unsupervised clustering approaches and algorithms. Those methods are advanced undoubtedly, but the selection of a certain clustering method for sample- and gene-clustering tasks is separate, in which the latter task is often more complicated.ResultsThis study presented an R-package, Overlapping CoExpressed gene Module (oCEM), armed with the decomposition methods to solve the challenges above. We also developed a novel auxiliary statistical approach to select the optimal number of principal components using a permutation procedure. We showed that oCEM outperformed state-of-the-art techniques in the ability to detect biologically relevant modules additionally.ConclusionsoCEM helped non-technical users easily perform complicated statistical analyses and then gain robust results. oCEM and its applications, along with example data, were freely provided at https://github.com/huynguyen250896/oCEM.

Towards fine-scale population stratification modeling based on kernel principal component analysis and random forest.

Population stratification modeling is essential in Genome-Wide Association Studies. In this paper, we aim to build a fine-scale population stratification model to efficiently infer individual genetic ancestry. Kernel Principal Component Analysis (PCA) and random forest are adopted to build the population stratification model, together with parameter optimization. We explore different PCA methods, including standard PCA and kernel PCA to extract relevant features from the genotype data that is transformed by vcf2geno, a pipeline from LASER software. These extracted features are fed into a random forest for ensemble learning. Parameter tuning is performed to jointly find the optimal number of principal components, kernel function for PCA and parameters of the random forest. Experiments based on HGDP dataset show that kernel PCA with Sigmoid function and Gaussian function can achieve higher prediction accuracy than the standard PCA. Compared to standard PCA with the two principal components, the accuracy by using KPCA-Sigmoid with the optimal number of principal components can achieve around 100% and 200% improvement for East Asian and European populations, respectively. With the optimal parameter configuration on both PCA and random forest, our proposed method can infer the individual genetic ancestry more accurately, given their variants.

Adaptive dimensionality reduction for neural network-based online principal component analysis.

“Principal Component Analysis” (PCA) is an established linear technique for dimensionality reduction. It performs an orthonormal transformation to replace possibly correlated variables with a smaller set of linearly independent variables, the so-called principal components, which capture a large portion of the data variance. The problem of finding the optimal number of principal components has been widely studied for offline PCA. However, when working with streaming data, the optimal number changes continuously. This requires to update both the principal components and the dimensionality in every timestep. While the continuous update of the principal components is widely studied, the available algorithms for dimensionality adjustment are limited to an increment of one in neural network-based and incremental PCA. Therefore, existing approaches cannot account for abrupt changes in the presented data. The contribution of this work is to enable in neural network-based PCA the continuous dimensionality adjustment by an arbitrary number without the necessity to learn all principal components. A novel algorithm is presented that utilizes several PCA characteristics to adaptivly update the optimal number of principal components for neural network-based PCA. A precise estimation of the required dimensionality reduces the computational effort while ensuring that the desired amount of variance is kept. The computational complexity of the proposed algorithm is investigated and it is benchmarked in an experimental study against other neural network-based and incremental PCA approaches where it produces highly competitive results.

Computer vision and unsupervised machine learning for pore-scale structural analysis of fractured porous media

Understanding fluid flow in complex fractured porous media requires an accurate representation of the pore space, especially in the presence of both granular pores and fractures, which significantly differ in their geometries. The effect of such a complex fluid pathway is prominent in fractured sandstones and carbonates, which store a significant amount of energy resources. Digital core analysis allows three-dimensional imaging of rock cores at high resolutions to capture essential features such as granular pores, fractures, and minerals. These features are represented by a multi-modal grey-level histogram. Later, segmentation techniques are applied to these images to uniquely differentiate pores (fractures and granular pores) from minerals. However, these segmentation routines are purely based on grey-level intensities and hence, are incapable of automatically segregating the pore space into granular pores and fractures. This paper applies a computer vision technique called contour detection for structural analysis of the entire pore space. Since fractures are mainly considered planar features, we carry out a slice-by-slice analysis on 3D segmented images of fractured sandstones and carbonates. Contours of pores (granular pores and fractures) and their structural properties are read into a principal component analysis followed by a K-means clustering algorithm to segregate granular pores from fractures. The exploratory analysis showed that the optimum number of principal components required for segregation is 2 for both sandstones and carbonates. The test for generalization used the above information for K-means clustering in x, y, and z directions. The voxels identified as fractures and granular pores are then merged to give a 3D representation of fractures showing an accuracy greater than 89% when compared to the ground truth labels. The permeability differences between reconstructed and labelled fractures for digitally fractured samples were less than 9% for all the directions. This analysis provides pathways to better understand competing fluid flow phenomena in pores and fractures and aids in the extraction of pore network models for complex fractured porous media.

An Effective Mental Stress State Detection and Evaluation System Using Minimum Number of Frontal Brain Electrodes.

Currently, mental stress is a common social problem affecting people. Stress reduces human functionality during routine work and may lead to severe health defects. Detecting stress is important in education and industry to determine the efficiency of teaching, to improve education, and to reduce risks from human errors that might occur due to workers’ stressful situations. Therefore, the early detection of mental stress using machine learning (ML) techniques is essential to prevent illness and health problems, improve quality of education, and improve industrial safety. The human brain is the main target of mental stress. For this reason, an ML system is proposed which investigates electroencephalogram (EEG) signal for thirty-six participants. Extracting useful features is essential for an efficient mental stress detection (MSD) system. Thus, this framework introduces a hybrid feature-set that feeds five ML classifiers to detect stress and non-stress states, and classify stress levels. To produce a reliable, practical, and efficient MSD system with a reduced number of electrodes, the proposed MSD scheme investigates the electrodes placements on different sites on the scalp and selects that site which has the higher impact on the accuracy of the system. Principal Component analysis is employed also, to reduce the features extracted from such electrodes to lower model complexity, where the optimal number of principal components is examined using sequential forward procedure. Furthermore, it examines the minimum number of electrodes placed on the site which has greater impact on stress detection and evaluation. To test the effectiveness of the proposed system, the results are compared with other feature extraction methods shown in literature. They are also compared with state-of-the-art techniques recorded for stress detection. The highest accuracies achieved in this study are 99.9%(sd = 0.015) and 99.26% (sd = 0.08) for identifying stress and non-stress states, and distinguishing between stress levels, respectively, using only two frontal brain electrodes for detecting stress and non-stress, and three frontal electrodes for evaluating stress levels respectively. The results show that the proposed system is reliable as the sensitivity is 99.9(0.064), 98.35(0.27), specificity is 99.94(0.02), 99.6(0.05), precision is 99.94(0.06), 98.9(0.23), and the diagnostics odd ratio (DOR) is ≥ 100 for detecting stress and non-stress, and evaluating stress levels respectively. This shows that the proposed framework has compelling performance and can be employed for stress detection and evaluation in medical, educational and industrial fields. Finally, the results verified the efficiency and reliability of the proposed system in predicting stress and non-stress on new patients, as the accuracy achieved 98.48% (sd = 1.12), sensitivity = 97.78% (sd = 1.84), specificity = 97.75% (sd = 2.05), precision = 99.26% (sd = 0.67), and DOR ≥ 100 using only two frontal electrodes.

Diagnosis of defects by principal component analysis of a gas turbine

This study examines the application of the Principal Component Analysis (PCA) technique to detect the failures in complex industrial processes such as gas turbines used for electric power generation. The early detection of failures in such complex processes is indeed paramount to prevent product deterioration, performance degradation, significant property damage and human health. We identified the PCA model by determining the optimal number of principal components retained in the PCA model, then we validated the PCA model by checking the evolution of measurements and estimated the two variables X2 and X8. Thereafter, the evolution of three detection indexes is illustrated highlighting that the filtered SPE index is the best suited one for our installation, and finally, we checked the efficiency of the linear PCA method from the filtered SPE detection index using real data of defects that may occur within the gas turbine. The results obtained will aid to confirm the performance of the linear PCA method in the field of early failure detection. Thus, the PCA method appears as an efficacious tool to monitor and diagnose complex installations.

Extracting Common Mode Errors of Regional GNSS Position Time Series in the Presence of Missing Data by Variational Bayesian Principal Component Analysis.

Removal of the common mode error (CME) is very important for the investigation of global navigation satellite systems’ (GNSS) error and the estimation of an accurate GNSS velocity field for geodynamic applications. The commonly used spatiotemporal filtering methods normally process the evenly spaced time series without missing data. In this article, we present the variational Bayesian principal component analysis (VBPCA) to estimate and extract CME from the incomplete GNSS position time series. The VBPCA method can naturally handle missing data in the Bayesian framework and utilizes the variational expectation-maximization iterative algorithm to search each principal subspace. Moreover, it could automatically select the optimal number of principal components for data reconstruction and avoid the overfitting problem. To evaluate the performance of the VBPCA algorithm for extracting CME, 44 continuous GNSS stations located in Southern California were selected. Compared to previous approaches, VBPCA could achieve better performance with lower CME relative errors when more missing data exists. Since the first principal component (PC) extracted by VBPCA is remarkably larger than the other components, and its corresponding spatial response presents nearly uniform distribution, we only use the first PC and its eigenvector to reconstruct the CME for each station. After filtering out CME, the interstation correlation coefficients are significantly reduced from 0.43, 0.46, and 0.38 to 0.11, 0.10, and 0.08, for the north, east, and up (NEU) components, respectively. The root mean square (RMS) values of the residual time series and the colored noise amplitudes for the NEU components are also greatly suppressed, with average reductions of 27.11%, 28.15%, and 23.28% for the former, and 49.90%, 54.56%, and 49.75% for the latter. Moreover, the velocity estimates are more reliable and precise after removing CME, with average uncertainty reductions of 51.95%, 57.31%, and 49.92% for the NEU components, respectively. All these results indicate that the VBPCA method is an alternative and efficient way to extract CME from regional GNSS position time series in the presence of missing data. Further work is still required to consider the effect of formal errors on the CME extraction during the VBPCA implementation.

Malignant melanoma detection using multi layer preceptron with visually imperceptible features and PCA components from MED-NODE dataset

In this paper, a scheme is worked out for classification of images belonging to malignant melanoma and nevus class by multi layer neural network architecture with different trainings and cost functions. Total 1,875 shape, colour and texture features are extracted from 170 images from MED-NODE dataset. With the total 1,875 features an accuracy of 82.05% is achieved. Feature ranking algorithm ReliefF is used for ranking these features. MLP is run with varying number of best ranked features. With 10 best features an accuracy of 83.33%, sensitivity of 86.77% and specificity of 72.78% are achieved with 3 fold cross-validation. Effect of pre-processing the features with principal component analysis is explored and found that the optimal number of principal components is 25, which yields a maximum accuracy of 87.18% which is much higher than the previously reported accuracy level with this dataset.

Malignant melanoma detection using multi layer preceptron with visually imperceptible features and PCA components from MED-NODE dataset

In this paper, a scheme is worked out for classification of images belonging to malignant melanoma and nevus class by multi layer neural network architecture with different trainings and cost functions. Total 1,875 shape, colour and texture features are extracted from 170 images from MED-NODE dataset. With the total 1,875 features an accuracy of 82.05% is achieved. Feature ranking algorithm ReliefF is used for ranking these features. MLP is run with varying number of best ranked features. With 10 best features an accuracy of 83.33%, sensitivity of 86.77% and specificity of 72.78% are achieved with 3 fold cross-validation. Effect of pre-processing the features with principal component analysis is explored and found that the optimal number of principal components is 25, which yields a maximum accuracy of 87.18% which is much higher than the previously reported accuracy level with this dataset.

Forecasting exchange rates using principal components

We introduce a novel atheoretical approach to forecasting bilateral exchange rates. We first obtain principal components for a set of up to 20 bilateral exchange rates for a set of major currencies of interest. We then fit autoregressive processes to get one-period-ahead forecasts of each of the principal components and use these to forecast individual bilateral exchange rates. We focus on six major currencies, including the US dollar, Japanese yen, British pound, euro, and the Australian and Canadian dollars. Based on the daily data from 01/02/1999 to 08/03/2018, our results suggest this approach can be useful in forecasting some one-day and one-month ahead bilateral exchange rates, particularly for the pound and Australian dollar. The optimal number of principal components that should be included in the forecasting procedure depends on the currency of interest.

The linkage between geopotential height and monthly precipitation in Iran

This paper investigates the linkage between large-scale atmospheric circulation and monthly precipitation during November to April over Iran. Canonical correlation analysis (CCA) is used to set up the statistical linkage between the 850 hPa geopotential height large-scale circulation and monthly precipitation over Iran for the period 1968–2010. The monthly precipitation dataset for 50 synoptic stations distributed in different climate regions of Iran is considered as the response variable in the CCA. The monthly geopotential height reanalysis dataset over an area between 10° N and 60° N and from 20° E to 80° E is utilized as the explanatory variable in the CCA. Principal component analysis (PCA) as a pre-filter is used for data reduction for both explanatory and response variables before applying CCA. The optimal number of principal components and canonical variables to be retained in the CCA equations is determined using the highest average cross-validated Kendall’s tau value. The 850 hPa geopotential height pattern over the Red Sea, Saudi Arabia, and Persian Gulf is found to be the major pattern related to Iranian monthly precipitation. The Pearson correlation between the area averaged of the observed and predicted precipitation over the study area for Jan, Feb, March, April, November, and December months are statistically significant at the 5% significance level and are 0.78, 0.80, 0.82, 0.74, 0.79, and 0.61, respectively. The relative operating characteristic (ROC) indicates that the highest scores for the above- and below-normal precipitation categories are, respectively, for February and April and the lowest scores found for December.

Improvements of the Vis-NIRS Model in the Prediction of Soil Organic Matter Content Using Spectral Pretreatments, Sample Selection, and Wavelength Optimization

A total of 130 topsoil samples collected from Guoyang County, Anhui Province, China, were used to establish a Vis-NIR model for the prediction of organic matter content (OMC) in lime concretion black soils. Different spectral pretreatments were applied for minimizing the irrelevant and useless information of the spectra and increasing the spectra correlation with the measured values. Subsequently, the Kennard–Stone (KS) method and sample set partitioning based on joint x–y distances (SPXY) were used to select the training set. Successive projection algorithm (SPA) and genetic algorithm (GA) were then applied for wavelength optimization. Finally, the principal component regression (PCR) model was constructed, in which the optimal number of principal components was determined using the leave-one-out cross validation technique. The results show that the combination of the Savitzky–Golay (SG) filter for smoothing and multiplicative scatter correction (MSC) can eliminate the effect of noise and baseline drift; the SPXY method is preferable to KS in the sample selection; both the SPA and the GA can significantly reduce the number of wavelength variables and favorably increase the accuracy, especially GA, which greatly improved the prediction accuracy of soil OMC with Rcc, RMSEP, and RPD up to 0.9316, 0.2142, and 2.3195, respectively.

Quantitative Analysis for Levocetirizine Hydrochloride Tablets Based on NIR Spectroscopy

The aim of this study was to develop a quantitative analytical method to measure the effective components in the left cetirizine hydrochloride tablets using near infrared spectroscopy combining with a partial least square (PLS) analysis model. The method was internal cross-validated to determine the best wavelength range, spectral preprocessing methods and the optimal number of principal components. The concentration of validation set samples was predictable by PLS model. The RMSECV value was 0.276, and the R(2) value was 0.974. Our study suggests that this model can be used for rapid quantitative analysis of left cetirizine hydrochloride tablets from different manufacturers.