Support Vector Machine-based Method Research Articles

Support vector machine-based method for colorimetric characterization of computer-controlled liquid crystal displays

Support vector machine-based method for colorimetric characterization of computer-controlled liquid crystal displays

POOE: predicting oomycete effectors based on a pre-trained large protein language model.

Oomycetes are fungus-like eukaryotic microorganisms which can cause catastrophic diseases in many plants. Successful infection of oomycetes depends highly on their effector proteins that are secreted into plant cells to subvert plant immunity. Thus, systematic identification of effectors from the oomycete proteomes remains an initial but crucial step in understanding plant-pathogen relationships. However, the number of experimentally identified oomycete effectors is still limited. Currently, only a few bioinformatics predictors exist to detect potential effectors, and their prediction performance needs to be improved. Here, we used the sequence embeddings from a pre-trained large protein language model (ProtTrans) as input and developed a support vector machine-based method called POOE for predicting oomycete effectors. POOE could achieve a highly accurate performance with an area under the precision-recall curve of 0.804 (area under the receiver operating characteristic curve = 0.893, accuracy = 0.874, precision = 0.777, recall = 0.684, and specificity = 0.936) in the fivefold cross-validation, considerably outperforming various combinations of popular machine learning algorithms and other commonly used sequence encoding schemes. A similar prediction performance was also observed in the independent test. Compared with the existing oomycete effector prediction methods, POOE provided very competitive and promising performance, suggesting that ProtTrans effectively captures rich protein semantic information and dramatically improves the prediction task. We anticipate that POOE can accelerate the identification of oomycete effectors and provide new hints to systematically understand the functional roles of effectors in plant-pathogen interactions. The web server of POOE is freely accessible at http://zzdlab.com/pooe/index.php. The corresponding source codes and data sets are also available at https://github.com/zzdlabzm/POOE.IMPORTANCEIn this work, we use the sequence representations from a pre-trained large protein language model (ProtTrans) as input and develop a Support Vector Machine-based method called POOE for predicting oomycete effectors. POOE could achieve a highly accurate performance in the independent test set, considerably outperforming existing oomycete effector prediction methods. We expect that this new bioinformatics tool will accelerate the identification of oomycete effectors and further guide the experimental efforts to interrogate the functional roles of effectors in plant-pathogen interaction.

Exploring seafarers’ emotional responses to emergencies: An empirical study using a shiphandling simulator

Seafarers are required to make quick decisions to avoid accidents in case of emergencies. However, officers with anxiety generally have a high probability of making wrong decisions that threaten safety and security during the voyage. With the help of a shiphandling simulator, this study aims to investigate the emotional changes of seafarers under simulated scenarios of emergencies. The State-Trait Anxiety Inventory (S-TAI) scale and electrocardiograph (ECG) signal are adopted to evaluate the emotions of the participant seafarers. To classify the anxiety state of the participants, a support vector machine-based method is applied to establish an anxiety recognition model. Classification results reveal that this proposed model can effectively identify different emotions of participants based on ECG features (cross-validation accuracy: 86.0%; test accuracy: 92.3%). The experimental results show that poor visibility could cause the greatest impact on the anxiety of seafarers. In addition, navigational officers and marine pilots react differently in case of emergencies. Seafarers tend to experience more anxiety when dealing with emergency situations, while marine pilots experience more anxiety during multi-ship encounter periods. Consequently, the findings of this study aid to effectively identify the scenarios that cause anxiety emotion of different professional seafarers, providing the corresponding reference for the training of seafarers. This could help prevent catastrophic accidents that pose a threat to oceans and coasts caused by human error.

A support vector machine-based method for improving real-time hourly precipitation forecast in Japan

• Improved real-time hourly precipitation forecast accuracy using machine learning. • Investigated the use of CDF-transform for short-range forecast bias correction. • Provided forcing data for the next step to enhance flood early warning accuracy. Real-time precipitation forecast facilitates water management and water-associated disaster early warning. However, numerical weather prediction (NWP) models provide precipitation forecasts with bias. This study proposed to combine support vector machine (SVM) regression with quantile-based bias correction method to improve real-time 39-hour precipitation forecasts in Japan. Five methods were compared and evaluated against observations, which include SVM regression, quantile mapping (QM), cumulative distribution function transform (CDFt), and the combination of SVM and QM (or CDFt). Results indicated that the combination of SVM and CDFt (i.e., SVM-CDFt) generally provided the highest accuracy with good computational efficiency. SVM alone improved the spatial representation of hourly precipitation with a correlation coefficient increased from 0.387 to 0.490 in January and from 0.235 to 0.296 in July in the cross-validation experiment. However, SVM underestimated the variability of hourly precipitation and heavy precipitation events. QM and CDFt perform well in correcting the bias in modeled precipitation, while they have limited capability in correcting the rainband location. Combining SVM and quantile-based method took advantage of both approaches, providing a more consistent variability with observations and better predicted extreme precipitation events, although overestimation of rainfall area was witnessed. The simple concept, high computational efficiency, as well as evident improvement in forecast accuracy make the combined cases, especially the SVM-CDFt method, beneficial for real-time precipitation forecast and flood early warning.

A Wave Texture Difference Method for Rainfall Detection Using X-Band Marine Radar

To suppress the influence of rainfall when extracting sea surface wind and wave parameters using X-band marine radar and control the quality of the collected radar image, it is necessary to detect whether the radar image is contaminated by rainfall. Since the detection accuracy of the statistical characteristics methods (e.g., the zero pixel percentage method and the high-clutter direction method) is limited and the threshold is difficult to determine, the machine learning methods (e.g., the support vector machine-based method and the neural network algorithm) are difficult to select appropriate quality and quantity of data for model training. Therefore, based on the feature that rainfall can change the sea surface texture, a wave texture difference method for rainfall detection is proposed in this paper. Considering the spatial rainfall is uneven, the polar coordinates of the radar image are converted into Cartesian coordinates to detect rainfall. To express the maximum wave difference more accurately, the calculation method of the pixels in the radar texture difference map is redefined. Then, a consecutive pixel method is used to detect the calculated radar texture difference map, and this method can detect adaptively with the change of wind. The data collected from the shore of Haitan Island along the East China Sea are used to validate the effectiveness of the proposed method. Compared with the zero pixel percentage method and the support vector machine-based method, the experimental results demonstrate that the proposed method has better rainfall detection performance. In addition, the research on the applicability of the proposed method shows that the wave texture difference method can finish the task of rainfall detection in most marine environments.

Research on laser ultrasonic surface defect identification based on a support vector machine.

To solve the problem of difficult quantitative identification of surface defect depth during laser ultrasonic inspection, a support vector machine-based method for quantitative identification of surface rectangular defect depth is proposed. Based on the thermal-elastic mechanism, the finite element model for laser ultrasound inspection of aluminum materials containing surface defects was developed by using the finite element software COMSOL. The interaction process between laser ultrasound and rectangular defects was simulated, and the reflected wave signals corresponding to defects of different depths under pulsed laser irradiation were obtained. Laser ultrasonic detection experiments were conducted for surface defects of different depths, and multiple sets of ultrasonic signal waveform were collected, and several feature vectors such as time-domain peak, center frequency peak, waveform factor and peak factor were extracted by using MATLAB, the quantitative defect depth identification model based on support vector machine was established. The experimental results show that the laser ultrasonic surface defect identification model based on support vector machine can achieve high accuracy prediction of defect depth, the regression coefficient of determination is kept above 0.95, and the average relative error between the true value and the predicted value is kept below 10%, and the prediction accuracy is better than that of the reflection echo method and BP neural network model.

Classifying the superfamily of small heat shock proteins by using g-gap dipeptide compositions

Small heat shock protein (sHSP) is a superfamily of molecular chaperone and is found from archaea to human. Recent researches have demonstrated that sHSPs participate in a series of biological processes and are even closely associated with serious diseases. Since sHSP is a very large superfamily and members from different superfamilies exhibit distinct functions, accurate classification of the subfamily of sHSP will be helpful for unrevealing its functions. In the present work, a support vector machine-based method was proposed to classify the subfamily of sHSPs. In the 10-fold cross validation test, an overall accuracy of 93.25% was obtained for classifying the subfamily of sHSPs. The superiority of the proposed method was also demonstrated by comparing it with the other methods. It is anticipated that the proposed method will become a useful tool for classifying the subfamily of sHSPs.

Random forest-based classsification and analysis of hemiplegia gait using low-cost depth cameras.

Hemiplegia is a form of paralysis that typically has the symptom of dysbasia. In current clinical rehabilitations, to measure the level of hemiplegia gaits, clinicians often conduct subject evaluations through observations, which is unreliable and inaccurate. The Microsoft Kinect sensor (MS Kinect) is a widely used, low-cost depth sensor that can be used to detect human behaviors in real time. The purpose of this study is to investigate the usage of the Kinect data for the classification and analysis of hemiplegia gait. We first acquire the gait data by using a MS Kinect and extract a set of gait features including the stride length, gait speed, left/right moving distances, and up/down moving distances. With the gait data of 60 subjects including 20 hemiplegia patients and 40 healthy subjects, we employ a random forest-based classification approach to analyze the importances of different gait features for hemiplegia classification. Thanks to the over-fitting avoidance nature of the random forest approach, we do not need to have a careful control over the percentage of patients in the training data. In our experiments, our approach obtained the averaged classification accuracy of 90.65% among all the combinations of the gait features, which substantially outperformed state-of-the-art methods. The best classification accuracy of our approach is 95.45%, which is superior than all existing methods. Additionally, our approach also correctly reveals the importance of different gait features for hemiplegia classification. Our random forest-based approach outperforms support vector machine-based method and the Bayesian-based method, and can effectively extract gait features of subjects with hemiplegia for the classification and analysis of hemiplegia. Graphical Abstract Random Forest based Classsification and Analysis of Hemiplegia Gait using Low-cost Depth Cameras. Left: Motion capture with MS Kinect; Top-right: Random Forest Classsification based on the extracted gait features; Bottom-right: Sensitivity and specificity evaluation of the proposed classification approach.

Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning

Histopathological images contain morphological markers of disease progression that have diagnostic and predictive values. In this study, we demonstrate how deep learning framework can be used for an automatic classification of Renal Cell Carcinoma (RCC) subtypes, and for identification of features that predict survival outcome from digital histopathological images. Convolutional neural networks (CNN’s) trained on whole-slide images distinguish clear cell and chromophobe RCC from normal tissue with a classification accuracy of 93.39% and 87.34%, respectively. Further, a CNN trained to distinguish clear cell, chromophobe and papillary RCC achieves a classification accuracy of 94.07%. Here, we introduced a novel support vector machine-based method that helped to break the multi-class classification task into multiple binary classification tasks which not only improved the performance of the model but also helped to deal with data imbalance. Finally, we extracted the morphological features from high probability tumor regions identified by the CNN to predict patient survival outcome of most common clear cell RCC. The generated risk index based on both tumor shape and nuclei features are significantly associated with patient survival outcome. These results highlight that deep learning can play a role in both cancer diagnosis and prognosis.

Robust and adaptive algorithm for hyperspectral palmprint region of interest extraction

Recently, hyperspectral imaging has attracted more and more considerable research attention because of its discriminative information. This study proposes a robust approach to adaptively extract the hyperspectral palmprint region of interest (ROI) captured by a hyperspectral palmprint acquisition device, which is considered one of the most important stages in palmprint recognition. For different spectral wavelengths, the image has different illuminations and unbalanced shadows. In particular, mean grey values of palm images in different bands have large variations, such that binarisation of the palm image can be considered a challenging task to accurately separate the contour of the palm from the original image. To solve these problems, this study proposes an adaptive ROI segmentation algorithm, whereby a support vector machine-based method is used to detect the palm from the image and a coordinate established to ensure the accuracy of the ROI. The proposed method has been tested on a hyperspectral palm data set which covers spectrums from 530–1030 nm with 20 nm intervals. The experimental results showed that the proposed algorithm is effective and efficient at locating the ROI in hyperspectral palmprint images, where local binary pattern features were extracted from the ROIs achieving an equal error rate (EER) of 1.49% and an accuracy of 99.51% in recognition.

TriPepSVM: de novo prediction of RNA-binding proteins based on short amino acid motifs.

In recent years, hundreds of novel RNA-binding proteins (RBPs) have been identified, leading to the discovery of novel RNA-binding domains. Furthermore, unstructured or disordered low-complexity regions of RBPs have been identified to play an important role in interactions with nucleic acids. However, these advances in understanding RBPs are limited mainly to eukaryotic species and we only have limited tools to faithfully predict RNA-binders in bacteria. Here, we describe a support vector machine-based method, called TriPepSVM, for the prediction of RNA-binding proteins. TriPepSVM applies string kernels to directly handle protein sequences using tri-peptide frequencies. Testing the method in human and bacteria, we find that several RBP-enriched tri-peptides occur more often in structurally disordered regions of RBPs. TriPepSVM outperforms existing applications, which consider classical structural features of RNA-binding or homology, in the task of RBP prediction in both human and bacteria. Finally, we predict 66 novel RBPs in Salmonella Typhimurium and validate the bacterial proteins ClpX, DnaJ and UbiG to associate with RNA in vivo.

Identification of repurposed protein kinase B binders from FDA-approved drug library: a hybrid–structure activity relationship and systems modeling based approach

Food and Drug Administration (FDA)-approved drugs may be repurposed against those diseases, for which their therapeutic action has not been described. The present study deals with repurposing FDA-approved drugs for selective targeting of protein kinase B (PKB/Akt) for anti-cancer activity, through a two-tier (Cell and Target) model hybridization protocol implemented with support vector machine-based learning method. The hybridization was done as per rules of reaction kinetics. The hybridization process was facilitated as a standalone application for free access at https://github.com/undwivedi/Akt-Selective.git. The selectivity of the ligands for PKB/Akt binding was also evaluated on the basis of mitophagy system model for anti-apoptotic activity. Screening of the FDA-approved drug library, using the developed H- SAR model, led to identification of four compounds (Cas nos. 94749-08-3, 57808-66-9, 62-13-5, 76-43-7), bearing the selectivity for PKB/Akt. Since, the identified compounds have already crossed the barriers of absorption, distribution, metabolism, excretion, toxicity in clinical trials, therefore are safe to be considered for repurposing individually or in combination with other drugs.Communicated by Ramaswamy H. Sarma

An ensemble method for multi-type Gram-negative bacterial secreted protein prediction by integrating different PSSM-based features

ABSTRACTIn Gram-negative bacteria, a wide range of proteins are secreted by highly specialized secretion systems. These secreted proteins play essential roles in the response of bacteria to their environment and also in several physiological processes such as adhesion, pathogenicity, adaptation and survival. Therefore, identifying secreted proteins in Gram-negative bacteria may assist in understanding the secretion mechanism and development of new antimicrobial strategies. Considering that a single-feature model is less likely to comprehensively cover this information, three kinds of feature models were used in this paper to represent protein samples by composition analysis, correlation analysis and smoothing encoding method on position-specific scoring matrix profiles. A support vector machine-based ensemble method with these hybrid features was developed to predict multi-type Gram-negative bacterial secreted proteins. Finally, our method achieves overall accuracies of 97.09% and 96.51% using an independent dataset test and jackknife test on a public test dataset, which are 3.49% and 2.32% higher, respectively, than results obtained by other methods. These results show the effectiveness and stability of the proposed ensemble method. It is anticipated that our method will provide useful information for further research on bacterial secreted proteins and secreted systems.

An improved support vector machine-based diabetic readmission prediction

Background and objectiveIn healthcare systems, the cost of unplanned readmission accounts for a large proportion of total hospital payment. Hospital-specific readmission rate becomes a critical issue around the world. Quantification and early identification of unplanned readmission risks will improve the quality of care during hospitalization and reduce the occurrence of readmission. In clinical practice, medical workers generally use LACE score method to evaluate patient readmission risks, but this method usually performs poorly. With this in mind, this study presents a novel method combining support vector machine and genetic algorithm to build the risk prediction model, which simultaneously involves feature selection and the processing of imbalanced data. This model aims to provide decision support for clinicians during the discharge management of patients with diabetes. MethodThe experiments were conducted from a set of 8756 medical records with 50 different features about diabetic readmission. After preprocessing the data, an effective SMOTE-based method was proposed to solve the imbalance data problem. Further, in order to improve prediction performance, a hybrid feature selection mechanism was devised to select the important features. Subsequently, an improved support vector machine-based (SVM-based) method was developed and the genetic algorithm was used to tune the sensitive parameter of the algorithm. Finally, the five-fold cross-validation method was applied to compare the performance of proposed method with other methods (LACE score, logistic regression, naïve bayes, decision tree and feed forward neural networks). ResultsExperimental results indicate that the proposed SVM-based method achieves an accuracy of 81.02%, a sensitivity of 82.89%, a specificity of 79.23%, and outperforms other popular algorithms in identifying diabetic patients who may be readmitted. ConclusionsOur research can improve the performance of clinic decision support systems for diabetic readmission, by which the readmission possibility as well as the waste of medical resources can be reduced.

Prediction of zinc binding sites in proteins using sequence derived information

Zinc is one the most abundant catalytic cofactor and also an important structural component of a large number of metallo-proteins. Hence prediction of zinc metal binding sites in proteins can be a significant step in annotation of molecular function of a large number of proteins. Majority of existing methods for zinc-binding site predictions are based on a data-set of proteins, which has been compiled nearly a decade ago. Hence there is a need to develop zinc-binding site prediction system using the current updated data to include recently added proteins. Herein, we propose a support vector machine-based method, named as ZincBinder, for prediction of zinc metal-binding site in a protein using sequence profile information. The predictor was trained using fivefold cross validation approach and achieved 85.37% sensitivity with 86.20% specificity during training. Benchmarking on an independent non-redundant data-set, which was not used during training, showed better performance of ZincBinder vis-à-vis existing methods. Executable versions, source code, sample datasets, and usage instructions are available at http://proteininformatics.org/mkumar/znbinder/

Improving Hyperspectral Image Classification by Fusing Spectra and Absorption Features

Many features can be extracted to classify hyperspectral imagery. Classification relying on a single feature set may lose some useful information due to the intrinsic limitation of each feature extraction model. To improve classification accuracy, we propose an information fusion approach, in which both the global and the local aspects of hyperspectral data are taken into account and are combined by a decision-level fusion method. The global features are hyperspectral reflectance curves representing the holistic response to the incident light, and the local features are absorption characteristics reflected by materials’ individual constituents. The decision-level fusion is carried out by analyzing the entropy of the classification output from the global feature set and modifying this output via the results of a multilabel classification using the local feature set. Simulations of classification performance on 16 classes of vegetation from the AVIRIS 92AV3C and Salinas data set show the effectiveness of the method, which increases the classification accuracy compared to a popular support vector machine-based method and a production-rule-based decision fusion method.

Identifying N 6-methyladenosine sites in the Arabidopsis thaliana transcriptome

N 6-Methyladenosine (m6A) plays important roles in many biological processes. The knowledge of the distribution of m6A is helpful for understanding its regulatory roles. Although the experimental methods have been proposed to detect m6A, the resolutions of these methods are still unsatisfying especially for Arabidopsis thaliana. Benefitting from the experimental data, in the current work, a support vector machine-based method was proposed to identify m6A sites in A. thaliana transcriptome. The proposed method was validated on a benchmark dataset using jackknife test and was also validated by identifying strain-specific m6A sites in A. thaliana. The obtained predictive results indicate that the proposed method is quite promising. For the convenience of experimental biologists, an online webserver for the proposed method was built, which is freely available at http://lin.uestc.edu.cn/server/M6ATH . These results indicate that the proposed method holds a potential to become an elegant tool in identifying m6A site in A. thaliana.

A support vector machine-based method to identify mild cognitive impairment with multi-level characteristics of magnetic resonance imaging

Mild cognitive impairment (MCI) represents a transitional state between normal aging and Alzheimer’s disease (AD). Non-invasive diagnostic methods are desirable to identify MCI for early therapeutic interventions. In this study, we proposed a support vector machine (SVM)-based method to discriminate between MCI patients and normal controls (NCs) using multi-level characteristics of magnetic resonance imaging (MRI). This method adopted a radial basis function (RBF) as the kernel function, and a grid search method to optimize the two parameters of SVM. The calculated characteristics, i.e., the Hurst exponent (HE), amplitude of low-frequency fluctuations (ALFF), regional homogeneity (ReHo) and gray matter density (GMD), were adopted as the classification features. A leave-one-out cross-validation (LOOCV) was used to evaluate the classification performance of the method. Applying the proposed method to the experimental data from 29 MCI patients and 33 healthy subjects, we achieved a classification accuracy of up to 96.77%, with a sensitivity of 93.10% and a specificity of 100%, and the area under the curve (AUC) yielded up to 0.97. Furthermore, the most discriminative features for classification were found to predominantly involve default-mode regions, such as hippocampus (HIP), parahippocampal gyrus (PHG), posterior cingulate gyrus (PCG) and middle frontal gyrus (MFG), and subcortical regions such as lentiform nucleus (LN) and amygdala (AMYG). Therefore, our method is promising in distinguishing MCI patients from NCs and may be useful for the diagnosis of MCI.

Novel Grouping Method-based support vector machine plus for structured data

In the traditional Support Vector Machine Plus (SVM+), the grouping method has great randomness and only takes into account part of the structural information of the dataset. In order to overcome these shortcomings, in this paper, we propose a novel framework termed as FCSVM+ to improve the performance of SVM+ by combining clustering technique and feature selection. The new framework strategy is expected to not only take fully into account the structural information of the training data, but also partition the training data into more meaningful groups. To prove the advantage of the framework, in particular, we adopt two simplest feature selection methods, i.e. F-score and Laplacian score methods, to select the features, then apply a recently proposed clustering technique to get a better partition of training data by the selected features, in which the number of clusters could be found automatically. Three major contributions of this paper can be concluded as: (1) improving the performance of the existing SVM+ classifier; (2) extracting the potential structural information of the training data by using more feature attributes instead of one; (3) replacing the truncation method in SVM+ with a clustering technique. The comprehensive experimental results on the UCI benchmark datasets illustrate the validity and advantage of our approach.

Identifying 2′-O-methylationation sites by integrating nucleotide chemical properties and nucleotide compositions

2′-O-methylationation is an important post-transcriptional modification and plays important roles in many biological processes. Although experimental technologies have been proposed to detect 2′-O-methylationation sites, they are cost-ineffective. As complements to experimental techniques, computational methods will facilitate the identification of 2′-O-methylationation sites. In the present study, we proposed a support vector machine-based method to identify 2′-O-methylationation sites. In this method, RNA sequences were formulated by nucleotide chemical properties and nucleotide compositions. In the jackknife cross-validation test, the proposed method obtained an accuracy of 95.58% for identifying 2′-O-methylationation sites in the human genome. Moreover, the model was also validated by identifying 2′-O-methylation sites in the Mus musculus and Saccharomyces cerevisiae genomes, and the obtained accuracies are also satisfactory. These results indicate that the proposed method will become a useful tool for the research on 2′-O-methylation.