Ectoine hyperproduction by engineered Halomonas bluephagenesis.

Ectoine, a crucial osmoprotectant for salt adaptation in halophiles, has gained growing interest in cosmetics and medical industries. However, its production remains challenged by stringent fermentation process in model microorganisms and low production level in its native producers. Here, we systematically engineered the native ectoine producer Halomonas bluephagenesis for ectoine production by overexpressing ectABC operon, increasing precursors availability, enhancing product transport system and optimizing its growth medium. The final engineered H. bluephagenesis produced 85 g/L ectoine in 52 h under open unsterile incubation in a 7 L bioreactor in the absence of plasmid, antibiotic or inducer. Furthermore, it was successfully demonstrated the feasibility of decoupling salt concentration with ectoine synthesis and co-production with bioplastic P(3HB-co-4HB) by the engineered H. bluephagenesis. The unsterile fermentation process and significantly increased ectoine titer indicate that H. bluephagenesis as the chassis of Next-Generation Industrial Biotechnology (NGIB), is promising for the biomanufacturing of not only intracellular bioplastic PHA but also small molecular compound such as ectoine.

Engineering low-salt growth Halomonas Bluephagenesis for cost-effective bioproduction combined with adaptive evolution.

Halophilic Halomonas bluephagenesis has been engineered to produce various added-value bio-compounds with reduced costs. However, the salt-stress regulatory mechanism remained unclear. H. bluephagenesis was randomly mutated to obtain low-salt growing mutants via atmospheric and room temperature plasma (ARTP). The resulted H. bluephagenesis TDH4A1B5 was constructed with the chromosomal integration of polyhydroxyalkanoates (PHA) synthesis operon phaCAB and deletion of phaP1 gene encoding PHA synthesis associated protein phasin, forming H. bluephagenesis TDH4A1B5P, which led to increased production of poly(3-hydroxybutyrate) (PHB) and poly(3-hydroxybutyrate-co-4-hydrobutyrate) (P34HB) by over 1.4-fold. H. bluephagenesis TDH4A1B5P also enhanced production of ectoine and threonine by 50% and 77%, respectively. A total 101 genes related to salinity tolerance was identified and verified via comparative genomic analysis among four ARTP mutated H. bluephagenesis strains. Recombinant H. bluephagenesis TDH4A1B5P was further engineered for PHA production utilizing sodium acetate or gluconate as sole carbon source. Over 33% cost reduction of PHA production could be achieved using recombinant H. bluephagenesis TDH4A1B5P. This study successfully developed a low-salt tolerant chassis H. bluephagenesis TDH4A1B5P and revealed salt-stress related genes of halophilic host strains.

MOCSS: Multi-omics data clustering and cancer subtyping via shared and specific representation learning.

Cancer is an extremely complex disease and each type of cancer usually has several different subtypes. Multi-omics data can provide more comprehensive biological information for identifying and discovering cancer subtypes. However, existing unsupervised cancer subtyping methods cannot effectively learn comprehensive shared and specific information of multi-omics data. Therefore, a novel method is proposed based on shared and specific representation learning. For each omics data, two autoencoders are applied to extract shared and specific information, respectively. To reduce redundancy and mutual interference, orthogonality constraint is introduced to separate shared and specific information. In addition, contrastive learning is applied to align the shared information and strengthen their consistency. Finally, the obtained shared and specific information for all samples are used for clustering tasks to achieve cancer subtyping. Experimental results demonstrate that the proposed method can effectively capture shared and specific information of multi-omics data and outperform other state-of-the-art methods on cancer subtyping.

Efficacy of Mobile-Based Cognitive Behavioral Therapy on Lowering Low-density Lipoprotein Cholesterol Levels in Patients With Atherosclerotic Cardiovascular Disease: Multicenter, Prospective Randomized Controlled Trial.

BACKGROUND: Elevated low-density lipoprotein cholesterol (LDL-C) is an established risk factor for atherosclerotic cardiovascular disease (ASCVD). However, low adherence to medication and lifestyle management has limited the benefits of lowering lipid levels. Cognitive behavioral therapy (CBT) has been proposed as a promising solution. OBJECTIVE: This trial aimed to evaluate the efficacy of mobile-based CBT interventions in lowering LDL-C levels in patients with ASCVD. METHODS: This multicenter, prospective, randomized controlled trial enrolled 300 patients with ASCVD, who were randomly assigned to the mobile-based CBT intervention group and the control group in a ratio of 1:1. The intervention group received CBT for ASCVD lifestyle interventions delivered by WeChat MiniApp: "CBT ASCVD." The control group only received routine health education during each follow-up. The linear regression and logistic regression analyses were used to determine the effects of a mobile-based CBT intervention on LDL-C, triglyceride, C-reactive protein, the score of General Self-Efficacy Scale (GSE), quality of life index (QL-index), and LDL-C up-to-standard rate (<1.8 mmol/L) at the first, third, and sixth months. RESULTS: Finally, 296 participants completed the 6-month follow-up (CBT group: n=148; control group: n=148). At baseline, the mean LDL-C level was 2.48 (SD 0.90) mmol/L, and the LDL-C up-to-standard rate (<1.8 mmol/L) was 21.3%. Mobile-based CBT intervention significantly increased the reduction of LDL-C change (%) at the 6-month follow-up (ß=-10.026, 95% CI -18.111 to -1.940). In addition, this benefit remained when baseline LDL-C <1.8 mmol/L (ß=-24.103, 95% CI -43.110 to -5.095). Logistic regression analysis showed that mobile-based CBT intervention moderately increased the LDL-C up-to-standard rates (<1.8 mmol/L) in the sixth month (odds ratio 1.579, 95% CI 0.994-2.508). For GSE and QL-index, mobile-based CBT intervention significantly increased the change of scores (%) at the 1-, 3-, and 6-month follow-up (all P values <.05). CONCLUSIONS: In patients with ASCVD, mobile-based CBT is effective in reducing LDL-C levels (even for those who already had a standard LDL-C) and can improve self-efficacy and quality of life. TRIAL REGISTRATION: Chinese Clinical Trial Registry ChiCTR2100046775; https://www.chictr.org.cn/showproj.aspx?proj=127140.

A benchmark study of deep learning-based multi-omics data fusion methods for cancer.

BACKGROUND: A fused method using a combination of multi-omics data enables a comprehensive study of complex biological processes and highlights the interrelationship of relevant biomolecules and their functions. Driven by high-throughput sequencing technologies, several promising deep learning methods have been proposed for fusing multi-omics data generated from a large number of samples. RESULTS: In this study, 16 representative deep learning methods are comprehensively evaluated on simulated, single-cell, and cancer multi-omics datasets. For each of the datasets, two tasks are designed: classification and clustering. The classification performance is evaluated by using three benchmarking metrics including accuracy, F1 macro, and F1 weighted. Meanwhile, the clustering performance is evaluated by using four benchmarking metrics including the Jaccard index (JI), C-index, silhouette score, and Davies Bouldin score. For the cancer multi-omics datasets, the methods' strength in capturing the association of multi-omics dimensionality reduction results with survival and clinical annotations is further evaluated. The benchmarking results indicate that moGAT achieves the best classification performance. Meanwhile, efmmdVAE, efVAE, and lfmmdVAE show the most promising performance across all complementary contexts in clustering tasks. CONCLUSIONS: Our benchmarking results not only provide a reference for biomedical researchers to choose appropriate deep learning-based multi-omics data fusion methods, but also suggest the future directions for the development of more effective multi-omics data fusion methods. The deep learning frameworks are available at https://github.com/zhenglinyi/DL-mo .

Effective production of Poly(3-hydroxybutyrate-co-4-hydroxybutyrate) by engineered Halomonas bluephagenesis grown on glucose and 1,4-Butanediol.

Halomonas bluephagenesis has been engineered to produce flexible copolymers P34HB or poly(3-hydroxybutyrate-co-4-hydroxybutyrate) from glucose and petrol-chemical precursor, γ-butyrolactone. Herein, gene cluster aldD-dhaT was constructed in recombinant H. bluephagenesis for catalyzing 1,4-butanediol (BDO) into 4-hydroxybutyrate, which could grow to 86 g L-1 dry cell mass (DCM) containing 77 wt% P(3HB-co-14 mol% 4HB) in 7-L bioreactor fed with glucose and bio-based BDO. Furthermore, 4HB monomer ratio could be increased to 16 mol% by engineered H. bluephagenesis TDH4-WZY254 with defected outer-membrane. Upon deletion of 4HB degradation pathway, followed by aldD-dhaT integration, the resulted H. bluephagenesis TDB141ΔAC was grown to 95 g L-1 DCM containing 79 wt% P(3HB-co-14 mol% 4HB) with a BDO conversion efficiency of 86% under fed-batch fermentation. Notably, 4HB molar ratio can be significantly improved to 21 mol% with negligible effects on cell growth and P34HB synthesis by adding 50% more BDO. This study successfully demonstrated a fully bio-based P34HB effectively produced by H. bluephagenesis.

DTI-HETA: prediction of drug-target interactions based on GCN and GAT on heterogeneous graph.

Drug-target interaction (DTI) prediction plays an important role in drug repositioning, drug discovery and drug design. However, due to the large size of the chemical and genomic spaces and the complex interactions between drugs and targets, experimental identification of DTIs is costly and time-consuming. In recent years, the emerging graph neural network (GNN) has been applied to DTI prediction because DTIs can be represented effectively using graphs. However, some of these methods are only based on homogeneous graphs, and some consist of two decoupled steps that cannot be trained jointly. To further explore GNN-based DTI prediction by integrating heterogeneous graph information, this study regards DTI prediction as a link prediction problem and proposes an end-to-end model based on HETerogeneous graph with Attention mechanism (DTI-HETA). In this model, a heterogeneous graph is first constructed based on the drug-drug and target-target similarity matrices and the DTI matrix. Then, the graph convolutional neural network is utilized to obtain the embedded representation of the drugs and targets. To highlight the contribution of different neighborhood nodes to the central node in aggregating the graph convolution information, a graph attention mechanism is introduced into the node embedding process. Afterward, an inner product decoder is applied to predict DTIs. To evaluate the performance of DTI-HETA, experiments are conducted on two datasets. The experimental results show that our model is superior to the state-of-the-art methods. Also, the identification of novel DTIs indicates that DTI-HETA can serve as a powerful tool for integrating heterogeneous graph information to predict DTIs.

A Deep Learning-Based Classification Method for Different Frequency EEG Data.

In recent years, the research on electroencephalography (EEG) has focused on the feature extraction of EEG signals. The development of convenient and simple EEG acquisition devices has produced a variety of EEG signal sources and the diversity of the EEG data. Thus, the adaptability of EEG classification methods has become significant. This study proposed a deep network model for autonomous learning and classification of EEG signals, which could self-adaptively classify EEG signals with different sampling frequencies and lengths. The artificial design feature extraction methods could not obtain stable classification results when analyzing EEG data with different sampling frequencies. However, the proposed depth network model showed considerably better universality and classification accuracy, particularly for EEG signals with short length, which was validated by two datasets.

Drug-Target Interaction Prediction Based on Adversarial Bayesian Personalized Ranking.

The prediction of drug-target interaction (DTI) is a key step in drug repositioning. In recent years, many studies have tried to use matrix factorization to predict DTI, but they only use known DTIs and ignore the features of drug and target expression profiles, resulting in limited prediction performance. In this study, we propose a new DTI prediction model named AdvB-DTI. Within this model, the features of drug and target expression profiles are associated with Adversarial Bayesian Personalized Ranking through matrix factorization. Firstly, according to the known drug-target relationships, a set of ternary partial order relationships is generated. Next, these partial order relationships are used to train the latent factor matrix of drugs and targets using the Adversarial Bayesian Personalized Ranking method, and the matrix factorization is improved by the features of drug and target expression profiles. Finally, the scores of drug-target pairs are achieved by the inner product of latent factors, and the DTI prediction is performed based on the score ranking. The proposed model effectively takes advantage of the idea of learning to rank to overcome the problem of data sparsity, and perturbation factors are introduced to make the model more robust. Experimental results show that our model could achieve a better DTI prediction performance.

NegStacking: Drug-Target Interaction Prediction Based on Ensemble Learning and Logistic Regression.

Drug-target interactions (DTIs) identification is an important issue of drug research, and many methods proposed to predict potential DTIs based on machine learning treat it as a binary classification problem. However, the number of known interacting drug-target pairs (positive samples) is far less than that of non-interacting pairs (negative samples). Most methods do not utilize these large numbers of negative samples sufficiently, which limits their prediction performance. To address this problem, we proposed a stacking framework named NegStacking. First, it uses sampling to obtain multiple completely different negative sample sets. Then, each weak learner is trained with a different negative sample set and the same positive sample set, and the logistic regression (LR) is used as a meta-learner to adaptively combine these weak learners. Moreover, in the training process, feature subspacing and hyperparameter perturbation are applied to increase ensemble diversity. Finally, the trained model could be used to predict new samples. We compared NegStacking with other methods, and the experimental results show that our model is superior. NegStacking can improve the performance of predictive DTIs, and it has broad application prospects for improving the drug discovery process. The source code and datasets are available at https://github.com/Open-ss/NegStacking.

Domain-adversarial multi-task framework for novel therapeutic property prediction of compounds.

MOTIVATION: With the rapid development of high-throughput technologies, parallel acquisition of large-scale drug-informatics data provides significant opportunities to improve pharmaceutical research and development. One important application is the purpose prediction of small-molecule compounds with the objective of specifying the therapeutic properties of extensive purpose-unknown compounds and repurposing the novel therapeutic properties of FDA-approved drugs. Such a problem is extremely challenging because compound attributes include heterogeneous data with various feature patterns, such as drug fingerprints, drug physicochemical properties and drug perturbation gene expressions. Moreover, there is a complex non-linear dependency among heterogeneous data. In this study, we propose a novel domain-adversarial multi-task framework for integrating shared knowledge from multiple domains. The framework first uses an adversarial strategy to learn target representations and then models non-linear dependency among several domains. RESULTS: Experiments on two real-world datasets illustrate that our approach achieves an obvious improvement over competitive baselines. The novel therapeutic properties of purpose-unknown compounds that we predicted have been widely reported or brought to clinics. Furthermore, our framework can integrate various attributes beyond the three domains examined herein and can be applied in industry for screening significant numbers of small-molecule drug candidates. AVAILABILITY AND IMPLEMENTATION: The source code and datasets are available at https://github.com/JohnnyY8/DAMT-Model. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Deep learning-based transcriptome data classification for drug-target interaction prediction.

BACKGROUND: The ability to predict the interaction of drugs with target proteins is essential to research and development of drug. However, the traditional experimental paradigm is costly, and previous in silico prediction paradigms have been impeded by the wide range of data platforms and data scarcity. RESULTS: In this paper, we modeled the prediction of drug-target interactions as a binary classification task. Using transcriptome data from the L1000 database of the LINCS project, we developed a framework based on a deep-learning algorithm to predict potential drug target interactions. Once fully trained, the model achieved over 98% training accuracy. The results of our research demonstrated that our framework could discover more reliable DTIs than found by other methods. This conclusion was validated further across platforms with a high percentage of overlapping interactions. CONCLUSIONS: Our model's capacity of integrating transcriptome data from drugs and genes strongly suggests the strength of its potential for DTI prediction, thereby improving the drug discovery process.

QTL mapping and epistatic interaction analysis of field resistance to sudden death syndrome (Fusarium virguliforme) in soybean.

KEY MESSAGE: Two interactive quantitative trait loci (QTLs) controlled the field resistance to sudden death syndrome (SDS) in soybean. The interaction between them was confirmed. Sudden death syndrome (SDS), caused by Fusarium virguliforme, is a major disease of soybean [Glycine max (L.) Merr.] in the United States. Breeding for soybean resistance to SDS is the most cost-effective method to manage the disease. The objective of this study was to identify and characterize quantitative trait loci (QTLs) underlying field resistance to SDS in a recombinant inbred line population from the cross GD2422 × LD01-5907. This population was genotyped with 1786 polymorphic single nucleotide polymorphisms (SNPs) using SoySNP6 K iSelect BeadChip and evaluated for SDS resistance in a naturally infested field. Four SDS resistance QTLs were mapped on Chromosomes 4, 8, 12 and 18. The resistant parent, LD01-5907, contributed the resistance alleles for the QTLs on Chromosomes 8 and 18 (qSDS-8 and qSDS-18), while the other parent, GD2422, provided the resistance alleles for the QTLs on Chromosomes 4 and 12 (qSDS-4 and qSDS-12). The minor QTL on Chromosome 12 (qSDS-12) is novel. The QTL on Chromosomes 8 and 18 (qSDS-8 and qSDS-18) overlapped with two soybean cyst nematode resistance-related loci, Rhg4 and Rhg1, respectively. A significant interaction between qSDS-8 and qSDS-18 was detected by disease incidence. Individual effects together with the interaction effect explained around 70% of the phenotypic variance. The epistatic interaction of qSDS-8 and qSDS-18 was confirmed by the field performance across multiple years. Furthermore, the resistance alleles at qSDS-8 and qSDS-18 were demonstrated to be recessive. The SNP markers linked to these QTLs will be useful for marker-assisted breeding to enhance the SDS resistance.

Fine mapping of the soybean aphid-resistance genes Rag6 and Rag3c from Glycine soja 85-32.

KEY MESSAGE: Rag6 and Rag3c were delimited to a 49-kb interval on chromosome 8 and a 150-kb interval on chromosome 16, respectively. Structural variants in the exons of candidate genes were identified. The soybean aphid, an invasive species, has significantly threatened soybean production in North America since 2000. Host-plant resistance is known as an ideal management strategy for aphids. Two novel aphid-resistance loci, Rag6 and Rag3c, from Glycine soja 85-32, were previously detected in a 10.5-cM interval on chromosome 8 and a 7.5-cM interval on chromosome 16, respectively. Defining the exact genomic position of these two genes is critical for improving the effectiveness of marker-assisted selection for aphid resistance and for identification of the functional genes. To pinpoint the locations of Rag6 and Rag3c, four populations segregating for Rag6 and Rag3c were used to fine map these two genes. The availability of the Illumina Infinium SoySNP50K/8K iSelect BeadChip, combined with single-nucleotide polymorphism (SNP) markers discovered through the whole-genome re-sequencing of E12901, facilitated the fine mapping process. Rag6 was refined to a 49-kb interval on chromosome 8 with four candidate genes, including three clustered nucleotide-binding site leucine-rich repeat (NBS-LRR) genes and an amine oxidase encoding gene. Rag3c was refined to a 150-kb interval on chromosome 16 with 11 candidate genes, two of which are a LRR gene and a lipase gene. Moreover, by sequencing the whole-genome exome-capture of the resistant source (E12901), structural variants were identified in the exons of the candidate genes of Rag6 and Rag3c. The closely linked SNP markers and the candidate gene information presented in this study will be significant resources for integrating Rag6 and Rag3c into elite cultivars and for future functional genetics studies.

Discovery of novel therapeutic properties of drugs from transcriptional responses based on multi-label classification.

Drug repositioning strategies have improved substantially in recent years. At present, two advances are poised to facilitate new strategies. First, the LINCS project can provide rich transcriptome data that reflect the responses of cells upon exposure to various drugs. Second, machine learning algorithms have been applied successfully in biomedical research. In this paper, we developed a systematic method to discover novel indications for existing drugs by approaching drug repositioning as a multi-label classification task and used a Softmax regression model to predict previously unrecognized therapeutic properties of drugs based on LINCS transcriptome data. This approach to complete the said task has not been achieved in previous studies. By performing in silico comparison, we demonstrated that the proposed Softmax method showed markedly superior performance over those of other methods. Once fully trained, the method showed a training accuracy exceeding 80% and a validation accuracy of approximately 70%. We generated a highly credible set of 98 drugs with high potential to be repositioned for novel therapeutic purposes. Our case studies included zonisamide and brinzolamide, which were originally developed to treat indications of the nervous system and sensory organs, respectively. Both drugs were repurposed to the cardiovascular category.

Mapping novel aphid resistance QTL from wild soybean, Glycine soja 85-32.

KEY MESSAGE: Two novel QTLs conferring aphid resistance were mapped and validated on soybean chromosomes 8 and 16, respectively. Closely linked markers were developed to assist breeding for aphid resistance. Soybean aphid, Aphis glycines Matsumura, is a highly destructive pest for soybean production. E08934, a soybean advanced breeding line derived from the wild soybean Glycine soja 85-32, has shown strong resistance to aphids. To dissect the genetic basis of aphid resistance in E08934, a mapping population (070020) consisting of 140 F3-derived lines was developed by crossing E08934 with an aphid-susceptible line E00003. This mapping population was evaluated for aphid resistance in a greenhouse trial in 2010 and three field trials in 2009, 2010, and 2011, respectively. The broad-sense heritability across the field trials was 0.84. In the mapping population 070020, two major quantitative trait loci (QTL) were detected as significantly associated with aphid resistance, and designated as Rag6 and Rag3c, respectively. Rag6 was mapped to a 10.5 centiMorgan (cM) interval between markers MSUSNP08-2 and Satt209 on chromosome 8, explaining 19.5-46.4% of the phenotypic variance in different trials. Rag3c was located at a 7.5 cM interval between markers MSUSNP16-10 and Sat_370 on chromosome 16, explaining 12.5-22.9% of the phenotypic variance in different trials. Rag3c had less resistance effect than Rag6 across all the trials. Furthermore, Rag6 and Rag3c were confirmed in two validation populations with different genetic backgrounds. No significant interaction was detected between Rag6 and Rag3c in either the mapping population or the validation populations. Both Rag6 and Rag3c were indicated as conferring antibiosis resistance to aphids by a no-choice test. The new aphid-resistance gene(s) derived from the wild germplasm G. soja 85-32 are valuable in improving soybeans for aphid resistance.

Effective and extensible feature extraction method using genetic algorithm-based frequency-domain feature search for epileptic EEG multiclassification.

In this paper, genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to classify EEG signals. The extracted features are analyzed experimentally. The features extracted by GAFDS show remarkable independence, and they are superior to the nonlinear features in terms of the ratio of interclass distance and intraclass distance. Moreover, the proposed feature search method can search for features of instantaneous frequency in a signal after Hilbert transformation. The classification results achieved using these features are reasonable; thus, GAFDS exhibits good extensibility. Multiple classical classifiers (i.e., k-nearest neighbor, linear discriminant analysis, decision tree, AdaBoost, multilayer perceptron, and Naïve Bayes) achieve satisfactory classification accuracies by using the features generated by the GAFDS method and the optimized feature selection. The accuracies for 2-classification and 3-classification problems may reach up to 99% and 97%, respectively. Results of several cross-validation experiments illustrate that GAFDS is effective in the extraction of effective features for EEG classification. Therefore, the proposed feature selection and optimization model can improve classification accuracy.

Automatic epileptic seizure detection in EEGs using MF-DFA, SVM based on cloud computing.

BACKGROUND: Epilepsy is a chronic disease with transient brain dysfunction that results from the sudden abnormal discharge of neurons in the brain. Since electroencephalogram (EEG) is a harmless and noninvasive detection method, it plays an important role in the detection of neurological diseases. However, the process of analyzing EEG to detect neurological diseases is often difficult because the brain electrical signals are random, non-stationary and nonlinear. OBJECTIVE: In order to overcome such difficulty, this study aims to develop a new computer-aided scheme for automatic epileptic seizure detection in EEGs based on multi-fractal detrended fluctuation analysis (MF-DFA) and support vector machine (SVM). METHODS: New scheme first extracts features from EEG by MF-DFA during the first stage. Then, the scheme applies a genetic algorithm (GA) to calculate parameters used in SVM and classify the training data according to the selected features using SVM. Finally, the trained SVM classifier is exploited to detect neurological diseases. The algorithm utilizes MLlib from library of SPARK and runs on cloud platform. RESULTS: Applying to a public dataset for experiment, the study results show that the new feature extraction method and scheme can detect signals with less features and the accuracy of the classification reached up to 99%. CONCLUSIONS: MF-DFA is a promising approach to extract features for analyzing EEG, because of its simple algorithm procedure and less parameters. The features obtained by MF-DFA can represent samples as well as traditional wavelet transform and Lyapunov exponents. GA can always find useful parameters for SVM with enough execution time. The results illustrate that the classification model can achieve comparable accuracy, which means that it is effective in epileptic seizure detection.

Features extraction and multi-classification of sEMG using a GPU-Accelerated GA/MLP hybrid algorithm.

BACKGROUND: Surface electromyography (sEMG) signal is the combined effect of superficial muscle EMG and neural electrical activity. In recent years, researchers did large amount of human-machine system studies by using the physiological signals as control signals. OBJECTIVE: To develop and test a new multi-classification method to improve performance of analyzing sEMG signals based on public sEMG dataset. METHODS: First, ten features were selected as candidate features. Second, a genetic algorithm (GA) was applied to select representative features from the initial ten candidates. Third, a multi-layer perceptron (MLP) classifier was trained by the selected optimal features. Last, the trained classifier was used to predict the classes of sEMG signals. A special graphics processing unit (GPU) was used to speed up the learning process. RESULTS: Experimental results show that the classification accuracy of the new method reached higher than 90%. Comparing to other previously reported results, using the new method yielded higher performance. CONCLUSIONS: The proposed features selection method is effective and the classification result is accurate. In addition, our method could have practical application value in medical prosthetics and the potential to improve robustness of myoelectric pattern recognition.

A two-dimensional matrix image based feature extraction method for classification of sEMG: A comparative analysis based on SVM, KNN and RBF-NN.

BACKGROUND: The computer mouse is an important human-computer interaction device. But patients with physical finger disability are unable to operate this device. Surface EMG (sEMG) can be monitored by electrodes on the skin surface and is a reflection of the neuromuscular activities. Therefore, we can control limbs auxiliary equipment by utilizing sEMG classification in order to help the physically disabled patients to operate the mouse. OBJECTIVE: To develop a new a method to extract sEMG generated by finger motion and apply novel features to classify sEMG. METHODS: A window-based data acquisition method was presented to extract signal samples from sEMG electordes. Afterwards, a two-dimensional matrix image based feature extraction method, which differs from the classical methods based on time domain or frequency domain, was employed to transform signal samples to feature maps used for classification. In the experiments, sEMG data samples produced by the index and middle fingers at the click of a mouse button were separately acquired. Then, characteristics of the samples were analyzed to generate a feature map for each sample. Finally, the machine learning classification algorithms (SVM, KNN, RBF-NN) were employed to classify these feature maps on a GPU. RESULTS: The study demonstrated that all classifiers can identify and classify sEMG samples effectively. In particular, the accuracy of the SVM classifier reached up to 100%. CONCLUSIONS: The signal separation method is a convenient, efficient and quick method, which can effectively extract the sEMG samples produced by fingers. In addition, unlike the classical methods, the new method enables to extract features by enlarging sample signals' energy appropriately. The classical machine learning classifiers all performed well by using these features.