Natural variation of MS2 confers male fertility and drives hybrid breeding in soybean.

A complete and genetically stable male sterile line with high outcrossing rate is a prerequisite for the development of commercial hybrid soybean. It was reported in the last century that the soybean male sterile ms2 mutant has the highest record with seed set. Here we report the cloning and characterization of the MS2 gene in soybean, which encodes a protein that is specifically expressed in the anther. MS2 functions in the tapetum and microspore by directly regulating genes involved in the biosynthesis of secondary metabolites and the lipid metabolism, which is essential for the formation of microspore cell wall. Through comparison of the field performance with the widely used male sterile mutants in the same genetic background, we demonstrated that the ms2 mutant conducts the best in outcrossing rate and makes it an ideal tool in building a cost-effective hybrid system for soybean.

Alternative Splicing of Heat Shock Transcription Factor 2 Regulates the Expression of Laccase Gene Family in Response to Copper in Trametes trogii.

White-rot fungi, especially Trametes strains, are the primary source of industrial laccases in bioenergy and bioremediation. Trametes strains express members of the laccase gene family with different physicochemical properties and expression patterns. However, the literature on the expression pattern of the laccase gene family in T. trogii S0301 and the response mechanism to Cu2+, a key laccase inducer, in white-rot fungal strains is scarce. In the present study, we found that Cu2+ could induce the mRNAs and proteins of the two alternative splicing variants of heat shock transcription factor 2 (TtHSF2). Furthermore, the overexpression of alternative splicing variants TtHSF2α and TtHSF2ß-I in the homokaryotic T. trogii S0301 strain showed opposite effects on the extracellular total laccase activity, with the maximum laccase activity of approximately 0.6 U mL-1 and 3.0 U mL-1, respectively, on the eighth day, which is 0.4 and 2.3 times that of the wild type strain. Similarly, TtHSF2α and TtHSF2ß-I play opposite roles in the oxidation tolerance to H2O2 In addition, the direct binding of TtHSF2α to the promoter regions of the representative laccase isoenzymes (TtLac1 and TtLac13) and protein-protein interactions between TtHSF2α and TtHSF2ß-I were detected. Our results demonstrate the crucial roles of TtHSF2 and its alternative splicing variants in response to Cu2+ We believe that these findings will deepen our understanding of alternative splicing of HSFs and their regulatory mechanism of the laccase gene family in white-rot fungi.Importance The members of laccase gene family in Trametes strains are the primary source of industrial laccase and have gained widespread attention. Increasing the yield and enzymatic properties of laccase through various methods has always been a topic worthy of attention, and there is no report on the regulation of laccase expression through HSF transcription factor engineering. Here, we found that two alternative splicing variants of TtHSF2 functioned oppositely in regulating the expression of laccase genes, and copper can induce the expression of almost all members of the laccase gene family. Most importantly, our study suggested that TtHSF2 and its alternative splicing variants are vital for copper-induced production of laccases in T. trogii S0301.

Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation.

Mass spectrometry-coupled cellular thermal shift assay (MS-CETSA), a biophysical principle-based technique that measures the thermal stability of proteins at the proteome level inside the cell, has contributed significantly to the understanding of drug mechanisms of action and the dissection of protein interaction dynamics in different cellular states. One of the barriers to the wide applications of MS-CETSA is that MS-CETSA experiments must be performed on the specific cell lines of interest, which is typically time-consuming and costly in terms of labeling reagents and mass spectrometry time. In this study, we aim to predict CETSA features in various cell lines by introducing a computational framework called CycleDNN based on deep neural network technology. For a given set of n cell lines, CycleDNN comprises n auto-encoders. Each auto-encoder includes an encoder to convert CETSA features from one cell line into latent features in a latent space [Formula: see text]. It also features a decoder that transforms the latent features back into CETSA features for another cell line. In such a way, the proposed CycleDNN creates a cyclic prediction of CETSA features across different cell lines. The prediction loss, cycle-consistency loss, and latent space regularization loss are used to guide the model training. Experimental results on a public CETSA dataset demonstrate the effectiveness of our proposed approach. Furthermore, we confirm the validity of the predicted MS-CETSA data from our proposed CycleDNN through validation in protein-protein interaction prediction.

From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks.

Deep neural networks (DNNs) have been widely used in many artificial intelligence (AI) tasks. However, deploying them brings significant challenges due to the huge cost of memory, energy, and computation. To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning. Recently, there has been a surge in research on compression methods to achieve model efficiency while retaining performance. Furthermore, more and more works focus on customizing the DNN hardware accelerators to better leverage the model compression techniques. In addition to efficiency, preserving security and privacy is critical for deploying DNNs. However, the vast and diverse body of related works can be overwhelming. This inspires us to conduct a comprehensive survey on recent research toward the goal of high-performance, cost-efficient, and safe deployment of DNNs. Our survey first covers the mainstream model compression techniques, such as model quantization, model pruning, knowledge distillation, and optimizations of nonlinear operations. We then introduce recent advances in designing hardware accelerators that can adapt to efficient model compression approaches. In addition, we discuss how homomorphic encryption can be integrated to secure DNN deployment. Finally, we discuss several issues, such as hardware evaluation, generalization, and integration of various compression approaches. Overall, we aim to provide a big picture of efficient DNNs from algorithm to hardware accelerators and security perspectives.

Malignancy Suspicious Region Guided Deep Neural Networks for Gastric Ulcer Classification.

Malignant transformation of gastric ulcer can result in gastric cancer, hence an accurate gastric ulcer classification method is of vital importance. Despite marvelous progress has been achieved in recent years, there are still many challenges in diagnosis of gastric ulcer. In this paper, we propose a mechanism to mimic gastroenterologist's behaviours based on deep learning techniques, by integrating the segmented malignancy suspicious masks with gastroscopic images for gastric ulcer classification, which instructs the model to focus on the area where symptoms occur for gastric ulcer diagnosis. Specifically, a U-Net-type deep neural network is built to segment the suspicious pathological regions from gastroscopic images, then the segmented regions are treated as an attention channel of gastroscopic images for the gastric ulcer classification by a ResNet-type deep neural network. Experiments on a real gastroscopic dataset with 900+ patient cases demonstrate that our proposed approach achieves much better performance for gastric ulcer diagnosis, compared with standard method with only gastroscopic images.

Highly Efficient Biotransformation of Phenolic Glycosides Using a Recombinant ß-Glucosidase From White Rot Fungus Trametes trogii.

Phenolic glycosides are the important bioactive molecules, and their bioavailability can be influenced by enzyme hydrolysis, such as ß-glucosidases (EC3.2.1.21) and other glycosyl hydrolases (GHs). Wood rotting fungi possess a superfamily of GHs, but little attention has been paid to the GHs and their potential applications in biotransformation of phenolic glycosides. In this study, two GH3 gene family members of Trametes trogii S0301, mainly expressed in the carbon sources conversion stage were cloned, and TtBgl3 coded by T_trogii_12914 showed ß-glucosidase activity toward 4-nitrophenyl ß-D-glucopyranoside (pNPG). The recombinant TtBgl3 preferred an intermediately neutral optimum pH with >80% of the maximum activity at pH 5.0-7.0 and was stable at a wide range of pH (5.0-10.0). Phenolic glycosides transformation experiments showed that TtBgl3 was a dual-activity enzyme with both activities of aryl-ß-D-glucosidase and ß-glucuronidase, and could hydrolyze the ß-glucoside/glucuronide bond of phenolic glycosides. Under optimized conditions, the recombinant TtBgl3 had much higher transformation efficiency toward the ß-glucoside bond of gastrodin, esculin and daidzin than ß-glucuronide bond of baicalin, with the transformation rate of 100 and 50%, respectively. Our homology modeling, molecular docking, and mutational analysis demonstrated that His85 and Lys467 in the acceptor-binding pocket of TtBgl3 were the potential active sites. The point mutation of His85 and Lys467 leads to the significantly impaired catalytic activity toward pNPG and also the weak transformation efficiency toward gastrodin. These findings provide insights for the identification of novel GH3 ß-glucosidases from T. trogii and other wood-rotting fungi. Furthermore, TtBgl3 might be applied as green and efficient biological catalysts in the deglycosylation of diverse phenolics to produce bioactive glycosides for drug discovery in the future.

CETSA Feature Based Clustering for Protein Outlier Discovery by Protein-to-Protein Interaction Prediction.

The Cellular Thermal Shift Assay (CETSA) is a biophysical assay based on the principle of ligand-induced thermal stabilization of target proteins. This technology has revolutionized cell-based target engagement studies and has been used as guidance for drug design. Although many ap-plications of CETSA data have been explored, the correlations between CETSA data and protein-protein interactions (PPI) have barely been touched. In this study, we conduct the first exploration study applying CETSA data for PPI prediction. We use a machine learning method, Decision Tree, to predict PPI scores using proteins' CETSA features. It shows promising results that the predicted PPI scores closely match the ground-truth PPI scores. Furthermore, for a small number of protein pairs, whose PPI score predictions mismatch the ground truth, we use iterative clustering strategy to gradually reduce the number of these pairs. At the end of iterative clustering, the remaining protein pairs may have some unusual properties and are of scientific value for further biological investigation. Our study has demonstrated that PPI is a brand-new application of CETSA data. At the same time, it also manifests that CETSA data can be used as a new data source for PPI exploration study.

CycleDNN - A Novel Deep Neural Network Model for CETSA Feature Prediction cross Cell Lines.

Cellular Thermal Shift Assay (CETSA) has been widely used in drug discovery, cancer cell biology, immunology, etc. One of the barriers for CETSA applications is that CETSA experiments have to be conducted on various cell lines, which is extremely time-consuming and costly. In this study, we make an effort to explore the translation of CETSA features cross cell lines, i.e., known CETSA feature of a given protein in one cell line, can we automatically predict the CETSA feature of this protein in another cell line, and vice versa? Inspired by pix2pix and CycleGAN, which perform well on image-to-image translation cross various domains in computer vision, we propose a novel deep neural network model called CycleDNN for CETSA feature translation cross cell lines. Given cell lines A and B, the proposed CycleDNN consists of two auto-encoders, the first one encodes the CETSA feature from cell line A into Z in the latent space [Formula: see text], then decodes Z into the CETSA feature in cell line B., Similarly, the second one translates the CETSA feature from cell line B to cell line A through the latent space [Formula: see text]. In such a way, the two auto-encoders form a cyclic feature translation between cell lines. The reconstructed loss, cycle-consistency loss, and latent vector regularization loss are used to guide the training of the model. The experimental results on a public CETSA dataset demonstrate the effectiveness of the proposed approach.

A Thermo-Active Laccase Isoenzyme From Trametes trogii and Its Potential for Dye Decolorization at High Temperature.

A thermo-activation and thermostable laccase isoenzyme (Lac 37 II) produced by Trametes trogii S0301 at 37°C was purified to apparent homogeneity by anionic exchange chromatography and sephadex G-75 chromatography, with 12.3% of yeiled and a specific activity of 343.1 U mg-1. The molecular weight of the purified Lac 37 II was estimated to be approximately 56 kDa in 12% sodium dodecyl sulfate polyacrylamide gel electrophoresis (SDS-PAGE). The optimal pH and temperature for the protein was 2.7 and 60°C, respectively. The purified Lac 37 II showed higher resistance to all tested metal ions and organic solvents except for Fe2+ and Cd2+ at 37°C and the activity of the purified Lac 37 was significantly enhanced by Cu2+ at 50 mM. The K cat , K m , and K cat /K m of Lac 37 II were 2.977 s-1, 16.1 µM, and 184.9 s-1 µM-1, respecively, in the condition of pH 2.7 and 60°C using ABTS as a substrate. Peptide-mass fingerprinting analysis showed that the Lac 37 II matched to the gene-deduced sequences of lcc3 in T. trogii BAFC 463, other than Lcc1, Lcc 2, and Lcc 4. Compared with laccase prepared at 28°C, the onset of thermo-activation of Lac 37 II activity occurred at 30°C with an increase of 10%, and reached its maximum at the temperatures range of 40-60°C with an increase of about 40% of their original activity. Furthermore, Lac 37 II showed the efficient decolorization ability toward triphenylmethane dyes at 60°C, with decolorization rates of 100 and 99.1% for 25 mg L-1 malachite and crystal violet in 5 h, respectively, when hydroxybenzotriazole (HBT) was used as a mediator. In conclusion, it is the first time to report a thermo-activation laccase from a thermophilic T. trogii strain, which has a better enzyme property and higher decolorization ability among fungal laccases, and it also has a further application prospective in the field of biotechnology.

Lignin degradation potential and draft genome sequence of Trametes trogii S0301.

BACKGROUND: Trametes trogii is a member of the white-rot fungi family, which has a unique ability to break down recalcitrant lignin polymers to CO2 and water, and they have enormous potential to biodegrade a wide range of toxic environmental pollutants. Because of its industrial potential, the identification of lignin-degrading enzyme systems in Trametes is an important area of research. Development and utilization of industrial value genes are suffering due to deficiency knowledge of genome available for their manipulation. RESULTS: In the present study, Homokaryotic strains of T. trogii S0301 were screened and sequencing by PacBio Sequel II platform. The final draft genome is ~ 39.88 Mb, with a contig N50 size of 2.4 Mb, this was the first genome sequencing and assembly of T. trogii species. Further analyses predicted 14,508 protein-coding genes. Results showed that T. trogii S0301 contains 602 genes encoding CAZymes, include 211 glycoside hydrolase and 117 lignin-degrading family genes, nine laccases related genes. Small subunit ribosomal RNA gene (18S rRNA) sequencing confirms its phylogenetic position. Moreover, T. trogii S0301 has the largest number of cytochromes P450 (CYPs) superfamily genes compare to other fungi. All these results are consistent with enzymatic assays and transcriptome analysis results. We also analyzed other genome characteristics in the T. trogii S0301genome. CONCLUSION: Here, we present a nearly complete genome for T. trogii S0301, which will help elucidate the biosynthetic pathways of the lignin-degrading enzyme, advancing the discovery, characterization, and modification of novel enzymes from this genus. This genome sequence will provide a valuable reference for the investigation of lignin degradation in the Trametes genus.

A Multi-channel Deep Learning Approach for Segmentation of the Left Ventricular Endocardium from Cardiac Images.

Cardiac segmentation is the first most important step in assessing cardiac diseases. However, it still remains challenging owing to the complicated information of myocardium's boundary. In this work, we investigate approaches based on deep learning for fully automatic segmentation of the left ventricular (LV) endocardium using cardiac magnetic resonance (CMR) images. The deep convolutional neural network architectures, specifically, GoogleNet and U-Net, are modified and deployed to extract the features and then classify each pixel into either endocardium or background. Since adjacent frames for a given slice are imaged over a short time period across a cardiac cycle, the LV endocardium exhibit strong temporal correlation. To utilize the temporal information of heart motion to assist segmentation, we propose to construct multi-channel cardiac images by combining adjacent frames together with the current frame, which are used as the inputs for deep learning models. This allows the deep learning models to automatically learn spatial and temporal information. The performance of our constructed networks is evaluated by using the Dice metric to compare the segmented areas with the manually segmented ground truth. The experiments show that the multi-channel approaches converge more rapidly and achieve higher segmentation accuracy compared to the single channel approach.

Skin Lesion Analysis By Multi-Target Deep Neural Networks.

Automatic skin lesion analysis involves two critical steps: lesion segmentation and lesion classification. In this work, we propose a novel multi-target deep convolutional neural network (DCNN) to simultaneously tackle the problem of segmentation and classification. Based on U-Net and GoogleNet, a single model is constructed with three different targets of both lesion segmentation and two independent binary lesion classifications (i.e., melanoma detection and seborrheic keratosis identification), aiming to explore the differences and commonalities over different target models. We conduct experiments on dermoscopic images from the International Skin Imaging Collaboration (ISIC) 2017 Challenge. Results of our multi-target DCNN model demonstrates superiority over single model with one target only (such as U-net or GoogleNet), indicating its learning efficiency and potential for application in automatic skin lesion diagnosis. To the best of our knowledge, this work is the first demonstration for a single end-to-end deep neural network model that simultaneously handle both segmentation and classification in the field of skin lesion analysis.

Multi-dimensional proprio-proximus machine learning for assessment of myocardial infarction.

This work presents a novel analysis methodology that utilises high-resolution, multi-dimensional information to better classify regions of the left ventricle after myocardial infarction. Specifically, the focus is to determine degree of infarction in regions of the left ventricle based on information extracted from cardiac magnetic resonance imaging. Enhanced classification accuracy is achieved using three mechanisms: Firstly, a plurality of indices/features is used in the pattern classification process, rather than a single index/feature (hence the term "multi-dimensional). Secondly, the method incorporates not only the indices/features of the region in consideration, but also indices/features from the neighbouring regions (hence the term "proprio-proximus"). Thirdly, advanced machine learning techniques are used for both feature selection and pattern classification process to ameliorate the effect of class-imbalance existing in the data. Numerical results from multiple experiments on real data showed that using multiple features improved the ability to distinguish between infarcted and non-infarcted remote segments, and using neighbouring information improved classification performance. The proposed methodology is general and can be adapted for the analysis of biological functions of other human organs.

Cardiac Image Segmentation Using Memory Persistence Methodology.

This paper presents a novel computer-aided framework for cardiac image segmentation using a methodology based on memory persistence. The primary concept is to mimic the process of human cognition in the segmentation of time-varying images (i.e., 2D + time or 3D + time), by remembering and exploiting results of previously segmented frames, to aid in segmentation of the region of interest with poor or ambiguous boundaries. The framework involves an intelligent image segmentation process which incorporates an automatic contour initialization mechanism, and a segmentation refinement mechanism that iteratively improves the segmentation results. The proposed framework is general and can integrate most existing image segmentation algorithms in the literature. The experimental results show the benefits of the proposed framework achieving insensitivity to contour initialization, high automation and better segmentation accuracy as compared to the original algorithm and its standard temporal constraint version.

CardioXNet: Automated Detection for Cardiomegaly Based on Deep Learning.

In this paper, we present an automated procedure to determine the presence of cardiomegaly on chest X-ray image based on deep learning. The proposed algorithm CardioXNet uses deep learning methods U-NET and cardiothoracic ratio for diagnosis of cardiomegaly from chest X-rays. U-NET learns the segmentation task from the ground truth data. OpenCV is used to denoise and maintain the precision of region of interest once minor errors occur. Therefore, Cardiothoracic ratio (CTR) is calculated as a criterion to determine cardiomegaly from U-net segmentations. End-to-end Dense-Net neural network is used as baseline. This study has shown that the feasibility of combing deep learning segmentation and medical criterion to automatically recognize heart disease in medical images with high accuracy and agreement with the clinical results.

Computational Platform Based on Deep Learning for Segmenting Ventricular Endocardium in Long-axis Cardiac MR Imaging.

This paper presents an automated computational platform based on deep learning (DL) approach for left ventricular (LV) and right ventricular (RV) endocardium segmentation in long-axis cine cardiovascular magnetic resonance (CMR). The proposed method uses modified deep U-Net convolutional networks. We trained our model using 4800 images from 40 human subjects (20 healthy volunteers, 20 patients with various cardiac diseases) and validated the technique in 6000 images from 50 subjects (10 healthy volunteers, 40 patients). An average Dice metric of 0.929 ± 0.036 along with an average Jaccard index of 0.869 ± 0.059 were achieved for all the studied subjects. In addition, a high level of correlation and agreement with the ground truth contours for LV ejection fraction (R=0.975), LV fractional area change (R=0.959 to 0.971), and RV fractional area change (R=0.927) were observed. The proposed DL-based segmentation process took less than 3 seconds per subject (or < 30 milliseconds per image over 120 images for each subject). Therefore, our proposed framework offers a promising means to achieve fully automated and rapid segmentation for both LV and RV endocardium in long-axis cine CMR images using an appropriately trained deep convolutional neural network.

Automatic segmentation of left ventricle cavity from short-axis cardiac magnetic resonance images.

In this paper, a computational framework is proposed to perform a fully automatic segmentation of the left ventricle (LV) cavity from short-axis cardiac magnetic resonance (CMR) images. In the initial phase, the region of interest (ROI) is automatically identified on the first image frame of the CMR slices. This is done by partitioning the image into different regions using a standard fuzzy c-means (FCM) clustering algorithm where the LV region is identified according to its intensity, size and circularity in the image. Next, LV segmentation is performed within the identified ROI by using a novel clustering method that utilizes an objective functional with a dissimilarity measure that incorporates a circular shape function. This circular shape-constrained FCM algorithm is able to differentiate pixels with similar intensity but are located in different regions (e.g. LV cavity and non-LV cavity), thus improving the accuracy of the segmentation even in the presence of papillary muscles. In the final step, the segmented LV cavity is propagated to the adjacent image frame to act as the ROI. The segmentation and ROI propagation are then iteratively executed until the segmentation has been performed for the whole cardiac sequence. Experiment results using the LV Segmentation Challenge validation datasets show that our proposed framework can achieve an average perpendicular distance (APD) shift of 2.23 ± 0.50 mm and the Dice metric (DM) index of 0.89 ± 0.03, which is comparable to the existing cutting edge methods. The added advantage over state of the art is that our approach is fully automatic, does not need manual initialization and does not require a prior trained model.

Lipidomic Profiling of Lung Pleural Effusion Identifies Unique Metabotype for EGFR Mutants in Non-Small Cell Lung Cancer.

Cytology and histology forms the cornerstone for the diagnosis of non-small cell lung cancer (NSCLC) but obtaining sufficient tumour cells or tissue biopsies for these tests remains a challenge. We investigate the lipidome of lung pleural effusion (PE) for unique metabolic signatures to discriminate benign versus malignant PE and EGFR versus non-EGFR malignant subgroups to identify novel diagnostic markers that is independent of tumour cell availability. Using liquid chromatography mass spectrometry, we profiled the lipidomes of the PE of 30 benign and 41 malignant cases with or without EGFR mutation. Unsupervised principal component analysis revealed distinctive differences between the lipidomes of benign and malignant PE as well as between EGFR mutants and non-EGFR mutants. Docosapentaenoic acid and Docosahexaenoic acid gave superior sensitivity and specificity for detecting NSCLC when used singly. Additionally, several 20- and 22- carbon polyunsaturated fatty acids and phospholipid species were significantly elevated in the EGFR mutants compared to non-EGFR mutants. A 7-lipid panel showed great promise in the stratification of EGFR from non-EGFR malignant PE. Our data revealed novel lipid candidate markers in the non-cellular fraction of PE that holds potential to aid the diagnosis of benign, EGFR mutation positive and negative NSCLC.

A spatial shape constrained clustering method for mammographic mass segmentation.

A novel clustering method is proposed for mammographic mass segmentation on extracted regions of interest (ROIs) by using deterministic annealing incorporating circular shape function (DACF). The objective function reported in this study uses both intensity and spatial shape information, and the dominant dissimilarity measure is controlled by two weighting parameters. As a result, pixels having similar intensity information but located in different regions can be differentiated. Experimental results shows that, by using DACF, the mass segmentation results in digitized mammograms are improved with optimal mass boundaries, less number of noisy patches, and computational efficiency. An average probability of segmentation error of 7.18% for well-defined masses (or 8.06% for ill-defined masses) was obtained by using DACF on MiniMIAS database, with 5.86% (or 5.55%) and 6.14% (or 5.27%) improvements as compared to the standard DA and fuzzy c-means methods.

Vicinal support vector classifier using supervised kernel-based clustering.

OBJECTIVE: Support vector machines (SVMs) have drawn considerable attention due to their high generalisation ability and superior classification performance compared to other pattern recognition algorithms. However, the assumption that the learning data is identically generated from unknown probability distributions may limit the application of SVMs for real problems. In this paper, we propose a vicinal support vector classifier (VSVC) which is shown to be able to effectively handle practical applications where the learning data may originate from different probability distributions. METHODS: The proposed VSVC method utilises a set of new vicinal kernel functions which are constructed based on supervised clustering in the kernel-induced feature space. Our proposed approach comprises two steps. In the clustering step, a supervised kernel-based deterministic annealing (SKDA) clustering algorithm is employed to partition the training data into different soft vicinal areas of the feature space in order to construct the vicinal kernel functions. In the training step, the SVM technique is used to minimise the vicinal risk function under the constraints of the vicinal areas defined in the SKDA clustering step. RESULTS: Experimental results on both artificial and real medical datasets show our proposed VSVC achieves better classification accuracy and lower computational time compared to a standard SVM. For an artificial dataset constructed from non-separated data, the classification accuracy of VSVC is between 95.5% and 96.25% (using different cluster numbers) which compares favourably to the 94.5% achieved by SVM. The VSVC training time is between 8.75s and 17.83s (for 2-8 clusters), considerable less than the 65.0s required by SVM. On a real mammography dataset, the best classification accuracy of VSVC is 85.7% and thus clearly outperforms a standard SVM which obtains an accuracy of only 82.1%. A similar performance improvement is confirmed on two further real datasets, a breast cancer dataset (74.01% vs. 72.52%) and a heart dataset (84.77% vs. 83.81%), coupled with a reduction in terms of learning time (32.07s vs. 92.08s and 25.00s vs. 53.31s, respectively). Furthermore, the VSVC results in the number of support vectors being equal to the specified cluster number, and hence in a much sparser solution compared to a standard SVM. CONCLUSION: Incorporating a supervised clustering algorithm into the SVM technique leads to a sparse but effective solution, while making the proposed VSVC adaptive to different probability distributions of the training data.