Imbalanced datasets are prominent in real-world problems. In such problems, the data samples in one class are significantly higher than in the other classes, even though the other classes might be more important. The standard classification algorithms may classify all the data into the majority class, and this is a significant drawback of most standard learning algorithms, so imbalanced datasets need to be handled carefully. One of the traditional algorithms, twin support vector machines (TSVM), performed well on balanced data classification but poorly on imbalanced datasets classification. In order to improve the TSVM algorithm's classification ability for imbalanced datasets, recently, driven by the universum twin support vector machine (UTSVM), a reduced universum twin support vector machine for class imbalance learning (RUTSVM) was proposed. The dual problem and finding classifiers involve matrix inverse computation, which is one of RUTSVM's key drawbacks. In this paper, we improve the RUTSVM and propose an improved reduced universum twin support vector machine for class imbalance learning (IRUTSVM). We offer alternative Lagrangian functions to tackle the primal problems of RUTSVM in the suggested IRUTSVM approach by inserting one of the terms in the objective function into the constraints. As a result, we obtain new dual formulation for each optimization problem so that we need not compute inverse matrices neither in the training process nor in finding the classifiers. Moreover, the smaller size of the rectangular kernel matrices is used to reduce the computational time. Extensive testing is carried out on a variety of synthetic and real-world imbalanced datasets, and the findings show that the IRUTSVM algorithm outperforms the TSVM, UTSVM, and RUTSVM algorithms in terms of generalization performance.

• Klíčová slova
• Class-imbalanced, Rectangular kernel, Reduced universum twin support vector machine, Twin support vector machine, Universum, Universum twin support vector machine,
• MeSH
• algoritmy * MeSH
• support vector machine * MeSH
• Publikační typ
• časopisecké články MeSH

Laser-induced breakdown spectroscopy is often combined with a multivariate black box model-such as support vector machines (SVMs)-to obtain desirable quantitative or qualitative results. This approach carries obvious risks when practiced in high-stakes applications. Moreover, the lack of understanding of a black-box model limits the user's ability to fine-tune the model. Thus, here we present four approaches to interpret SVMs through investigating which features the models consider important in the classification task of 19 algal and cyanobacterial species. The four feature importance metrics are compared with popular approaches to feature selection for optimal SVM performance. We report that the distinct feature importance metrics yield complementary and often comparable information. In addition, we identify our SVM model's bias towards features with a large variance, even though these features exhibit a significant overlap between classes. We also show that the linear and radial basis kernel SVMs weight the same features to the same degree.

• Klíčová slova
• Classification, Feature importance, Interpretable machine learning, LIBS, SVM,
• MeSH
• lasery * MeSH
• spektrální analýza MeSH
• support vector machine * MeSH
• Publikační typ
• časopisecké články MeSH

In the realm of multi-class classification, the twin K-class support vector classification (Twin-KSVC) generates ternary outputs {-1,0,+1} by evaluating all training data in a "1-versus-1-versus-rest" structure. Recently, inspired by the least-squares version of Twin-KSVC and Twin-KSVC, a new multi-class classifier called improvements on least-squares twin multi-class classification support vector machine (ILSTKSVC) has been proposed. In this method, the concept of structural risk minimization is achieved by incorporating a regularization term in addition to the minimization of empirical risk. Twin-KSVC and its improvements have an influence on classification accuracy. Another aspect influencing classification accuracy is feature selection, which is a critical stage in machine learning, especially when working with high-dimensional datasets. However, most prior studies have not addressed this crucial aspect. In this study, motivated by ILSTKSVC and the cardinality-constrained optimization problem, we propose ℓp-norm least-squares twin multi-class support vector machine (PLSTKSVC) with 0

• Klíčová slova
• -norm, Cardinality-constrained optimization problem, Feature selection, Least-squares, Multi-class classification, Twin k-class support vector classification,
• MeSH
• metoda nejmenších čtverců MeSH
• strojové učení * MeSH
• support vector machine * MeSH
• Publikační typ
• časopisecké články MeSH

Non-coding RNAs (ncRNAs) are nucleotide sequences that are known to assume regulatory roles previously thought to be reserved for proteins. Their functions include the regulation of protein activity and localization and the organization of subcellular structures. Sequencing studies have now identified thousands of ncRNAs encoded within the prokaryotic and eukaryotic genomes, leading to advances in several fields including parasitology. ncRNAs play major roles in several aspects of vector-host-pathogen interactions. Arthropod vector ncRNAs are secreted through extracellular vesicles into vertebrate hosts to counteract host defense systems and ensure arthropod survival. Conversely, hosts can use specific ncRNAs as one of several strategies to overcome arthropod vector invasion. In addition, pathogens transmitted through vector saliva into vertebrate hosts also possess ncRNAs thought to contribute to their pathogenicity. Recent studies have addressed ncRNAs in vectors or vertebrate hosts, with relatively few studies investigating the role of ncRNAs derived from pathogens and their involvement in establishing infections, especially in the context of vector-borne diseases. This Review summarizes recent data focusing on pathogen-derived ncRNAs and their role in modulating the cellular responses that favor pathogen survival in the vertebrate host and the arthropod vector, as well as host ncRNAs that interact with vector-borne pathogens.

• Klíčová slova
• Host–pathogen interactions, Non-coding RNAs, Vector-borne infection,
• MeSH
• členovci - vektory MeSH
• eukaryotické buňky MeSH
• infekce přenášené vektorem * MeSH
• interakce hostitele a patogenu genetika   MeSH
• nekódující RNA * genetika   MeSH
• zvířata MeSH
• Check Tag
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• přehledy MeSH
• Názvy látek
• nekódující RNA * MeSH

Atrial fibrillation (AF) is a serious heart arrhythmia leading to a significant increase of the risk for occurrence of ischemic stroke. Clinically, the AF episode is recognized in an electrocardiogram. However, detection of asymptomatic AF, which requires a long-term monitoring, is more efficient when based on irregularity of beat-to-beat intervals estimated by the heart rate (HR) features. Automated classification of heartbeats into AF and non-AF by means of the Lagrangian Support Vector Machine has been proposed. The classifier input vector consisted of sixteen features, including four coefficients very sensitive to beat-to-beat heart changes, taken from the fetal heart rate analysis in perinatal medicine. Effectiveness of the proposed classifier has been verified on the MIT-BIH Atrial Fibrillation Database. Designing of the LSVM classifier using very large number of feature vectors requires extreme computational efforts. Therefore, an original approach has been proposed to determine a training set of the smallest possible size that still would guarantee a high quality of AF detection. It enables to obtain satisfactory results using only 1.39% of all heartbeats as the training data. Post-processing stage based on aggregation of classified heartbeats into AF episodes has been applied to provide more reliable information on patient risk. Results obtained during the testing phase showed the sensitivity of 98.94%, positive predictive value of 98.39%, and classification accuracy of 98.86%.

• Klíčová slova
• AF detection, HRV features, atrial fibrillation (AF), heart rate variability (HRV), support vector machine (SVM),
• MeSH
• algoritmy MeSH
• databáze faktografické MeSH
• diagnóza počítačová MeSH
• elektrokardiografie metody   MeSH
• fibrilace síní diagnóza   patofyziologie   MeSH
• lidé MeSH
• počítačové zpracování signálu MeSH
• srdeční frekvence fyziologie   MeSH
• support vector machine MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

• Klíčová slova
• arthropod, immunity, microbiome, pathogen, transcriptome, vector,
• MeSH
• členovci - vektory * MeSH
• infekce přenášené vektorem * MeSH
• interakce hostitele a patogenu MeSH
• Publikační typ
• Research Support, N.I.H., Extramural MeSH
• úvodní články MeSH
• úvodníky MeSH

We have developed a Potato virus X (PVX)-based vector system compatible with the GoldenBraid 2.0 (GB) cloning strategy to transiently express heterologous proteins or peptides in plants for biotechnological purposes. This vector system consists of three domestication vectors carrying three GB parts-the cauliflower mosaic virus (CaMV) 35S promoter with PVX upstream of the second subgenomic promoter of the PVX coat protein (PVX CP SGP), nopaline synthase (NOS) terminator with PVX downstream of the first PVX CP SGP and the gene of interest (GOI). The full-length PVX clone carrying the sequence encoding a green fluorescent protein (GFP) as GOI was incorporated into the binary GB vector in a one-step reaction of three GB parts using the four-nucleotide GB standard syntax. We investigated whether the obtained vector named GFP/pGBX enables systemic PVX infection and expression of GFP in Nicotiana benthamiana plants. We show that this GB-compatible vector system can be used for simple and efficient assembly of PVX-based expression constructs and that it meets the current need for interchange of standard biological parts used in different expression systems.

• Klíčová slova
• GoldenBraid, Nicotiana benthamiana, PVX vector, Potato virus X, transient expression,
• MeSH
• genetické vektory genetika   MeSH
• Potexvirus * genetika   MeSH
• rostliny MeSH
• tabák MeSH
• zelené fluorescenční proteiny genetika   metabolismus   MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• zelené fluorescenční proteiny MeSH

Vector-borne diseases (VBD) challenge our understanding of emerging diseases. Recently, arthropod vectors have been involved in emerging anaphylactic diseases. In particular, the immunoglobulin E (IgE) antibody response to the carbohydrate Galα1-3Galβ1-(3)4GlcNAc-R (α-gal) following a tick bite was associated with allergies to red meat, cetuximab, and gelatin. By contrast, an anti-α-gal IgM antibody response was shown to protect against mosquito-borne malaria. Herein, we highlight the interplay between the gut microbiota, vectors, transmitted pathogens, and the regulation of the immune response as a model to understand the protective or allergic effect of α-gal. Establishing the source of α-gal in arthropod vectors and the immune response to vector bites and transmitted pathogens will be essential for diagnosing, treating, and ultimately preventing these emerging anaphylactic and other vector-borne diseases.

• Klíčová slova
• alpha-gal, malaria, tick, vaccine, vector-borne diseases,
• MeSH
• alergie imunologie   MeSH
• členovci - vektory imunologie   MeSH
• imunoglobulin E imunologie   MeSH
• infekce přenášené vektorem * MeSH
• interakce hostitele a parazita imunologie   MeSH
• lidé MeSH
• proteiny členovců imunologie   MeSH
• Th2 buňky imunologie   MeSH
• zvířata MeSH
• Check Tag
• lidé MeSH
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• přehledy MeSH
• Názvy látek
• imunoglobulin E MeSH
• proteiny členovců MeSH

BACKGROUND: Leishmania infantum is the most widespread etiological agent of visceral leishmaniasis (VL) in the world, with significant mortality rates in human cases. In Latin America, this parasite is primarily transmitted by Lutzomyia longipalpis, but the role of Lutzomyia migonei as a potential vector for this protozoan has been discussed. Laboratory and field investigations have contributed to this hypothesis; however, proof of the vector competence of L. migonei has not yet been provided. In this study, we evaluate for the first time the susceptibility of L. migonei to L. infantum. METHODS: Females of laboratory-reared L. migonei were fed through a chick-skin membrane on rabbit blood containing L. infantum promastigotes, dissected at 1, 5 and 8 days post-infection (PI) and checked microscopically for the presence, intensity and localisation of Leishmania infections. In addition, morphometric analysis of L. infantum promastigotes was performed. RESULTS: High infection rates of both L. infantum strains tested were observed in L. migonei, with colonisation of the stomodeal valve already on day 5 PI. At the late-stage infection, most L. migonei females had their cardia and stomodeal valve colonised by high numbers of parasites, and no significant differences were found compared to the development in L. longipalpis. Metacyclic forms were found in all parasite-vector combinations since day 5 PI. CONCLUSIONS: We propose that Lutzomyia migonei belongs to sand fly species permissive to various Leishmania spp. Here we demonstrate that L. migonei is highly susceptible to the development of L. infantum. This, together with its known anthropophily, abundance in VL foci and natural infection by L. infantum, constitute important evidence that L. migonei is another vector of this parasite in Latin America.

• Klíčová slova
• Leishmania infantum, Lutzomyia migonei, Vector competence,
• MeSH
• hmyz - vektory * MeSH
• Leishmania infantum cytologie   izolace a purifikace   MeSH
• mikroskopie MeSH
• Psychodidae růst a vývoj   parazitologie   MeSH
• zvířata MeSH
• Check Tag
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

A method is described for characterizing the spatial directions of vectors with the aid of the angle alpha, characterizing the direction of the vector's projection upon the frontal plane, and angle beta, indicating the deflection of the spatial vector from the frontal plane. Angle alpha is expressed in the mode used with the conventional ECG system [from 0 degrees to +/- 180 degrees], and angle beta from 0 degrees to +/- 90 degrees. Calculations are made with the aid of algebraic formulae, and the results are tabulated. To facilitate the calculations of the magnitudes and directions of vectors in the space with respect to the orthogonal leads, and for better illustration, special schemes are presented.

• MeSH
• elektrokardiografie metody   MeSH
• lidé MeSH
• matematika MeSH
• vektorkardiografie metody   MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH