Plants interact with root microbes via chemical signaling, which modulates competence or symbiosis. Although several volatile organic compounds (VOCs) from fungi may affect plant growth and ...development, the signal transduction pathways mediating VOC sensing are not fully understood. 6‐pentyl‐2H‐pyran‐2‐one (6‐PP) is a major VOC biosynthesized by Trichoderma spp. which is probably involved in plant–fungus cross‐kingdom signaling. Using microscopy and confocal imaging, the effects of 6‐PP on root morphogenesis were found to be correlated with DR5:GFP, DR5:VENUS, H2B::GFP, PIN1::PIN1::GFP, PIN2::PIN2::GFP, PIN3::PIN3::GFP and PIN7::PIN7::GFP gene expression. A genetic screen for primary root growth resistance to 6‐PP in wild‐type seedlings and auxin‐ and ethylene‐related mutants allowed identification of genes controlling root architectural responses to this metabolite. Trichoderma atroviride produced 6‐PP, which promoted plant growth and regulated root architecture, inhibiting primary root growth and inducing lateral root formation. 6‐PP modulated expression of PIN auxin‐transport proteins in a specific and dose‐dependent manner in primary roots. TIR1, AFB2 and AFB3 auxin receptors and ARF7 and ARF19 transcription factors influenced the lateral root response to 6‐PP, whereas EIN2 modulated 6‐PP sensing in primary roots. These results indicate that root responses to 6‐PP involve components of auxin transport and signaling and the ethylene‐response modulator EIN2.
The Synthetic Minority Oversampling Technique (SMOTE) preprocessing algorithm is considered "de facto" standard in the framework of learning from imbalanced data. This is due to its simplicity in the ...design of the procedure, as well as its robustness when applied to different type of problems. Since its publication in 2002, SMOTE has proven successful in a variety of applications from several different domains. SMOTE has also inspired several approaches to counter the issue of class imbalance, and has also significantly contributed to new supervised learning paradigms, including multilabel classification, incremental learning, semi-supervised learning, multi-instance learning, among others. It is standard benchmark for learning from imbalanced data. It is also featured in a number of different software packages - from open source to commercial. In this paper, marking the fifteen year anniversary of SMOTE, we reflect on the SMOTE journey, discuss the current state of affairs with SMOTE, its applications, and also identify the next set of challenges to extend SMOTE for Big Data problems.
•Autoencoders are a growing family of tools for nonlinear feature fusion.•A taxonomy of these methods is proposed, detailing each one of them.•Comparisons to other feature fusion techniques and ...applications are studied.•Guidelines on autoencoder design and example results are provided.•Available software for building autoencoders is summarized.
Many of the existing machine learning algorithms, both supervised and unsupervised, depend on the quality of the input characteristics to generate a good model. The amount of these variables is also important, since performance tends to decline as the input dimensionality increases, hence the interest in using feature fusion techniques, able to produce feature sets that are more compact and higher level. A plethora of procedures to fuse original variables for producing new ones has been developed in the past decades. The most basic ones use linear combinations of the original variables, such as PCA (Principal Component Analysis) and LDA (Linear Discriminant Analysis), while others find manifold embeddings of lower dimensionality based on non-linear combinations, such as Isomap or LLE (Linear Locally Embedding) techniques.
More recently, autoencoders (AEs) have emerged as an alternative to manifold learning for conducting nonlinear feature fusion. Dozens of AE models have been proposed lately, each with its own specific traits. Although many of them can be used to generate reduced feature sets through the fusion of the original ones, there also AEs designed with other applications in mind.
The goal of this paper is to provide the reader with a broad view of what an AE is, how they are used for feature fusion, a taxonomy gathering a broad range of models, and how they relate to other classical techniques. In addition, a set of didactic guidelines on how to choose the proper AE for a given task is supplied, together with a discussion of the software tools available. Finally, two case studies illustrate the usage of AEs with datasets of handwritten digits and breast cancer.
Summary
Phosphate (Pi) is a critical macronutrient for the biochemical and molecular functions of cells. Under phosphate limitation, plants manifest adaptative strategies to increase phosphate ...scavenging. However, how low phosphate sensing links to the transcriptional machinery remains unknown.
The role of the MEDIATOR (MED) transcriptional co‐activator, through its MED16 subunit in Arabidopsis root system architecture remodeling in response to phosphate limitation was assessed. Its critical function acting over the SENSITIVE TO PROTON RHIZOTOXICITY1 (STOP1)‐ALUMINUM‐ACTIVATED MALATE TRANSPORT1 (ALMT1) signaling module was tested through a combination of genetic, biochemical, and genome‐wide transcriptomic approaches.
Root system configuration in response to phosphate scarcity involved MED16 functioning, which modulates the expression of a large set of low‐phosphate‐induced genes that respond to local and systemic signals in the Arabidopsis root tip, including those directly activated by STOP1. Biomolecular fluorescence complementation analysis suggests that MED16 is required for the transcriptional activation of STOP1 targets, including the membrane permease ALMT1, to increase malate exudation in response to low phosphate.
Our results unveil the function of a critical transcriptional component, MED16, in the root adaptive responses to a scarce plant macronutrient, which helps understanding how plant cells orchestrate root morphogenesis to gene expression with the STOP1‐ALMT1 module.
Background
The relationship between obesity and risk of complications described during the 2009 influenza pandemic is poorly defined for seasonal influenza and other viral causes of influenza‐like ...illness (ILI).
Methods
An observational cohort of hospitalized and outpatient participants with ILI was conducted in six hospitals in Mexico. Nasopharyngeal swabs were tested for influenza and other common respiratory pathogens.
Results
A total of 4778 participants were enrolled in this study and had complete data. A total of 2053 (43.0%) had severe ILI. Seven hundred and seventy‐eight (16.3%) were positive for influenza, 2636 (55.2%) were positive for other viral respiratory pathogens, and 1364 (28.5%) had no respiratory virus isolated. Adults with influenza were more likely to be hospitalized if they were underweight (OR: 5.20), obese (OR: 3.18), or morbidly obese (OR: 18.40) compared to normal‐weight adults. Obese adults with H1N1 had a sixfold increase in odds of hospitalization over H3N2 and B (obese OR: 8.96 vs 1.35, morbidly obese OR: 35.13 vs 5.58, respectively) compared to normal‐weight adults. In adults with coronavirus, metapneumovirus, parainfluenza, and rhinovirus, participants that were underweight (OR: 4.07) and morbidly obese (OR: 2.78) were more likely to be hospitalized as compared to normal‐weight adults. All‐cause influenza‐like illness had a similar but less pronounced association between underweight or morbidly obesity and hospitalization.
Conclusions
There is an increased risk of being hospitalized in adult participants that are underweight or morbidly obese, regardless of their viral pathogen status. Having influenza, however, significantly increases the odds of hospitalization in those who are underweight or morbidly obese.
Plants host a diverse microbiome and differentially react to the fungal species living as endophytes or around their roots through emission of volatiles. Here, using divided Petri plates for ...Arabidopsis‐T. atroviride co‐cultivation, we show that fungal volatiles increase endogenous sugar levels in shoots, roots and root exudates, which improve Arabidopsis root growth and branching and strengthen the symbiosis. Tissue‐specific expression of three sucrose phosphate synthase‐encoding genes (AtSPS1F, AtSPS2F and AtSPS3F), and AtSUC2 and SWEET transporters revealed that the gene expression signatures differ from those of the fungal pathogens Fusarium oxysporum and Alternaria alternata and that AtSUC2 is largely repressed either by increasing carbon availability or by perception of the fungal volatile 6‐pentyl‐2H‐pyran‐2‐one. Our data point to Trichoderma volatiles as chemical signatures for sugar biosynthesis and exudation and unveil specific modulation of a critical, long‐distance sucrose transporter in the plant.
T. atroviride volatiles trigger Arabidopsis biomass production and root branching by modulating genes encoding proteins for sugar biosynthesis and transport. A single volatile, namely 6‐pentyl‐2H‐pyran‐2‐one directly influences the major sucrose transporter AtSUC2, which may be critical for the development of the symbiosis.
The interest in nonparametric statistical analysis has grown recently in the field of computational intelligence. In many experimental studies, the lack of the required properties for a proper ...application of parametric procedures–independence, normality, and homoscedasticity–yields to nonparametric ones the task of performing a rigorous comparison among algorithms.
In this paper, we will discuss the basics and give a survey of a complete set of nonparametric procedures developed to perform both pairwise and multiple comparisons, for multi-problem analysis. The test problems of the CEC’2005 special session on real parameter optimization will help to illustrate the use of the tests throughout this tutorial, analyzing the results of a set of well-known evolutionary and swarm intelligence algorithms. This tutorial is concluded with a compilation of considerations and recommendations, which will guide practitioners when using these tests to contrast their experimental results.
Experimental analysis of the performance of a proposed method is a crucial and necessary task in an investigation. In this paper, we focus on the use of nonparametric statistical inference for ...analyzing the results obtained in an experiment design in the field of computational intelligence. We present a case study which involves a set of techniques in classification tasks and we study a set of nonparametric procedures useful to analyze the behavior of a method with respect to a set of algorithms, such as the framework in which a new proposal is developed.
Particularly, we discuss some basic and advanced nonparametric approaches which improve the results offered by the Friedman test in some circumstances. A set of post hoc procedures for multiple comparisons is presented together with the computation of adjusted
p-values. We also perform an experimental analysis for comparing their power, with the objective of detecting the advantages and disadvantages of the statistical tests described. We found that some aspects such as the number of algorithms, number of data sets and differences in performance offered by the control method are very influential in the statistical tests studied. Our final goal is to offer a complete guideline for the use of nonparametric statistical procedures for performing multiple comparisons in experimental studies.
Classification problems involving multiple classes can be addressed in different ways. One of the most popular techniques consists in dividing the original data set into two-class subsets, learning a ...different binary model for each new subset. These techniques are known as binarization strategies.
In this work, we are interested in ensemble methods by binarization techniques; in particular, we focus on the well-known one-vs-one and one-vs-all decomposition strategies, paying special attention to the final step of the ensembles, the combination of the outputs of the binary classifiers. Our aim is to develop an empirical analysis of different aggregations to combine these outputs. To do so, we develop a double study: first, we use different base classifiers in order to observe the suitability and potential of each combination within each classifier. Then, we compare the performance of these ensemble techniques with the classifiers' themselves. Hence, we also analyse the improvement with respect to the classifiers that handle multiple classes inherently.
We carry out the experimental study with several well-known algorithms of the literature such as Support Vector Machines, Decision Trees, Instance Based Learning or Rule Based Systems. We will show, supported by several statistical analyses, the goodness of the binarization techniques with respect to the base classifiers and finally we will point out the most robust techniques within this framework.
► One-vs-one and one-vs-all are ensembles for multi-class problems. ► The confidence estimates and their aggregation are key factors of these ensembles. ► Aggregations based on voting and estimation of probabilities are the most robust. ► One-vs-one is more robust, one-vs-all has received less attention. ► Binarization is beneficial even when it is not necessary.