Tannins represent a heterogeneous group of high-molecular-weight polyphenols that are ubiquitous among plant families, especially in cereals, as well as in many fruits and vegetables. Hydrolysable and condensed tannins, in addition to phlorotannins from marine algae, are the main classes of these bioactive compounds. Despite their low bioavailability, tannins have many beneficial pharmacological effects, such as anti-inflammatory, antioxidant, antidiabetic, anticancer, and cardioprotective effects. Microbiota-mediated hydrolysis of tannins produces highly bioaccessible metabolites, which have been extensively studied and account for most of the health effects attributed to tannins. This review article summarises the effect of the human microbiota on the metabolism of different tannin groups and the expected health benefits that may be induced by such mutual interactions. Microbial metabolism of tannins yields highly bioaccessible microbial metabolites that account for most of the systemic effects of tannins. This article also uses explainable artificial intelligence to define the molecular signatures of gut-biotransformed tannin metabolites that are correlated with chemical and biological activity. An understanding of microbiota–tannin interactions, tannin metabolism-related phenotypes (metabotypes) and chemical tannin-metabolites motifs is of great importance for harnessing the biological effects of tannins for drug discovery and other health benefits.

The traditional way to address the problem of sentiment classification is based on machine learning techniques; however, these models are not able to grasp all the richness of the text that comes from different social media, personal web pages, blogs, etc., ignoring the semantic of the text. Knowledge graphs give a way to extract structured knowledge from images and texts in order to facilitate their semantic analysis. This work proposes a new hybrid approach for Sentiment Analysis based on Knowledge Graphs and Deep Learning techniques to identify the sentiment polarity (positive or negative) in short documents, such as posts on Twitter. In this proposal, tweets are represented as graphs; then, graph similarity metrics and a Deep Learning classification algorithm are applied to produce sentiment predictions. This approach facilitates the traceability and interpretability of the classification results, thanks to the integration of the Local Interpretable Model-agnostic Explanations (LIME) model at the end of the pipeline. LIME allows raising trust in predictive models, since the model is not a black box anymore. Uncovering the black box allows understanding and interpreting how the network could distinguish between sentiment polarities. Each phase of the proposed approach conformed by pre-processing, graph construction, dimensionality reduction, graph similarity, sentiment prediction, and interpretability steps is described. The proposal is compared with character n-gram embeddings-based Deep Learning models to perform Sentiment Analysis. Results show that the proposal is able to outperforms classical n-gram models, with a recall up to 89% and F1-score of 88%.

Flavobacteriaceae spp. are key players in global biogeochemical cycling and are known for their versatile carbohydrate and peptide catabolism. However, it is currently unknown whether secondary metabolism traits underlie their broad range of occurrence across the earth’s biomes. We examined 2,680 genomes to unveil an unprecedented phylogenetic signal dictating natural product biosynthesis diversification within the Flavobacteriaceae family. The distribution of secondary metabolite biosynthetic gene clusters (BGCs) across genomes usually follows macroevolutionary, genus-specific patterns. Noticeably, 88.6% of the observed BGCs were inferred to lead to the biosynthesis of likely novel natural products. We found an unanticipated, large diversity of taxon-specific BGCs encoding carotenoid and flexirubin pigments, the vast majority of which awaiting formal description. In particular, Aquimarina and Kordia spp. possessed large genomes, versatile catabolic traits, and a repertoire of BGCs possibly encoding drug-inspiring polyketides, non-ribosomal peptides, or post-translationally modified peptides. Using a machine learning approach (feature selection), we reveal that marine and non-marine Flavobacteriaceae genomes are differentially enriched in CAZymes and peptidases with distinct functionalities and molecular targets. IMPORTANCE: This is the most comprehensive study performed thus far on the biosynthetic potential within the Flavobacteriaceae family. Our findings reveal intertwined taxonomic and natural product biosynthesis diversification within the family. We posit that the carbohydrate, peptide, and secondary metabolism triad synergistically shaped the evolution of this keystone bacterial taxon, acting as major forces underpinning the broad host range and opportunistic-to-pathogenic behavior encompassed by species in the family. This study further breaks new ground for future research on select Flavobacteriaceae spp. as reservoirs of novel drug leads.

Objective : Early detection of sleep arousal in polysomnographic (PSG) signals is crucial for monitoring or diagnosing sleep disorders and reducing the risk of further complications, including heart disease and blood pressure fluctuations. Approach : In this paper, we present a new automatic detector of non-apnea arousal regions in multichannel PSG recordings. This detector cascades four different modules: a second-order scattering transform (ST) with Morlet wavelets; depthwise-separable convolutional layers; bidirectional long short-term memory (BiLSTM) layers; and dense layers. While the first two are shared across all channels, the latter two operate in a multichannel formulation. Following a deep learning paradigm, the whole architecture is trained in an end-to-end fashion in order to optimize two objectives: the detection of arousal onset and offset, and the classification of the type of arousal. Main results and Significance : The novelty of the approach is three-fold: it is the first use of a hybrid ST-BiLSTM network with biomedical signals; it captures frequency information lower (0.1 Hz) than the detection sampling rate (0.5 Hz); and it requires no explicit mechanism to overcome class imbalance in the data. In the follow-up phase of the 2018 PhysioNet/CinC Challenge the proposed architecture achieved a state-of-the-art area under the precision-recall curve (AUPRC) of 0.50 on the hidden test data, tied for the second-highest official result overall.

Fetal heart rate monitoring plays an essential role in helping to decrease the perinatal mortality rate associated with abnormalities in the cardiovascular system of the fetus. In this sense, a new approach to detect fetal QRS (fQRS) complexes from abdominal maternal ECG signals is proposed in this paper. First, signals were segmented into contiguous frames of 250 ms duration and then labeled in four classes. Principal component analysis was applied on Haar-Wavelet transform for dimensionality reduction and feature extraction, and interquartile ranges and sampling without replacement were employed to deal with outliers and imbalanced class problems, respectively. K-nearest neighborhood (KNN), support vector machine (SVM) and Bayesian network (BN) were trained and tested on the ECG signals of four electrodes of the PhysioNet/CinC challenge 2013 dataset, using 10-fold stratified cross-validation. Results show that KNN and SVM got better average accuracies over BN, that reach to 89.59% and 89.19%, respectively. Although KNN yielded better results, SVM was less time-consuming in prediction. In addition, the fourth electrode signals are less noisy and contain more representative data that helps SVM reaches an accuracy about 80% for fQRS estimation.

This paper demonstrates how hidden Markov model (HMM) approach is used potentially as a tool for predicting the next concepts visited by students in an adaptive and intelligent Web-based educational system (AIWBES) for teaching English as Foreign Language (EFL). This tool helps teachers to provide their students with appropriate assistance during the learning process in a timely manner. The prediction process is achieved by following three phases, Initialization phase, adjustment phase and prediction phase. The experiment results are encouraging and serve to show the promise of HMM in AIWBESs and they show accuracy in the next action prediction reaching up to 92%.