TERL: classification of transposable elements by convolutional neural networks.

Transposable elements (TEs) are the most represented sequences occurring in eukaryotic genomes. Few methods provide the classification of these sequences into deeper levels, such as superfamily level, which could provide useful and detailed information about these sequences. Most methods that classify TE sequences use handcrafted features such as k-mers and homology-based search, which could be inefficient for classifying non-homologous sequences. Here we propose an approach, called transposable elements pepresentation learner (TERL), that preprocesses and transforms one-dimensional sequences into two-dimensional space data (i.e., image-like data of the sequences) and apply it to deep convolutional neural networks. This classification method tries to learn the best representation of the input data to classify it correctly. We have conducted six experiments to test the performance of TERL against other methods. Our approach obtained macro mean accuracies and F1-score of 96.4% and 85.8% for superfamilies and 95.7% and 91.5% for the order sequences from RepBase, respectively. We have also obtained macro mean accuracies and F1-score of 95.0% and 70.6% for sequences from seven databases into superfamily level and 89.3% and 73.9% for the order level, respectively. We surpassed accuracy, recall and specificity obtained by other methods on the experiment with the classification of order level sequences from seven databases and surpassed by far the time elapsed of any other method for all experiments. Therefore, TERL can learn how to predict any hierarchical level of the TEs classification system and is about 20 times and three orders of magnitude faster than TEclass and PASTEC, respectively https://github.com/muriloHoracio/TERL. Contact:murilocruz@alunos.utfpr.edu.br.

Aspirin-Triggered Resolvin D1 (AT-RvD1) Protects Mouse Skin against UVB-Induced Inflammation and Oxidative Stress.

Intense exposure to UVB radiation incites excessive production of reactive oxygen species (ROS) and inflammation. The resolution of inflammation is an active process orchestrated by a family of lipid molecules that includes AT-RvD1, a specialized proresolving lipid mediator (SPM). AT-RvD1 is derived from omega-3, which presents anti-inflammatory activity and reduces oxidative stress markers. The present work aims to investigate the protective effect of AT-RvD1 on UVB-induced inflammation and oxidative stress in hairless mice. Animals were first treated with 30, 100, and 300 pg/animal AT-RvD1 (i.v.) and then exposed to UVB (4.14 J/cm2). The results showed that 300 pg/animal of AT-RvD1 could restrict skin edema, neutrophil and mast cell infiltration, COX-2 mRNA expression, cytokine release, and MMP-9 activity and restore skin antioxidant capacity as per FRAP and ABTS assays and control O2•- production, lipoperoxidation, epidermal thickening, and sunburn cells development. AT-RvD1 could reverse the UVB-induced downregulation of Nrf2 and its downstream targets GSH, catalase, and NOQ-1. Our results suggest that by upregulating the Nrf2 pathway, AT-RvD1 promotes the expression of ARE genes, restoring the skin's natural antioxidant defense against UVB exposition to avoid oxidative stress, inflammation, and tissue damage.

Rosmarinus officinalis extract-loaded emulgel prevents UVB irradiation damage to the skin.

UVB-irradiation increases the risk of various skin disorders, therefore leading to inflammation and oxidative stress. In this sense, antioxidant-rich herbs such as Rosmarinus officinalis may be useful in minimizing the damage promoted by reactive oxygen species. In this work, we report the efficacy of a R. officinalis hydroethanolic extract (ROe)-loaded emulgel in preventing UVB-related skin damage. Total phenols were determined using Folin-Ciocalteu assay, and the main phytocomponents in the extract were identified by UHPLC-HRMS. Moreover, in vitro sun protection factor (SPF) value of ROe was also assessed, and we investigated the in vivo protective effect of an emulgel containing ROe against UVB-induced damage in an animal model. The ROe exhibited commercially viable SPF activity (7.56 ± 0.16) and remarkable polyphenolic content (24.15 ± 0.11 mg (Eq.GA)/g). HPLC-MS and UHPLC-HRMS results showcased that the main compounds in ROe were: rosmarinic acid, carnosic acid and carnosol. The evaluation of the in vitro antioxidant activity demonstrated a dose-dependent effect of ROe against several radicals and the capacity to reduce iron. Therefore, we demonstrated that topical application of the formulation containing ROe inhibited edema formation, myeloperoxidase activity, GSH depletion and maintained ferric reducing (FRAP) and ABTS scavenging abilities of the skin after UVB exposure.

Pattern recognition analysis on long noncoding RNAs: a tool for prediction in plants.

MOTIVATION: Long noncoding RNAs (lncRNAs) correspond to a eukaryotic noncoding RNA class that gained great attention in the past years as a higher layer of regulation for gene expression in cells. There is, however, a lack of specific computational approaches to reliably predict lncRNA in plants, which contrast the variety of prediction tools available for mammalian lncRNAs. This distinction is not that obvious, given that biological features and mechanisms generating lncRNAs in the cell are likely different between animals and plants. Considering this, we present a machine learning analysis and a classifier approach called RNAplonc (https://github.com/TatianneNegri/RNAplonc/) to identify lncRNAs in plants. RESULTS: Our feature selection analysis considered 5468 features, and it used only 16 features to robustly identify lncRNA with the REPTree algorithm. That was the base to create the model and train it with lncRNA and mRNA data from five plant species (thale cress, cucumber, soybean, poplar and Asian rice). After an extensive comparison with other tools largely used in plants (CPC, CPC2, CPAT and PLncPRO), we found that RNAplonc produced more reliable lncRNA predictions from plant transcripts with 87.5% of the best result in eight tests in eight species from the GreeNC database and four independent studies in monocotyledonous (Brachypodium) and eudicotyledonous (Populus and Gossypium) species.

Protection against UVB deleterious skin effects in a mouse model: effect of a topical emulsion containing Cordia verbenacea extract.

Cordia verbenacea DC (Boraginaceae) is a flowering shrub found along the Brazilian Atlantic Forest, Brazilian coast, and low areas of the Amazon. The crude extract of its leaves is widely used in Brazilian folk medicine as an anti-inflammatory, both topically and orally. The aim of this study is to evaluate the activity of C. verbenacea ethanolic leaves extract (CVE) against UVB-triggered cutaneous inflammation and oxidative damage in hairless mice. CVE treatment recovered cutaneous antioxidant capacity demonstrated by scavenging ABTS+ free radical and iron-reducing antioxidant potential evaluated by FRAP. CVE also controlled the following UV-triggered events in the skin: reduced glutathione (GSH) depletion, catalase activity decrease, and superoxide anion (O⋅-) build-up. Furthermore, mice treated with CVE exhibited less inflammation, shown by the reduction in COX-2 expression, TNF-α, IL-1ß, IL-6, edema, and neutrophil infiltration. CVE also regulated epidermal thickening and sunburn cells, reduced dermal mast cells, and preserved collagen integrity. The best results were obtained using 5% CVE-added emulsion. The present data demonstrate that topical administration of CVE presents photochemoprotective activity in a mouse model of UVB inflammation and oxidative stress. Because of the intricate network linking inflammation, oxidative stress, and skin cancer, these results also indicate the importance of further studies elucidating a possible role of C. verbenacea in the prevention of UVB-induced skin cancer and evaluating a potential synergy between CVE and sunscreens in topical products against UVB damaging effects to the skin.

Topical Administration of 15-Deoxy-Δ 12,14-Prostaglandin J2 Using a Nonionic Cream: Effect on UVB-Induced Skin Oxidative, Inflammatory, and Histopathological Modifications in Mice.

UVB radiation is certainly one of the most important environmental threats to which we are subjected to. This fact highlights the crucial protective role of the skin. However, the skin itself may not be capable of protecting against UVB depending on irradiation intensity and time of exposition. Sun blockers are used to protect our skin, but they fail to fully protect it against oxidative and inflammatory injuries initiated by UVB. To solve this issue, topical administration of active molecules is an option. 15-Deoxy-Δ 12,14-prostaglandin J2 (15d-PGJ2) is an arachidonic acid-derived lipid with proresolution and anti-inflammatory actions. However, as far as we are aware, there is no evidence of its therapeutic use in a topical formulation to treat the deleterious events initiated by UVB, which was the aim of the present study. We used a nonionic cream to vehiculate 15d-PGJ2 (30, 90, and 300 ng/mouse) (TFcPGJ2) in the skin of hairless mice. UVB increased skin edema, myeloperoxidase activity, metalloproteinase-9 activity, lipid peroxidation, superoxide anion production, gp91phox and COX-2 mRNA expression, cytokine production, sunburn and mast cells, thickening of the epidermis, and collagen degradation. UVB also diminished skin ability to reduce iron and scavenge free radicals, reduced glutathione (GSH), sulfhydryl proteins, and catalase activity. TFcPGJ2 inhibited all these pathological alterations in the skin caused by UVB. No activity was observed with the unloaded topical formulation. The protective outcome of TFcPGJ2 indicates it is a promising therapeutic approach against cutaneous inflammatory and oxidative pathological alterations.

The Lipoxin Receptor/FPR2 Agonist BML-111 Protects Mouse Skin Against Ultraviolet B Radiation.

Excessive exposure to UV, especially UVB, is the most important risk factor for skin cancer and premature skin aging. The identification of the specialized pro-resolving lipid mediators (SPMs) challenged the preexisting paradigm of how inflammation ends. Rather than a passive process, the resolution of inflammation relies on the active production of SPMs, such as Lipoxins (Lx), Maresins, protectins, and Resolvins. LXA4 is an SPM that exerts its action through ALX/FPR2 receptor. Stable ALX/FPR2 agonists are required because SPMs can be quickly metabolized within tissues near the site of formation. BML-111 is a commercially available synthetic ALX/FPR2 receptor agonist with analgesic, antioxidant, and anti-inflammatory properties. Based on that, we aimed to determine the effect of BML-111 in a model of UVB-induced skin inflammation in hairless mice. We demonstrated that BML-111 ameliorates the signs of UVB-induced skin inflammation by reducing neutrophil recruitment and mast cell activation. Reduction of these cells by BML-111 led to lower number of sunburn cells formation, decrease in epidermal thickness, collagen degradation, cytokine production (TNF-α, IL-1ß, IL-6, TGF, and IL-10), and oxidative stress (observed by an increase in total antioxidant capacity and Nrf2 signaling pathway), indicating that BML-111 might be a promising drug to treat skin disorders.

Assessment of clustering techniques to support the analyses of soybean seed vigor.

Soy is the main product of Brazilian agriculture and the fourth most cultivated bean globally. Since soy cultivation tends to increase and due to this large market, the guarantee of product quality is an indispensable factor for enterprises to stay competitive. Industries perform vigor tests to acquire information and evaluate the quality of soy planting. The tetrazolium test, for example, provides information about moisture damage, bedbugs, or mechanical damage. However, the verification of the damage reason and its severity are done by an analyst, one by one. Since this is massive and exhausting work, it is susceptible to mistakes. Proposals involving different supervised learning approaches, including active learning strategies, have already been used, and have brought significant results. Therefore, this paper analyzes the performance of non-supervised techniques for classifying soybeans. An extensive experimental evaluation was performed, considering (9) different clustering algorithms (partitional, hierarchical, and density-based) applied to 5 image datasets of soybean seeds submitted to the tetrazolium test, including different damages and/or their levels. To describe those images, we considered 18 extractors of traditional features. We also considered four metrics (accuracy, FOWLKES, DAVIES, and CALINSKI) and two-dimensionality reduction techniques (principal component analysis and t-distributed stochastic neighbor embedding) for validation. Results show that this paper presents essential contributions since it makes it possible to identify descriptors and clustering algorithms that shall be used as preprocessing in other learning processes, accelerating and improving the classification process of key agricultural problems.

Classification of Skin Lesion through Active Learning Strategies.

BACKGROUND AND OBJECTIVE: According to the National Cancer Institute, among all malignant tumors, non-melanoma skin cancer, and melanoma are the most frequent in Brazil. Despite having a lower incidence, the melanoma type has accelerated growth and greater lethality. Several studies have been performed in recent years in the computer vision area to assist in the early diagnosis of skin cancer. Despite being widely used and presenting good results, deep learning approaches require a large amount of annotated data and considerable computational cost for training the model. Therefore, the present work explores active learning approaches to select a small set of more informative data for training the classifier. For that, different selection criteria are considered to obtain more effective and efficient classifiers for skin lesions. METHODS: We perform an extensive experimental evaluation considering three datasets and different learning strategies and scenarios for validation. In addition to data augmentation, we evaluated two segmentation strategies considering the U-net CNN model and the Fully Convolutional Networks (FCN) with a manual expert review. We also analyzed the best (handcrafted and deep) features that describe each skin lesion and the most suitable classifiers and combinations (extractor-classifier) for this context. The active learning approach evaluated different criteria based on uncertainty, diversity, and representativeness to select the most informative samples. The strategies used were Decreasing Boundary Edges, Entropy, Least Confidence, Margin Sampling, Minimum-Spanning Tree Boundary Edges, and Root-Distance based Sampling. RESULTS: It can be observed that the segmentation with FCN and manual correction by the specialist, the Border-Interior Classification (BIC) extractor, and the Random Forest (RF) classifier showed a better performance. Regarding the active learning approach, the Margin Sampling strategy presented the best classification accuracies (about 93%) with only 35% of the training set compared to the traditional learning approach (which requires the entire set). CONCLUSIONS: According to the results, it is possible to observe that the selection strategies allow for achieving high accuracies faster (fewer learning iterations) and with a smaller amount of labeled samples compared to the traditional learning approach. Hence, active learning can contribute significantly to the diagnosis of skin lesions, beneficially reducing specialists' annotation costs.

Computational Analysis of Transposable Elements and CircRNAs in Plants.

This chapter provides two main contributions: (1) a description of computational tools and databases used to identify and analyze transposable elements (TEs) and circRNAs in plants; and (2) data analysis on public TE and circRNA data. Our goal is to highlight the primary information available in the literature on circular noncoding RNAs and transposable elements in plants. The exploratory analysis performed on publicly available circRNA and TEs data help discuss four sequence features. Finally, we investigate the association on circRNAs:TE in plants in the model organism Arabidopsis thaliana.

Protective effect of oral treatment with Cordia verbenacea extract against UVB irradiation deleterious effects in the skin of hairless mouse.

Photochemoprotection of the skin can be achieved by inhibiting inflammation and oxidative stress, which we tested using Cordia verbenacea extract, a medicinal plant known for its rich content of antioxidant molecules and anti-inflammatory activity. In vitro antioxidant evaluation of Cordia verbenacea leaves ethanolic extract (CVE) presented the following results: ferric reducing antioxidant power (886.32 µM equivalent of Trolox/g extract); IC50 of 19.128 µg/ml for scavenging 2,2-diphenyl-1-picrylhydrazyl; IC50 of 12.48 µg/mL for scavenging 2,2'-azino-bis(3-ethylbenzothiazoline-6-sulphonic acid); decrease of hydroperoxides from linoleic acid (IC50 of 10.20 µg/mL); inhibition of thiobarbituric acid reactive substances (IC50 8.90 µg/mL); iron-chelating ability in bathophenanthroline iron assay (IC50 47.35 µg/mL); chemiluminescence triggered by free radicals in the H2O2/horseradish peroxidase/luminol (IC50 0.286 µg/mL) and xanthine/xanthine oxidase/luminol (IC50 0.42 µg/mL) methods. CVE (10-100 mg per kg, 30 min before and immediately after UVB exposure) treatment was performed by gavage in hairless mice. CVE inhibited skin edema, neutrophil infiltration, and overproduction of MMP-9; reduced levels of TNF-α, IL-1ß, and IL- 6; numbers of skin mast cells, epidermal thickening, number of epidermal apoptotic keratinocytes, and collagen degradation. CVE increased the skin's natural antioxidant defenses as observed by Nrf-2, NAD(P)H quinone oxidoreductase 1, and heme oxygenase 1 mRNA expression enhancement. Furthermore, CVE inhibited lipid peroxidation and superoxide anion production and recovered antioxidant reduced glutathione, catalase activity, and ROS scavenging capacity of the skin. Concluding, CVE downregulates the skin inflammatory and oxidative damages triggered by UVB, demonstrating its potentialities as a therapeutic approach.

Active semi-supervised learning for biological data classification.

Due to datasets have continuously grown, efforts have been performed in the attempt to solve the problem related to the large amount of unlabeled data in disproportion to the scarcity of labeled data. Another important issue is related to the trade-off between the difficulty in obtaining annotations provided by a specialist and the need for a significant amount of annotated data to obtain a robust classifier. In this context, active learning techniques jointly with semi-supervised learning are interesting. A smaller number of more informative samples previously selected (by the active learning strategy) and labeled by a specialist can propagate the labels to a set of unlabeled data (through the semi-supervised one). However, most of the literature works neglect the need for interactive response times that can be required by certain real applications. We propose a more effective and efficient active semi-supervised learning framework, including a new active learning method. An extensive experimental evaluation was performed in the biological context (using the ALL-AML, Escherichia coli and PlantLeaves II datasets), comparing our proposals with state-of-the-art literature works and different supervised (SVM, RF, OPF) and semi-supervised (YATSI-SVM, YATSI-RF and YATSI-OPF) classifiers. From the obtained results, we can observe the benefits of our framework, which allows the classifier to achieve higher accuracies more quickly with a reduced number of annotated samples. Moreover, the selection criterion adopted by our active learning method, based on diversity and uncertainty, enables the prioritization of the most informative boundary samples for the learning process. We obtained a gain of up to 20% against other learning techniques. The active semi-supervised learning approaches presented a better trade-off (accuracies and competitive and viable computational times) when compared with the active supervised learning ones.

Nectandra cuspidata fraction and the isolated polyphenols protect fibroblasts and hairless mice skin from UVB-induced inflammation and oxidative stress.

Excessive exposure to UVB radiation can lead to oxidative and inflammatory damage that compromises the cutaneous integrity. The application on the skin of photochemoprotective products is considered a relevant approach for the prevention of oxidative damage. In this study the in vitro and in vivo photochemoprotective effects of antioxidant plant materials obtained from the leaves of Nectandra cuspidata Nees following UVB irradiation were evaluated. The cytoprotective effect, reactive oxygen species (ROS) production and lipid peroxidation (LPO) were assessed in L-929 fibroblasts treated with the ethyl acetate fraction (EAF) or isolated compounds (epicatechin, isovitexin and vitexin) before or after irradiation with UVB (500 mJ/cm2). EAF substantially reduced the dead of cells and inhibited the UVB-induced ROS production and LPO in both treatments, compared with the irradiated untreated fibroblasts, presenting effects similar or better than pure compounds. The in vivo photochemoprotective effects of a topical emulsion containing 1% EAF (F2) were evaluated in hairless mice exposed to UVB. F2 improved all evaluated parameters in the skin of animals, inhibited ROS production, increased antioxidant defenses by decreasing reduced glutathione (GSH) and catalase depletion, reduced the activities of metalloproteinases (MMP-2 and MMP-9) and myeloperoxidase, decreased epidermal thickness and skin edema, and inhibited the appearance of sunburn cells as well as the recruitment of neutrophils and mast cell inflammatory infiltrates. These findings show that EAF presents high photochemoprotective effects, and that a topical formulation containing it may have potential for skin care.

Exploring Active Learning Based on Representativeness and Uncertainty for Biomedical Data Classification.

Nowadays, there is an abundance of biomedical data, such as images and genetic sequences, among others. However, there is a lack of annotation to such volume of data, due to the high costs involved to perform this task. Thus, it is mandatory to develop techniques to ease the burden of human annotation. To reach such goal active learning strategies can be applied. However, the state-of-the-art active learning methods, generally, are not feasible to lead with real-world datasets. Another important issue, that is generally neglected by these methods, is related to the conception that the classifier tends to learn more and more at each iteration. Their adopted selection criteria do not properly exploit the knowledge of the classifier. Therefore, in this paper, we propose the use of an active learning approach, in order to leverage the learning process, including the proposal of a novel active learning strategy. The main difference of our proposed strategy is related to the participation of the classifier in an extremely active way in its learning process. So, we can better maximize and prioritize the knowledge that is obtained by the classifier at each iteration, making use of this knowledge in a more appropriate and useful way when selecting more informative samples. To do so, in our selection criteria, we give significant importance to the classifications suggested by the classifier. In addition, jointly with the participation and the knowledge of the classifier, we consider both uncertainty and representativeness criteria through a fine-grained analysis of the samples. Experimental results show that our novel active learning approach outperforms state-of-the-art active learning methods, considering several supervised classifiers. Hence, dealing with real dataset problems in a better way, equalizing the tradeoff between annotation task and higher accuracy rates.

Contributing to agriculture by using soybean seed data from the tetrazolium test.

Agribusiness has a great relevance in the world׳s economy. It generates a considerable impact in the gross national product of several nations. Hence, it is the major driver of many national economies. Nowadays, from each new planting to harvesting process it is mandatory and crucial to apply some kind of technology to optimize a given singular process, or even the entire cropping chain. For instance, digital image analysis joined with machine learning methods can be applied to obtain and guarantee a higher quality of the harvest, leading to not only a greater profit for producers, but also better products with lower cost to the final consumers. Thus, to provide this possibility this work describes a visual feature dataset from soybean seed images obtained from the tetrazolium test. This is a test capable to define how healthy a given seed is (e.g. how much the plant will produce, or if it is resistant to inclement weather, among others). To answer these questions we proposed this dataset which is the cornerstone to provide an effective classification of the soybean seed vigor (i.e. an extremely tiresome human visual inspection process). Besides, as one of the most prominent international commodity, the soybean production must follow rigid quality control process to be part of world trade. Hence, small mistakes in the seed vigor definition of a given seed lot can lead to huge losses.

The Lipid Mediator Resolvin D1 Reduces the Skin Inflammation and Oxidative Stress Induced by UV Irradiation in Hairless Mice.

UV irradiation-induced oxidative stress and inflammation contribute to the development of skin diseases. Therefore, targeting oxidative stress and inflammation might contribute to reduce skin diseases. Resolvin D1 (RvD1) is a bioactive metabolite generated during inflammation to actively orchestrate the resolution of inflammation. However, the therapeutic potential of RvD1 in UVB skin inflammation remains undetermined, which was, therefore, the aim of the present study. The intraperitoneal treatment with RvD1 (3-100 ng/mouse) reduced UVB irradiation-induced skin edema, myeloperoxidase activity, matrix metalloproteinase 9 activity, and reduced glutathione depletion with consistent effects observed with the dose of 30 ng/mouse, which was selected to the following experiments. RvD1 inhibited UVB reduction of catalase activity, and hydroperoxide formation, superoxide anion production, and gp91phox mRNA expression. RvD1 also increased the Nrf2 and its downstream targets NQO1 and HO-1 mRNA expression. Regarding cytokines, RvD1 inhibited UVB-induced production of IL-1ß, IL-6, IL-33, TNF-α, TGF-ß, and IL-10. These immuno-biochemical alterations by RvD1 treatment had as consequence the reduction of UVB-induced epidermal thickness, sunburn and mast cell counts, and collagen degradation. Therefore, RvD1 inhibited UVB-induced skin oxidative stress and inflammation, rendering this resolving lipid mediator as a promising therapeutic agent.

Choosing the Most Effective Pattern Classification Model under Learning-Time Constraint.

Nowadays, large datasets are common and demand faster and more effective pattern analysis techniques. However, methodologies to compare classifiers usually do not take into account the learning-time constraints required by applications. This work presents a methodology to compare classifiers with respect to their ability to learn from classification errors on a large learning set, within a given time limit. Faster techniques may acquire more training samples, but only when they are more effective will they achieve higher performance on unseen testing sets. We demonstrate this result using several techniques, multiple datasets, and typical learning-time limits required by applications.