Assessing the relationship between species traits and extinction risk at a regional level: an analysis involving Brazilian terrestrial mammals.

One of the various concerns of conservation biology is determining why certain species are more threatened than others. In this study, we aim to relate the national conservation status of Brazilian mammals with the taxonomic group to which they belong and with three of their intrinsic traits: body mass, diet, and litter size. We compiled a database containing the species, their status, and their attributes, and a multiple correspondence analysis was applied to identify relationships between traits and status. The two groups that presented the highest relative frequencies of threatened species were "ungulates" and Carnivora. Additionally, mammals with body mass of 10 kg or more and with carnivorous diet had a higher relative frequency of threatened taxa. We found not only a strong relationship between intrinsic traits and conservation status, but also among the traits themselves, which highlights the role of the "group" variable as one of the best predictors of the risk that a given species be threatened. We believe our study has a broad potential for the conservation of species at the regional level, especially regarding the species currently classified as Data Deficient, and for identifying which species are prone to becoming threatened.

Ensemble Classifiers for Predicting HIV-1 Resistance from Three Rule-Based Genotypic Resistance Interpretation Systems.

Resistance to antiretrovirals (ARVs) is a major problem faced by HIV-infected individuals. Different rule-based algorithms were developed to infer HIV-1 susceptibility to antiretrovirals from genotypic data. However, there is discordance between them, resulting in difficulties for clinical decisions about which treatment to use. Here, we developed ensemble classifiers integrating three interpretation algorithms: Agence Nationale de Recherche sur le SIDA (ANRS), Rega, and the genotypic resistance interpretation system from Stanford HIV Drug Resistance Database (HIVdb). Three approaches were applied to develop a classifier with a single resistance profile: stacked generalization, a simple plurality vote scheme and the selection of the interpretation system with the best performance. The strategies were compared with the Friedman's test and the performance of the classifiers was evaluated using the F-measure, sensitivity and specificity values. We found that the three strategies had similar performances for the selected antiretrovirals. For some cases, the stacking technique with naïve Bayes as the learning algorithm showed a statistically superior F-measure. This study demonstrates that ensemble classifiers can be an alternative tool for clinical decision-making since they provide a single resistance profile from the most commonly used resistance interpretation systems.

Lopinavir Resistance Classification with Imbalanced Data Using Probabilistic Neural Networks.

Resistance to antiretroviral drugs has been a major obstacle for long-lasting treatment of HIV-infected patients. The development of models to predict drug resistance is recognized as useful for helping the decision of the best therapy for each HIV+ individual. The aim of this study was to develop classifiers for predicting resistance to the HIV protease inhibitor lopinavir using a probabilistic neural network (PNN). The data were provided by the Molecular Virology Laboratory of the Health Sciences Center, Federal University of Rio de Janeiro (CCS-UFRJ/Brazil). Using bootstrap and stepwise techniques, ten features were selected by logistic regression (LR) to be used as inputs to the network. Bootstrap and cross-validation were used to define the smoothing parameter of the PNN networks. Four balanced models were designed and evaluated using a separate test set. The accuracies of the classifiers with the test set ranged from 0.89 to 0.94, and the area under the receiver operating characteristic (ROC) curve (AUC) ranged from 0.96 to 0.97. The sensitivity ranged from 0.94 to 1.00, and the specificity was between 0.88 and 0.92. Four classifiers showed performances very close to three existing expert-based interpretation systems, the HIVdb, the Rega and the ANRS algorithms, and to a k-Nearest Neighbor.

Spatial Analysis of the Sociodemographic Characteristics, Comorbidities, Hospitalization, Signs, and Symptoms Among Hospitalized Coronavirus Disease 2019 Cases in the State of Rio De Janeiro, Brazil.

After more than 1 year from the beginning of the pandemic, the coronavirus disease 2019 (COVID-19) has reached all continents. The number of infected people is still increasing, and Brazil is among the countries with the highest number of registered cases in the world. In this study, we investigated the profile of hospitalized COVID-19 cases and the eventual clusters of similar areas, using geographic information systems. The study was conducted using secondary data. Variables such as sociodemographic characteristics, comorbidities, hospitalization, signs, and symptoms among confirmed cases were considered for each microregion/city of the state of Rio de Janeiro. These proportions were used when calculating the Global Moran's I. The local indicator of spatial association was used to identify local clusters. A significant global spatial auto correlation was found in 28% of the variables. The presence of spatial autocorrelation indicates that the proportions of patients with COVID-19 according to these characteristics are spatially oriented. Moran maps reveal 2 clusters, 1 of high proportions and 1 of low proportions. Understanding the geographic patterns of COVID-19 may assist public health investigators, contributing to actions to prevent and control the pandemic in the state.