Deep learning framework for epidemiological forecasting: A study on COVID-19 cases and deaths in the Amazon state of Pará, Brazil.

Modeling time series has been a particularly challenging aspect due to the need for constant adjustments in a rapidly changing environment, data uncertainty, dependencies between variables, volatile fluctuations, and the need to identify ideal hyperparameters. The present study presents a Framework capable of making projections from time series related to cases and deaths by COVID-19 in the Amazonian state of Pará, in Brazil. For the first time, deep learning models such as TCN, TRANSFORMER, TFT, N-BEATS, and N-HiTS were assessed for this purpose. The ARIMA statistical model was also used in post-processing for residual adjustment and short-term smoothing of the generated forecasts. The Framework generates probabilistic forecasts, with multivariate support, considering the following variables: daily cases per day of the first symptom, cases published daily, the occurrence of deaths, deaths published daily, and percentage of daily vaccination. The generated predictions are statistically evaluated by determining the best model for 7-day moving average projections using evaluating metrics such as MSE, RMSE, MAPE, sMAPE, r2, Coefficient of Variation, and residual analysis. As a result, the generated projections showed an average error of 5.4% for Cases Publication, 8.0% for Cases Symptoms, 11.12% for Deaths Publication, and 4.6% for Deaths Occurrence, with the N-HiTS and N-BEATS models obtaining better results. In general terms, the use of deep learning models to predict cases and deaths from COVID-19 has proven to be a valuable practice for analyzing the spread of the virus, which allows health managers to better understand and respond to this kind of pandemic outbreak.

Genomic Characterization of Aeromonas veronii Provides Insights into Taxonomic Assignment and Reveals Widespread Virulence and Resistance Genes throughout the World.

Aeromonas veronii is a Gram-negative bacterial species that causes disease in fish and is nowadays increasingly recurrent in enteric infections of humans. This study was performed to characterize newly sequenced isolates by comparing them with complete genomes deposited at the NCBI (National Center for Biotechnology Information). Nine isolates from fish, environments, and humans from the São Francisco Valley (Petrolina, Pernambuco, Brazil) were sequenced and compared with complete genomes available in public databases to gain insight into taxonomic assignment and to better understand virulence and resistance profiles of this species within the One Health context. One local genome and four NCBI genomes were misidentified as A. veronii. A total of 239 virulence genes were identified in the local genomes, with most encoding adhesion, motility, and secretion systems. In total, 60 genes involved with resistance to 22 classes of antibiotics were identified in the genomes, including mcr-7 and cphA. The results suggest that the use of methods such as ANI is essential to avoid misclassification of the genomes. The virulence content of A. veronii from local isolates is similar to those complete genomes deposited at the NCBI. Genes encoding colistin resistance are widespread in the species, requiring greater attention for surveillance systems.

In silico approach to identify microsatellite candidate biomarkers to differentiate the biovar of Corynebacterium pseudotuberculosis genomes.

Corynebacterium pseudotuberculosis is the causative bacterial agent of the zoonotic disease known as caseous lymphadenitis, and it presents several mechanisms of response to host defenses, including the presence of virulence factors (VFs). The genomes of these bacteria have several polymorphic markers known as microsatellites, or simple sequence repeats (SSRs), that can be used to characterize the genome, to study possible polymorphisms existing among strains, and to verify the effects of such polymorphic markers in coding regions and regions associated with VFs. In this study, several SSRs were identified within coding regions throughout the 54 genomes of this species, revealing possible polymorphisms associated with coding regions that could be used as strain-specific or serotype-specific identifiers of C. pseudotuberculosis. The similarities associated with SSRs amongst the different serum variants of C. pseudotuberculosis, biovars equi and ovis, were also evaluated, and it was possible to identify SSRs located in coding regions responsible for a VF enrolled in pathogenesis known to mediate bacterial adherence (SpaH-type pili virulence factor). Phylogenetic analyses revealed that strains sharing SSR patterns, including the possible polymorphisms identified in the same position of gene-coding regions, were displayed by strains with a common ancestor, corroborating with the Genome Tree Report of the NCBI. Statistical analysis showed that the microsatellite groups belonging to equi and ovis biovars have a significance of 0.006 (p-value) in similarity, thus indicating them as good biomarker candidates for C. pseudotuberculosis.

Functional annotation of hypothetical proteins from the Exiguobacterium antarcticum strain B7 reveals proteins involved in adaptation to extreme environments, including high arsenic resistance.

Exiguobacterium antarcticum strain B7 is a psychrophilic Gram-positive bacterium that possesses enzymes that can be used for several biotechnological applications. However, many proteins from its genome are considered hypothetical proteins (HPs). These functionally unknown proteins may indicate important functions regarding the biological role of this bacterium, and the use of bioinformatics tools can assist in the biological understanding of this organism through functional annotation analysis. Thus, our study aimed to assign functions to proteins previously described as HPs, present in the genome of E. antarcticum B7. We used an extensive in silico workflow combining several bioinformatics tools for function annotation, sub-cellular localization and physicochemical characterization, three-dimensional structure determination, and protein-protein interactions. This genome contains 2772 genes, of which 765 CDS were annotated as HPs. The amino acid sequences of all HPs were submitted to our workflow and we successfully attributed function to 132 HPs. We identified 11 proteins that play important roles in the mechanisms of adaptation to adverse environments, such as flagellar biosynthesis, biofilm formation, carotenoids biosynthesis, and others. In addition, three predicted HPs are possibly related to arsenic tolerance. Through an in vitro assay, we verified that E. antarcticum B7 can grow at high concentrations of this metal. The approach used was important to precisely assign function to proteins from diverse classes and to infer relationships with proteins with functions already described in the literature. This approach aims to produce a better understanding of the mechanism by which this bacterium adapts to extreme environments and to the finding of targets with biotechnological interest.

GO FEAT: a rapid web-based functional annotation tool for genomic and transcriptomic data.

Downstream analysis of genomic and transcriptomic sequence data is often executed by functional annotation that can be performed by various bioinformatics tools and biological databases. However, a full fast integrated tool is not available for such analysis. Besides, the current available software is not able to produce analytic lists of annotations and graphs to help users in evaluating the output results. Therefore, we present the Gene Ontology Functional Enrichment Annotation Tool (GO FEAT), a free web platform for functional annotation and enrichment of genomic and transcriptomic data based on sequence homology search. The analysis can be customized and visualized as per users' needs and specifications. GO FEAT is freely available at http://computationalbiology.ufpa.br/gofeat/ and its source code is hosted at https://github.com/fabriciopa/gofeat .

Draft Genome Sequence of Corynebacterium pseudotuberculosis Strain PA07 Biovar ovis, Isolated from a Sheep Udder in Amazonia.

In this work, we present the draft genome sequence of Corynebacterium pseudotuberculosis strain PA07 biovar ovis, isolated from a caseous secretion from a sheep udder in Pará, Brazil. The genome contains 2,320,235 bp, 52.2% G+C content, 2,191 coding sequences (CDSs), five pseudogenes, 48 tRNAs, and three rRNAs.