Dengue has become one of the most important worldwide arthropod-borne diseases. Dengue phenotypes are based on laboratorial and clinical exams, which are known to be inaccurate. Objective: We present a machine learning approach for the prediction of dengue fever severity based solely on human genome data. Methods: One hundred and two Brazilian dengue patients and controls were genotyped for 322 innate immunity Single Nucleotide Polymorphisms (SNPs). Our model uses a Support Vector Machine (SVM) algorithm to find the optimal loci classification subset, and then an Artificial Neural Network (ANN) is used to classify patients into dengue fever (DF) or severe dengue (SD). Results: The ANN trained on 13 key immune SNPs selected under dominant or recessive models produced median values of accuracy greater than 86%, and sensitivity and specificity over 98% and 51%, respectively. Conclusion: The proposed classification method, using only genome markers, can be used to identify individuals at high risk for developing the severe dengue phenotype even in uninfected conditions. Significance: Our results suggest that the genetic context is a key element in phenotype definition in dengue. The methodology proposed here is extendable to other Mendelian-based and genetically influenced diseases.

The Oropouche virus (OROV) is an arbovirus (Peribunyaviridae: Orthobunyavirus) that traditionally causes febrile outbreaks in Latin America’s Amazon region. Previously, OROV was not associated with severe pregnancy outcomes. During the 2022–2024 outbreak in Brazil, OROV expanded geographically, revealing links to adverse pregnancy outcomes. This study describes six cases with varied fetal outcomes, including miscarriage, antepartum, intrauterine fetal demise (IFD), and normal development, correlating with maternal symptoms but not symptom severity. Vertical transmission was confirmed by detecting OROV through RT-qPCR, ELISA, and immunohistochemistry in fetal tissues. Genome sequencing from an IFD case identified a novel reassortment pattern reported in the 2022–2024 outbreak. Severe encephalomalacia, meningoencephalitis, vascular compromise, and multi-organ damage were evident, underscoring the significant risk OROV poses to fetal development and emphasizing the need for further investigation.

The management of acute dengue patients during outbreaks is a challenging problem. Most of the dengue fever cases are benign, but some cases develop into a severe and possibly lethal vasculopathy, known as dengue hemorrhagic fever. Early symptoms of dengue and hemorrhagic fever are very similar. An early differential diagnosis is needed to predict which of these two clinical presentations is crucial to proper patient care and public health management. This study evaluates the predictive potential of specific mRNA expression markers of dengue hemorrhagic fever using quantitative real-time PCR assays. Six candidate "dengue hemorrhagic fever specific signature genes" were evaluated and all showed good correlation among their transcription levels at early days of infection and the later development of severe vasculopathy. The markers selected were able to indicate, at early stages of infection, the evolution of a dengue-infected patient to the severe form of the illness. Despite the fact that these results grant further validation studies, the panel of candidate prognostic markers obtained demonstrated the potential to be useful for clinical use in the form of a fast assay based in blood samples.

Dengue is considered one of the most challenging public health threats in the world. Infection may be clinically asymptomatic but can result in severe forms. The indoleamine 2,3 dioxygenase ( IDO ) gene encodes one of first enzymes ( IDO ) of the kynurenine pathway. This study aimed to verify the association between G2431A IDO1 gene single nucleotide polymorphism (SNP) (rs3739319) and dengue fever development. We included 299 dengue-infected individuals in the study and 96 dengue-free controls. We collected clinical and diagnostic test data and divided the patients with dengue infection into three groups, based on World Health Organization (WHO) criteria: 131 Dengue without warning signs (DWOS), 143 Dengue with warning signs (DWS), and 25 severe dengue (SD). We genotyped 193 of the dengue cases using quantitative polymerase chain reaction to the SNP rs3739319. The other 106 dengue cases and 96 dengue-free controls had previously been genotyped using the Illumina Genotyping Kit. Genotyping of the infected patients revealed frequencies of 106 GG (35.4%), 126 GA (42.1%), and 67 AA (22.4%), whereas the nondengue exposed control group showed similar frequencies, 29 GG (30.2%), 52 GA (54.2%), and 15 AA (15.6%). Under risk analysis we found that AA genotype patients had a higher risk of developing SD in a codominant model (AA × GG; odds ratio [OR] = 11.5-fold in comparison to non-SD group -DWOS and -DWS patients; confidence interval [CI] = 0.02–0.32; Yates correction = 1.9e-05) and in a recessive model (AA × AG+GG; OR = 9.41; CI = 3.62–26.7; Yates correction = 4.8e-08). An allelic model reinforced the association between A allele and SD phenotype development that was found in the SD versus DWOS+DWS analysis (OR = 3.59; CI = 1.50–9.56; Yates correction = 0.0033). Our data show an association between the IDO G2431A variant and the risk for SD. This SNP may be relevant for further investigation into disease mechanisms and host factors in future genetic and pathophysiological studies.

We present a genome polymorphisms/machine learning approach for severe COVID-19 prognosis. Ninety-six Brazilian severe COVID-19 patients and controls were genotyped for 296 innate immunity loci. Our model used a feature selection algorithm, namely recursive feature elimination coupled with a support vector machine, to find the optimal loci classification subset, followed by a support vector machine with the linear kernel (SVM-LK) to classify patients into the severe COVID-19 group. The best features that were selected by the SVM-RFE method included 12 SNPs in 12 genes: PD-L1, PD-L2, IL10RA, JAK2, STAT1, IFIT1, IFIH1, DC-SIGNR, IFNB1, IRAK4, IRF1, and IL10. During the COVID-19 prognosis step by SVM-LK, the metrics were: 85% accuracy, 80% sensitivity, and 90% specificity. In comparison, univariate analysis under the 12 selected SNPs showed some highlights for individual variant alleles that represented risk (PD-L1 and IFIT1) or protection (JAK2 and IFIH1). Variant genotypes carrying risk effects were represented by PD-L2 and IFIT1 genes. The proposed complex classification method can be used to identify individuals who are at a high risk of developing severe COVID-19 outcomes even in uninfected conditions, which is a disruptive concept in COVID-19 prognosis. Our results suggest that the genetic context is an important factor in the development of severe COVID-19.

The Orthobunyavirus oropoucheense in a arthropod borne zoonotic pathogen known to infect sylvatic animals and humans by means of biting midges transmission. Several large-scale human outbreaks of Oropouche virus (OROV), primarily confined to the Amazon region, were documented over the decades. However, since 2022, more widespread OROV outbreaks have been unfolding in Brazil and across South America, with cases exported to Cuba, Italy, and Germany. I In Brazil, the virus has reached and established communitary transmission in states from all major regions of the country. Here we isolated, characterized the cytopathic effect and the full genomic sequence of two OROV isolates from the current outbreak. Our data shows that OROV can readily infect and replicate in non-human primate cells, supporting the role of non-human primates as important reservoirs. Phylogenetic data supports a direct introduction of the same lineages causing the 2022-24 outbreak in Brazil from the Amazonas state, the epicenter of the epidemics in Brazil. Lastly, as case counts accumulate in the state and the Northeast region, clear evidence supports established and sustained transmission. Continued studies are critical to understand the transmission cycle in this region, the most important vectors and reservoirs, to appropriately deploy control measures.