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.

Lymphatic filariasis (LF) is a parasitic disease caused by the worms Wuchereria bancrofti, Brugia malayi, or Brugia timori. It is a tropical and subtropical illness that affects approximately 67 million people worldwide and that still requires better diagnostic tools to prevent its spread and enhance the effectiveness of control procedures. Traditional parasitological tests and diagnostic methods based on whole protein extracts from different worms are known for problems related to sample time collection, sensitivity, and specificity. More recently, new diagnostic tools based on immunological methods using recombinant antigens have been developed. The current review describes the several recombinant antigens used as tools for lymphatic filariasis diagnosis in antigen and antibody capture assays, highlighting their advantages and limitations as well as the main commercial tests developed based on them. The literature chronology is from 1991 to 2021. First, it describes the historical background related to the identification of relevant antigens and the generation of the recombinant polypeptides used for the LF diagnosis, also detailing features specific to each antigen. The subsequent section then discusses the use of those proteins to develop antigen and antibody capture tests to detect LF. So far, studies focusing on antibody capture assays are based on 13 different antigens with at least six commercially available tests, with five proteins further used for the development of antigen capture tests. Five antigens explored in this paper belong to the SXP/RAL-2 family (BmSXP, Bm14, WbSXP-1, Wb14, WbL), and the others are BmShp-1, Bm33, BmR1, BmVAH, WbVAH, BmALT-1, BmALT-2, and Wb123. It is expected that advances in research with these antigens will allow further development of tests combining both sensitivity and specificity with low costs, assisting the Global Program to Eliminate Lymphatic Filariasis (GPELF).

Background: The spread of Dengue virus (DENV) infections, as well as their signs and symptoms, are the result of a complex interaction between several factors. In Brazil, especially in the Northeastern, dengue is an important public health problem. Here, we report an epidemiological analysis of dengue cases in Pernambuco state, Northeastern Brazil, during 2015–2017. Methods: This work is a retrospective cross-sectional observational study on the epidemiological profile of all dengue cases confirmed and reported to the Health Secretary of Pernambuco between 2015 and 2017. These data cover all municipalities of Pernambuco, except Fernando de Noronha. DENV-positive individuals were classified according to the dengue type (without and with warning signs, or severe dengue), age, gender, ethnicity and intermediate geographic region of residence (Recife, Caruaru, Serra Talhada or Petrolina). The distribution of cases over the years was assessed by χ2 test. Temperature and rainfall data were evaluated by Unpaired t-test. p-value < 0.05 and CI 95% were considered in all analyses. Results: Most dengue cases was without warning signs. The most observed characteristics in the less severe dengue phenotypes were: female, mulatto ethnicity and age between 20 and 39 years old; this profile was more clearly observed in 2015. In 2016 and 2017, however, the numbers of dengue without and with warning signs were more evenly distributed and the difference in cases within groups decreased significantly. Regarding severe dengue, mulattoes were the most affected, but it is possible to note a trend towards a more uniform distribution between the genders and ages. Recife was the region with the highest numbers of both total cases and incidence rates and the highest rainfall levels. Overall, over the years, there has been a decrease in dengue cases in all regions of Pernambuco. Conclusions: We identified the epidemiological profile of dengue in Pernambuco, Brazil, reporting the gender, age, ethnicity and regions most affected by different dengue types. In addition, we observed that these cases were probably more influenced by rainfall than by temperature. Finally, we believe that this epidemiological knowledge is important to direct public health policies to the reality of each population.

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.

Key words: immunodiagnostic; Wuchereria bancrofti; ELISA; biotechnology

Dengue is a global and growing health threat, especially in Southeast Asia, West Pacific and South America. Infection by the dengue virus (DENV) results in dengue fever, which can evolve to severe forms. Cytokines, especially interferons, are involved in the immunopathogenesis of dengue fever, and so may influence the disease outcomes. The aim of this study was to investigate the association between severe forms of dengue and two single nucleotide polymorphisms (SNPs) in the interferon-gamma gene (IFNG): A256G (rs2069716) and A325G (rs2069727). We included 274 patients infected with DENV serotype 3: 119 cases of dengue without warning signs (DWoWS), and 155 with warning signs (DWWS) or severe dengue (SD). DNA was extracted, and genotyped with Illumina Genotyping Kit or real time PCR (TaqMan probes). We estimated the adjusted Odds Ratios (OR) by multivariate logistic regression models. When comparing with the ancestral AA/AA diplotype (A256G/A325G), we found a protective association of the AA/AG against DWWS/SD among patients with secondary dengue (OR 0.51; 95% IC 0.24-1.10, p = 0.085), adjusting for age and sex. The variant genotype at locus A325G of the IFNG, in combination with the ancestral genotype at locus A256G, can protect against severe clinical forms of secondary dengue in Brazilian DENV3-infected patients.