Integrating databases for spatial analysis of parasite-host associations and the novel Brazilian dataset.

Incomplete information on parasites, their associated hosts, and their precise geographical location hampers the ability to predict disease emergence in Brazil, a continental-sized country characterised by significant regional disparities. Here, we demonstrate how the NCBI Nucleotide and GBIF databases can be used as complementary databases to study spatially georeferenced parasite-host associations. We also provide a comprehensive dataset of parasites associated with mammal species that occur in Brazil, the Brazilian Mammal Parasite Occurrence Data (BMPO). This dataset integrates wild mammal species' morphological and life-history traits, zoonotic parasite status, and zoonotic microparasite transmission modes. Through meta-networks, comprising interconnected host species linked by shared zoonotic microparasites, we elucidate patterns of zoonotic microparasite dissemination. This approach contributes to wild animal and zoonoses surveillance, identifying and targeting host species accountable for disproportionate levels of parasite sharing within distinct biomes. Moreover, our novel dataset contributes to the refinement of models concerning disease emergence and parasite distribution among host species.

Statistically enriched geospatial datasets of Brazilian municipalities for data-driven modeling.

The lack of georeferencing in geospatial datasets hinders the accomplishment of scientific studies that rely on accurate data. This is particularly concerning in the field of health sciences, where georeferenced data could lead to scientific results of great relevance to society. The Brazilian health systems, especially those for Notifiable Diseases, in practice do not register georeferenced data; instead, the records indicate merely the municipality in which the event occurred. Typically in data-driven modeling, accurate disease prediction models based on occurrence requires socioenvironmental characteristics of the exact location of each event, which is often unavailable. To enrich the expressiveness of data-driven models when the municipality of the event is the best available information, we produced datasets with statistical characterization of all 5,570 Brazilian municipalities in 642 layers of thematic data that represent the natural and artificial characteristics of the municipalities' landscapes over time. This resulted in a collection of datasets comprising a total of 11,556 descriptive statistics attributes for each municipality.

Drug design and repurposing with DockThor-VS web server focusing on SARS-CoV-2 therapeutic targets and their non-synonym variants.

The COVID-19 caused by the SARS-CoV-2 virus was declared a pandemic disease in March 2020 by the World Health Organization (WHO). Structure-Based Drug Design strategies based on docking methodologies have been widely used for both new drug development and drug repurposing to find effective treatments against this disease. In this work, we present the developments implemented in the DockThor-VS web server to provide a virtual screening (VS) platform with curated structures of potential therapeutic targets from SARS-CoV-2 incorporating genetic information regarding relevant non-synonymous variations. The web server facilitates repurposing VS experiments providing curated libraries of currently available drugs on the market. At present, DockThor-VS provides ready-for-docking 3D structures for wild type and selected mutations for Nsp3 (papain-like, PLpro domain), Nsp5 (Mpro, 3CLpro), Nsp12 (RdRp), Nsp15 (NendoU), N protein, and Spike. We performed VS experiments of FDA-approved drugs considering the therapeutic targets available at the web server to assess the impact of considering different structures and mutations to identify possible new treatments of SARS-CoV-2 infections. The DockThor-VS is freely available at www.dockthor.lncc.br .

New machine learning and physics-based scoring functions for drug discovery.

Scoring functions are essential for modern in silico drug discovery. However, the accurate prediction of binding affinity by scoring functions remains a challenging task. The performance of scoring functions is very heterogeneous across different target classes. Scoring functions based on precise physics-based descriptors better representing protein-ligand recognition process are strongly needed. We developed a set of new empirical scoring functions, named DockTScore, by explicitly accounting for physics-based terms combined with machine learning. Target-specific scoring functions were developed for two important drug targets, proteases and protein-protein interactions, representing an original class of molecules for drug discovery. Multiple linear regression (MLR), support vector machine and random forest algorithms were employed to derive general and target-specific scoring functions involving optimized MMFF94S force-field terms, solvation and lipophilic interactions terms, and an improved term accounting for ligand torsional entropy contribution to ligand binding. DockTScore scoring functions demonstrated to be competitive with the current best-evaluated scoring functions in terms of binding energy prediction and ranking on four DUD-E datasets and will be useful for in silico drug design for diverse proteins as well as for specific targets such as proteases and protein-protein interactions. Currently, the MLR DockTScore is available at www.dockthor.lncc.br .

SISS-Geo: Leveraging Citizen Science to Monitor Wildlife Health Risks in Brazil.

The well-being of human and wildlife health involves many challenges, such as monitoring the movement of pathogens; expanding health surveillance; collecting data and extracting information to identify and predict risks; integrating specialists from different areas to handle data, species and distinct social and environmental contexts; and the commitment to bringing relevant information to society. In Brazil, there is still the difficulty of building a system that is not impaired by its large territorial extension and its poorly integrated sectoral policies. The Brazilian Wildlife Health Information System, SISS-Geo (SISS-Geo is the abbreviation of "Sistema de Informação em Saúde Silvestre Georreferenciado" (which translates to "Georeferenced Wildlife Health Information System") and can be accessed at http://www.biodiversidade.ciss.fiocruz.br or http://sissgeo.lncc.br (in Portuguese)), is a platform for collaborative monitoring that intends to overcome the challenges in wildlife health. It aims at the integration and participation of various segments of society, encompassing the registration of animals occurrences by citizen scientists; the reliable diagnosis of pathogens from the laboratory and expert networks; and computational and mathematical challenges in analytical and predictive systems, model interpretation, data integration and visualization, and geographic information systems. It has been successfully applied to support decision-making on recent wildlife health events, such as a Yellow Fever epizootic.

NICeSim: an open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making.

OBJECTIVE: This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques to aid health professionals to better understand the treatment and prognosis of premature newborns. METHODS: The application was developed and tested using data collected in a Brazilian hospital. The available data were used to feed an ML pipeline that was designed to create a simulator capable of predicting the outcome (death probability) for newborns admitted to neonatal intensive care units. However, unlike previous scoring systems, our computational tool is not intended to be used at the patients bedside, although it is possible. Our primary goal is to deliver a computational system to aid medical research in understanding the correlation of key variables with the studied outcome so that new standards can be established for future clinical decisions. In the implemented simulation environment, the values of key attributes can be changed using a user-friendly interface, where the impact of each change on the outcome is immediately reported, allowing a quantitative analysis, in addition to a qualitative investigation, and delivering a totally interactive computational tool that facilitates hypothesis construction and testing. RESULTS: Our statistical experiments showed that the resulting model for death prediction could achieve an accuracy of 86.7% and an area under the receiver operating characteristic curve of 0.84 for the positive class. Using this model, three physicians and a neonatal nutritionist performed simulations with key variables correlated with chance of death. The results indicated important tendencies for the effect of each variable and the combination of variables on prognosis. We could also observe values of gestational age and birth weight for which a low Apgar score and the occurrence of respiratory distress syndrome (RDS) could be less or more severe. For instance, we have noticed that for a newborn with 2000 g or more the occurrence of RDS is far less problematic than for neonates weighing less. CONCLUSIONS: The significant accuracy demonstrated by our predictive model shows that NICeSim might be used for hypothesis testing to minimize in vivo experiments. We observed that the model delivers predictions that are in very good agreement with the literature, demonstrating that NICeSim might be an important tool for supporting decision making in medical practice. Other very important characteristics of NICeSim are its flexibility and dynamism. NICeSim is flexible because it allows the inclusion and deletion of variables according to the requirements of a particular study. It is also dynamic because it trains a just-in-time model. Therefore, the system is improved as data from new patients become available. Finally, NICeSim can be extended in a cooperative manner because it is an open-source system.