João Vitor Oliveira Cruz

João Vitor Oliveira Cruz

Auto-generated profile, based on publicly available information

João Vitor Oliveira Cruz

Post-Graduate Program in Biotechnology, Institute of Health Sciences, Federal University of Bahia, Salvador-BA, Brazil; Institute of Health Sciences, Federal University of Bahia, Salvador-BA, Brazil

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 June 2024 in Journal of Global Antimicrobial Resistance
Verified
Journal Article
Open access
DRDANILO J P G ROCHA
DANILO J P G ROCHA
CSCarolina S. Silva
Carolina S. Silva
HJHendor N.R. Jesus
Hendor N.R. Jesus
FSFelipe G. Sacoda
Felipe G. Sacoda
JCJoão V.O. Cruz
João V.O. Cruz
Luis G. C. PachecoLuis G. C. Pacheco
Luis G. C. Pacheco
Herein, we combined different bioinformatics tools and databases (BV-BRC, ResFinder, RAST, and KmerResistance) to perform a prediction of antimicrobial resistance (AMR) in the genomic sequences of 107 Corynebacterium striatum isolates for which trustable antimicrobial susceptibility (AST) phenotypes could be retrieved. Then, the reliabilities of the AMR predictions were evaluated by different metrics: area under the ROC curve (AUC); Major Error Rates (MERs) and Very Major Error Rates (VMERs); Matthews Correlation Coefficient (MCC); F1-Score; and Accuracy. Out of 15 genes that were reliably detected in the C. striatum isolates, only tetW yielded predictive values for tetracycline resistance that were acceptable considering Food and Drug Administration (FDA)'s criteria for quality (MER < 3.0% and VMER with a 95% C.I. ≤1.5-≤7.5%); this was accompanied by a MCC score higher than 0.9 for this gene. Noteworthy, our results indicate that other commonly used metrics (AUC, F1-score, and Accuracy) may render overoptimistic evaluations of AMR-prediction reliabilities on imbalanced datasets. Accordingly, out of 10 genes tested by PCR on additional multidrug-resistant Corynebacterium spp. isolates (n = 18), the tetW gene rendered the best agreement values with AST profiles (94.11%). Overall, our results indicate that genome-based AMR prediction can still be challenging for MDR clinical isolates of emerging Corynebacterium spp.

31 December 2025 in BIOINFO
Verified
Journal Article
Closed access
LSLuiz R. Fraser Silva
Luiz R. Fraser Silva
CSCarolina S. Silva
Carolina S. Silva
JCJoão V. O. Cruz
João V. O. Cruz
FSFelipe G. Sacoda
Felipe G. Sacoda
DRDANILO J P G ROCHA
DANILO J P G ROCHA
Luis G. C. PachecoLuis G. C. Pacheco
Luis G. C. Pacheco
A pandemia de COVID-19, causada pelo SARS-CoV-2, trouxe à tona a importância das tecnologias de sequenciamento de nova geração (NGS) tanto na descoberta do vírus quanto na determinação de novas variantes. Em 2022, a Organização Mundial da Saúde emitiu uma estratégia global de vigilância genômica para patógenos de potencial pandêmico e epidêmico. Neste sentido, este trabalho busca implementar, comparar e validar protocolos que utilizam apenas dados brutos de sequenciamento para diagnóstico e determinação de variantes do vírus. Foram utilizados dados de 15 novos sequenciamentos de SARS-CoV-2, obtidos por metodologia direcionada Ion Ampliseq (n = 10) ou por abordagem metatranscriptômica (n = 5). A montagem dessas sequências foi realizada pelas plataformas ID-seq, CoronaSPAdes, PATRIC, BV-BRC e Genome Detective. Já a anotação foi realizada pelas plataformas BV-BRC, Genome Detective, GISAID e Nextclade. Inicialmente, a plataforma BV-BRC se mostrou a mais eficiente na determinação correta das variantes, porém, sofreu perda de especificidade após atualizações. Já o Genome Detective, em sua versão atualizada, apresentou uma maior capacidade de determinar a variante do vírus. A plataforma GISAID não gerou resultados satisfatórios para as amostras avaliadas, enquanto o Nextclade foi capaz de apontar a variante na maioria das nossas amostras, mostrando-se como uma plataforma confiável. Amostras sequenciadas pela metodologia Ion Ampliseq apresentaram valores mais uniformes e mais próximos das referências, em comparação à abordagem metatranscriptômica, evidenciando que o tipo de sequenciamento direcionado influencia a montagem e anotação.

11 June 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
MMMiguel Marinho
Miguel Marinho
JCJoão Cruz
João Cruz
Luis G. C. PachecoLuis G. C. Pacheco
Luis G. C. Pacheco
VMVitor Hugo Moreau
Vitor Hugo Moreau
Machine learning approaches are increasingly applied to microbial genomics, but their performance depends on how genomic data are represented. We present Genomage, a computational method that rapidly converts microbial genome sequences into RGB images for machine learning–based classification. Genomage encodes overlapping tetranucleotides into binary representations mapped to image pixels, preserving sequence composition and genome-scale organization. The method was evaluated using genomes from Klebsiella spp., hepatitis C virus (HCV), and hepatitis B virus (HBV). Classification models were trained using Google Teachable Machine, with optimal hyperparameters determined using Klebsiella pneumoniae and Klebsiella variicola. Genomage accurately discriminated K. pneumoniae from related species, differentiated HCV subgenotypes 1a and 1b with 92% accuracy (AUC = 0.96), and classified HBV genotypes A–F with accuracies exceeding 97%. Genomage provides an efficient interface between whole-genome data and machine learning workflows, with potential applications in pathogen genotyping, genomic surveillance, and the identification of antimicrobial resistance and hypervirulence signatures.

17 November 2023 in Boletim MicroVita
Verified
Journal Article
Open access
PDF file
LSLuiz Ricardo Fraser Silva
Luiz Ricardo Fraser Silva
CSCarolina dos Santos Silva
Carolina dos Santos Silva
JCJoão Vitor Oliveira Cruz
João Vitor Oliveira Cruz
FSFelipe Gazetta Sacoda
Felipe Gazetta Sacoda
LPLuis Pacheco
Luis Pacheco
Herein, we present a step-by-step guide for training students from different backgrounds in essential tools used for SARS-CoV-2 genome assembly and analysis. We anticipate that this guide can improve student awareness regarding genomic surveillance of viral pathogens and can, therefore, contribute to achieving the goals of the Global Genomic Surveillance Strategy 2022-2032 of the World Health Organization.