A Machine Learning Application Based in Random Forest for Integrating Mass Spectrometry-Based Metabolomic Data: A Simple Screening Method for Patients With Zika Virus

Autor(es):Mostrar menos -

Odir Rodrigues Melo, Carlos Fernando ^[1] ; Navarro, Luiz Claudio ^[2] ; de Oliveira, Diogo Noin ^[1] ; Guerreiro, Tatiane Melina ^[1] ; Lima, Estela de Oliveira ^[1] ; Delafiori, Jeany ^[1] ; Dabaja, Mohamed Ziad ^[1] ; Ribeiro, Marta da Silva ^[1] ; de Menezes, Maico ^[1] ; Martins Rodrigues, Rafael Gustavo ^[1] ; Morishita, Karen Noda ^[1] ; Esteves, Cibele Zanardi ^[1] ; Lucas de Amorim, Aline Lopes ^[1] ; Aoyagui, Caroline Tiemi ^[1] ; Parise, Pierina Lorencini ^[3] ; Milanez, Guilherme Paier ^[3] ; do Nascimento, Gabriela Mansano ^[3] ; Ribas Freitas, Andre Ricardo ^{[4, 5]} ; Angerami, Rodrigo ^[6] ; Maranhao Costa, Fabio Trindade ^[3] ; Arns, Clarice Weis ^[3] ; Resende, Mariangela Ribeiro ^[6] ; Amaral, Eliana ^[7] ; Passini Junior, Renato ^[7] ; Ribeiro-do-Valle, Carolina C. ^[7] ; Milanez, Helaine ^[7] ; Moretti, Maria Luiza ^[6] ; Proenca-Modena, Jose Luiz ^[3] ; Avila, Sandra ^[2] ; Rocha, Anderson ^[2] ; Catharino, Rodrigo Ramos ^[1] ; Network, Zika-Unicamp

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Sch Phannaceut Sci FCF, Innovate Biomarkers Lab, Campinas, SP - Brazil

^[2] Univ Estadual Campinas, IC, RECOD Lab, Campinas, SP - Brazil

^[3] Univ Estadual Campinas, Biol Inst, Dept Genet Evolut Microbiol & Immunol, Campinas, SP - Brazil

^[4] Sao Leopoldo Mandic Inst & Res Ctr, Campinas, SP - Brazil

^[5] Campinas Dept Publ Hlth Surveillance, Campinas, SP - Brazil

^[6] Univ Estadual Campinas, Sch Med Sci, Clin Pathol Dept, Campinas, SP - Brazil

^[7] Univ Campinas Campinas, Sch Med Sci, Obstet & Gynecol Dept, Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY; v. 6, APR 11 2018.
• Citações Web of Science: 0

Resumo

Recent Zika outbreaks in South America, accompanied by unexpectedly severe clinical complications have brought much interest in fast and reliable screening methods for ZIKV (Zika virus) identification. Reverse-transcriptase polymerase chain reaction (RT-PCR) is currently the method of choice to detect ZIKV in biological samples. This approach, none-theless, demands a considerable amount of time and resources such as kits and reagents that, in endemic areas, may result in a substantial financial burden over affected individuals and health services veering away from RT-PCR analysis. This study presents a powerful combination of high-resolution mass spectrometry and a machine-learning prediction model for data analysis to assess the existence of ZIKV infection across a series of patients that bear similar symptomatic conditions, but not necessarily are infected with the disease. By using mass spectrometry data that are inputted wrth the developed decision-making algorithm, we were able to provide a set of features that work as a ``fingerprint{''} for this specific pathophysiological condition, even after the acute phase of infection. Since both mass spectrometry and machine learning approaches are well-established and have largely utilized tools within their respective fields, this combination of methods emerges as a distinct alternative for clinical applications, providing a diagnostic screening-faster and more accurate-with improved cost-effectiveness when compared to existing technologies. (AU)

• Processo FAPESP: 14/00302-0 - Shotgun lipidômico em giardíase, meningites e tuberculose: a busca de marcadores para diagnósticos, empregando novas e revolucionárias técnicas de espectrometria de massas
• Beneficiário: Cibele Zanardi Esteves
• Linha de fomento: Bolsas no Brasil - Doutorado
• Processo FAPESP: 11/50400-0 - Metabolismo energético, estado redox e funcionalidade mitocondrial na morte celular e em desordens cardiometabólicas e neurodegenerativas
• Beneficiário: Aníbal Eugênio Vercesi
• Linha de fomento: Auxílio à Pesquisa - Temático
• Processo FAPESP: 15/06809-1 - Determinação de marcadores químicos em diferentes produtos bovinos por Espectrometria de Massas
• Beneficiário: Rodrigo Ramos Catharino
• Linha de fomento: Auxílio à Pesquisa - Regular
• Processo FAPESP: 16/17066-2 - Metabolômica e lipidômica do Zika vírus, do mosquito ao paciente
• Beneficiário: Carlos Fernando Odir Rodrigues Melo
• Linha de fomento: Bolsas no Brasil - Doutorado
• Processo FAPESP: 17/12646-3 - Déjà vu: coerência temporal, espacial e de caracterização de dados heterogêneos para análise e interpretação de integridade
• Beneficiário: Anderson de Rezende Rocha
• Linha de fomento: Auxílio à Pesquisa - Temático