Frontiers in Bioengineering and Biotechnology (Apr 2018)
A Machine Learning Application Based in Random Forest for Integrating Mass Spectrometry-Based Metabolomic Data: A Simple Screening Method for Patients With Zika Virus
- Carlos Fernando Odir Rodrigues Melo,
- Luiz Claudio Navarro,
- Diogo Noin de Oliveira,
- Tatiane Melina Guerreiro,
- Estela de Oliveira Lima,
- Jeany Delafiori,
- Mohamed Ziad Dabaja,
- Marta da Silva Ribeiro,
- Maico de Menezes,
- Rafael Gustavo Martins Rodrigues,
- Karen Noda Morishita,
- Cibele Zanardi Esteves,
- Aline Lopes Lucas de Amorim,
- Caroline Tiemi Aoyagui,
- Pierina Lorencini Parise,
- Guilherme Paier Milanez,
- Gabriela Mansano do Nascimento,
- André Ricardo Ribas Freitas,
- André Ricardo Ribas Freitas,
- Rodrigo Angerami,
- Fábio Trindade Maranhão Costa,
- Clarice Weis Arns,
- Mariangela Ribeiro Resende,
- Eliana Amaral,
- Renato Passini Junior,
- Carolina C. Ribeiro-do-Valle,
- Helaine Milanez,
- Maria Luiza Moretti,
- Jose Luiz Proenca-Modena,
- Sandra Avila,
- Anderson Rocha,
- Rodrigo Ramos Catharino
Affiliations
- Carlos Fernando Odir Rodrigues Melo
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Luiz Claudio Navarro
- RECOD Laboratory, Institute of Computing (IC), University of Campinas, Campinas, Brazil
- Diogo Noin de Oliveira
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Tatiane Melina Guerreiro
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Estela de Oliveira Lima
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Jeany Delafiori
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Mohamed Ziad Dabaja
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Marta da Silva Ribeiro
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Maico de Menezes
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Rafael Gustavo Martins Rodrigues
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Karen Noda Morishita
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Cibele Zanardi Esteves
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Aline Lopes Lucas de Amorim
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Caroline Tiemi Aoyagui
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- Pierina Lorencini Parise
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- Guilherme Paier Milanez
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- Gabriela Mansano do Nascimento
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- André Ricardo Ribas Freitas
- Campinas Department of Public Health Surveillance, Campinas, Brazil
- André Ricardo Ribas Freitas
- São Leopoldo Mandic Institute and Research Center, Campinas, Brazil
- Rodrigo Angerami
- Clinical Pathology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Fábio Trindade Maranhão Costa
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- Clarice Weis Arns
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- Mariangela Ribeiro Resende
- Clinical Pathology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Eliana Amaral
- Obstetrics and Gynecology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Renato Passini Junior
- Obstetrics and Gynecology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Carolina C. Ribeiro-do-Valle
- Obstetrics and Gynecology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Helaine Milanez
- Obstetrics and Gynecology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Maria Luiza Moretti
- Clinical Pathology Department, School of Medical Sciences, University of Campinas, Campinas, Brazil
- Jose Luiz Proenca-Modena
- Department of Genetics, Evolution, Microbiology and Immunology, Biology Institute, University of Campinas, Campinas, Brazil
- Sandra Avila
- RECOD Laboratory, Institute of Computing (IC), University of Campinas, Campinas, Brazil
- Anderson Rocha
- RECOD Laboratory, Institute of Computing (IC), University of Campinas, Campinas, Brazil
- Rodrigo Ramos Catharino
- Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences (FCF), University of Campinas, Campinas, Brazil
- DOI
- https://doi.org/10.3389/fbioe.2018.00031
- Journal volume & issue
-
Vol. 6
Abstract
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, nonetheless, 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 spectrometric data that are inputted with 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.
Keywords
- Zika virus
- Zika diagnosis
- diseases diagnosis
- high resolution mass spectrometry
- machine learning
- random forest
