Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses
ABSTRACT Brazil and many other Latin American countries are areas of endemicity for different neglected diseases, and the fungal infection paracoccidioidomycosis (PCM) is one of them. Among the clinical manifestations, pneumopathy associated with skin and mucosal lesions is the most frequent. PCM de...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Society for Microbiology
2020-06-01
|
| Series: | mSystems |
| Subjects: | |
| Online Access: | https://journals.asm.org/doi/10.1128/mSystems.00258-20 |
| _version_ | 1818422491143471104 |
|---|---|
| author | Estela de Oliveira Lima Luiz Claudio Navarro Karen Noda Morishita Camila Mika Kamikawa Rafael Gustavo Martins Rodrigues Mohamed Ziad Dabaja Diogo Noin de Oliveira Jeany Delafiori Flávia Luísa Dias-Audibert Marta da Silva Ribeiro Adriana Pardini Vicentini Anderson Rocha Rodrigo Ramos Catharino |
| author_facet | Estela de Oliveira Lima Luiz Claudio Navarro Karen Noda Morishita Camila Mika Kamikawa Rafael Gustavo Martins Rodrigues Mohamed Ziad Dabaja Diogo Noin de Oliveira Jeany Delafiori Flávia Luísa Dias-Audibert Marta da Silva Ribeiro Adriana Pardini Vicentini Anderson Rocha Rodrigo Ramos Catharino |
| author_sort | Estela de Oliveira Lima |
| collection | DOAJ |
| description | ABSTRACT Brazil and many other Latin American countries are areas of endemicity for different neglected diseases, and the fungal infection paracoccidioidomycosis (PCM) is one of them. Among the clinical manifestations, pneumopathy associated with skin and mucosal lesions is the most frequent. PCM definitive diagnosis depends on yeast microscopic visualization and immunological tests, but both present ambiguous results and difficulty in differentiating PCM from other fungal infections. This research has employed metabolomics analysis through high-resolution mass spectrometry to identify PCM biomarkers in serum samples in order to improve diagnosis for this debilitating disease. To upgrade the biomarker selection, machine learning approaches, using Random Forest classifiers, were combined with metabolomics data analysis. The proposed combination of these two analytical methods resulted in the identification of a set of 19 PCM biomarkers that show accuracy of 97.1%, specificity of 100%, and sensitivity of 94.1%. The obtained results are promising and present great potential to improve PCM definitive diagnosis and adequate pharmacological treatment, reducing the incidence of PCM sequelae and resulting in a better quality of life. IMPORTANCE Paracoccidioidomycosis (PCM) is a fungal infection typically found in Latin American countries, especially in Brazil. The identification of this disease is based on techniques that may fail sometimes. Intending to improve PCM detection in patient samples, this study used the combination of two of the newest technologies, artificial intelligence and metabolomics. This combination allowed PCM detection, independently of disease form, through identification of a set of molecules present in patients’ blood. The great difference in this research was the ability to detect disease with better confidence than the routine methods employed today. Another important point is that among the molecules, it was possible to identify some indicators of contamination and other infection that might worsen patients’ condition. Thus, the present work shows a great potential to improve PCM diagnosis and even disease management, considering the possibility to identify concomitant harmful factors. |
| first_indexed | 2024-12-14T13:27:06Z |
| format | Article |
| id | doaj.art-ac85687c0ff94853a2b955f83d53a6a6 |
| institution | Directory Open Access Journal |
| issn | 2379-5077 |
| language | English |
| last_indexed | 2024-12-14T13:27:06Z |
| publishDate | 2020-06-01 |
| publisher | American Society for Microbiology |
| record_format | Article |
| series | mSystems |
| spelling | doaj.art-ac85687c0ff94853a2b955f83d53a6a62022-12-21T22:59:48ZengAmerican Society for MicrobiologymSystems2379-50772020-06-015310.1128/mSystems.00258-20Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis DiagnosesEstela de Oliveira Lima0Luiz Claudio Navarro1Karen Noda Morishita2Camila Mika Kamikawa3Rafael Gustavo Martins Rodrigues4Mohamed Ziad Dabaja5Diogo Noin de Oliveira6Jeany Delafiori7Flávia Luísa Dias-Audibert8Marta da Silva Ribeiro9Adriana Pardini Vicentini10Anderson Rocha11Rodrigo Ramos Catharino12Department of Internal Medicine, Botucatu Medical School, São Paulo State University, Botucatu, SP, BrazilRECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilLaboratory of Mycosis Immunodiagnosis—Immunology Section, Adolfo Lutz Institute, São Paulo, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilLaboratory of Mycosis Immunodiagnosis—Immunology Section, Adolfo Lutz Institute, São Paulo, SP, BrazilRECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, BrazilInnovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, BrazilABSTRACT Brazil and many other Latin American countries are areas of endemicity for different neglected diseases, and the fungal infection paracoccidioidomycosis (PCM) is one of them. Among the clinical manifestations, pneumopathy associated with skin and mucosal lesions is the most frequent. PCM definitive diagnosis depends on yeast microscopic visualization and immunological tests, but both present ambiguous results and difficulty in differentiating PCM from other fungal infections. This research has employed metabolomics analysis through high-resolution mass spectrometry to identify PCM biomarkers in serum samples in order to improve diagnosis for this debilitating disease. To upgrade the biomarker selection, machine learning approaches, using Random Forest classifiers, were combined with metabolomics data analysis. The proposed combination of these two analytical methods resulted in the identification of a set of 19 PCM biomarkers that show accuracy of 97.1%, specificity of 100%, and sensitivity of 94.1%. The obtained results are promising and present great potential to improve PCM definitive diagnosis and adequate pharmacological treatment, reducing the incidence of PCM sequelae and resulting in a better quality of life. IMPORTANCE Paracoccidioidomycosis (PCM) is a fungal infection typically found in Latin American countries, especially in Brazil. The identification of this disease is based on techniques that may fail sometimes. Intending to improve PCM detection in patient samples, this study used the combination of two of the newest technologies, artificial intelligence and metabolomics. This combination allowed PCM detection, independently of disease form, through identification of a set of molecules present in patients’ blood. The great difference in this research was the ability to detect disease with better confidence than the routine methods employed today. Another important point is that among the molecules, it was possible to identify some indicators of contamination and other infection that might worsen patients’ condition. Thus, the present work shows a great potential to improve PCM diagnosis and even disease management, considering the possibility to identify concomitant harmful factors.https://journals.asm.org/doi/10.1128/mSystems.00258-20artificial intelligencediagnosismetabolomicsparacoccidioidomycosis |
| spellingShingle | Estela de Oliveira Lima Luiz Claudio Navarro Karen Noda Morishita Camila Mika Kamikawa Rafael Gustavo Martins Rodrigues Mohamed Ziad Dabaja Diogo Noin de Oliveira Jeany Delafiori Flávia Luísa Dias-Audibert Marta da Silva Ribeiro Adriana Pardini Vicentini Anderson Rocha Rodrigo Ramos Catharino Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses mSystems artificial intelligence diagnosis metabolomics paracoccidioidomycosis |
| title | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| title_full | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| title_fullStr | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| title_full_unstemmed | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| title_short | Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses |
| title_sort | metabolomics and machine learning approaches combined in pursuit for more accurate paracoccidioidomycosis diagnoses |
| topic | artificial intelligence diagnosis metabolomics paracoccidioidomycosis |
| url | https://journals.asm.org/doi/10.1128/mSystems.00258-20 |
| work_keys_str_mv | AT esteladeoliveiralima metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT luizclaudionavarro metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT karennodamorishita metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT camilamikakamikawa metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT rafaelgustavomartinsrodrigues metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT mohamedziaddabaja metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT diogonoindeoliveira metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT jeanydelafiori metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT flavialuisadiasaudibert metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT martadasilvaribeiro metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT adrianapardinivicentini metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT andersonrocha metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses AT rodrigoramoscatharino metabolomicsandmachinelearningapproachescombinedinpursuitformoreaccurateparacoccidioidomycosisdiagnoses |