دورية أكاديمية
أعرض في EDS

Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses.

التفاصيل البيبلوغرافية
العنوان: Metabolomics and Machine Learning Approaches Combined in Pursuit for More Accurate Paracoccidioidomycosis Diagnoses.
المؤلفون: Lima EO; Department of Internal Medicine, Botucatu Medical School, São Paulo State University, Botucatu, SP, Brazil.; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Navarro LC; RECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, Brazil., Morishita KN; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Kamikawa CM; Laboratory of Mycosis Immunodiagnosis-Immunology Section, Adolfo Lutz Institute, São Paulo, SP, Brazil., Rodrigues RGM; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Dabaja MZ; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., de Oliveira DN; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Delafiori J; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Dias-Audibert FL; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Ribeiro MDS; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil., Vicentini AP; Laboratory of Mycosis Immunodiagnosis-Immunology Section, Adolfo Lutz Institute, São Paulo, SP, Brazil., Rocha A; RECOD Laboratory, Institute of Computing, University of Campinas, Campinas, SP, Brazil anderson.rocha@ic.unicamp.br rrc@unicamp.br., Catharino RR; Innovare Biomarkers Laboratory, School of Pharmaceutical Sciences, University of Campinas, Campinas, SP, Brazil anderson.rocha@ic.unicamp.br rrc@unicamp.br.
المصدر: MSystems [mSystems] 2020 Jun 30; Vol. 5 (3). Date of Electronic Publication: 2020 Jun 30.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: American Society for Microbiology Country of Publication: United States NLM ID: 101680636 Publication Model: Electronic Cited Medium: Print ISSN: 2379-5077 (Print) Linking ISSN: 23795077 NLM ISO Abbreviation: mSystems Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: Washington, DC : American Society for Microbiology, [2016]-
مستخلص: 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.
(Copyright © 2020 Lima et al.)
References: Proc Natl Acad Sci U S A. 1985 Nov;82(21):7404-8. (PMID: 3933006)
Virulence. 2017 Oct 3;8(7):1417-1434. (PMID: 28704618)
FASEB J. 2018 Apr;32(4):1880-1890. (PMID: 29196503)
Expert Rev Mol Diagn. 2008 Sep;8(5):617-33. (PMID: 18785810)
J Exp Med. 1993 Dec 1;178(6):2249-54. (PMID: 7504064)
Ann Trop Paediatr. 1998 Sep;18 Suppl:S47-52. (PMID: 9876268)
Nat Rev Mol Cell Biol. 2000 Oct;1(1):31-9. (PMID: 11413487)
Biochemistry. 1999 Jun 1;38(22):7294-306. (PMID: 10353841)
J Fungi (Basel). 2017 Jan 03;3(1):. (PMID: 29371520)
Am J Respir Cell Mol Biol. 2013 Jan;48(1):87-93. (PMID: 23024063)
J Biol Chem. 1999 Oct 22;274(43):30580-8. (PMID: 10521441)
PLoS One. 2015 Sep 11;10(9):e0137619. (PMID: 26360774)
Front Bioeng Biotechnol. 2018 Apr 11;6:31. (PMID: 29696139)
Front Microbiol. 2011 Dec 05;2:239. (PMID: 22164155)
Clin Infect Dis. 2005 Aug 15;41(4):e31-7. (PMID: 16028144)
Annu Rev Biophys Biomol Struct. 2004;33:269-95. (PMID: 15139814)
Trans R Soc Trop Med Hyg. 2011 Aug;105(8):473-8. (PMID: 21684567)
Rev Inst Med Trop Sao Paulo. 2015 Sep;57 Suppl 19:11-20. (PMID: 26465364)
Toxicol Appl Pharmacol. 2002 May 1;180(3):197-204. (PMID: 12009859)
J Med Vet Mycol. 1995 Jul-Aug;33(4):247-51. (PMID: 8531023)
Med Mycol. 2011 Nov;49(8):785-98. (PMID: 21539506)
Open Microbiol J. 2017 Oct 31;11:224-282. (PMID: 29204222)
Microb Drug Resist. 2014 Jun;20(3):199-214. (PMID: 24799078)
Am J Respir Cell Mol Biol. 2008 Jun;38(6):639-46. (PMID: 18192502)
J Venom Anim Toxins Incl Trop Dis. 2017 Feb 15;23:11. (PMID: 28239394)
Cytokine. 2001 Feb 21;13(4):248-52. (PMID: 11237434)
Endocrinol Metab (Seoul). 2016 Mar;31(1):7-16. (PMID: 26676338)
Bull World Health Organ. 1999;77(9):754-66. (PMID: 10534900)
Med Mycol. 2001 Jun;39(3):233-41. (PMID: 11446526)
Clin Vaccine Immunol. 2007 Feb;14(2):150-6. (PMID: 17135452)
Trends Microbiol. 2002 Feb;10(2):80-7. (PMID: 11827809)
J Biol Chem. 1990 Nov 5;265(31):18713-6. (PMID: 2229037)
Front Microbiol. 2017 Nov 29;8:2373. (PMID: 29211063)
Front Cell Infect Microbiol. 2014 Sep 25;4:138. (PMID: 25309884)
mSystems. 2020 Jun 30;5(3):. (PMID: 32606026)
An Bras Dermatol. 2013 Sep-Oct;88(5):700-11. (PMID: 24173174)
Arch Biochem Biophys. 2012 Jan 15;517(2):83-97. (PMID: 22093697)
Front Microbiol. 2017 Oct 10;8:1954. (PMID: 29067015)
Bioinformatics. 2010 May 15;26(10):1340-7. (PMID: 20385727)
J Clin Microbiol. 2005 Aug;43(8):4255-7. (PMID: 16081993)
فهرسة مساهمة: Keywords: artificial intelligence; diagnosis; metabolomics; paracoccidioidomycosis
تواريخ الأحداث: Date Created: 20200702 Latest Revision: 20240329
رمز التحديث: 20240329
مُعرف محوري في PubMed: PMC7329323
DOI: 10.1128/mSystems.00258-20
PMID: 32606026
قاعدة البيانات: MEDLINE
الوصف
تدمد:2379-5077
DOI:10.1128/mSystems.00258-20