Mapping Thrombosis Serum Markers by <sup>1</sup>H-NMR Allied with Machine Learning Tools
Lucas G. Martins,
Bruna M. Manzini,
Silmara Montalvão,
Millene A. Honorato,
Marina P. Colella,
Gabriela G. Y. Hayakawa,
Erich V. de Paula,
Fernanda A. Orsi,
Erik S. Braga,
Nataša Avramović,
Folurunsho Bright Omage,
Ljubica Tasic,
Joyce M. Annichino-Bizzacchi
Affiliations
Lucas G. Martins
Laboratory of Biological Chemistry, Department of Organic Chemistry, Institute of Chemistry, Universidade Estadual de Campinas, Campinas 13083-862, SP, Brazil
Bruna M. Manzini
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Silmara Montalvão
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Millene A. Honorato
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Marina P. Colella
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Gabriela G. Y. Hayakawa
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Erich V. de Paula
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Fernanda A. Orsi
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Erik S. Braga
Laboratory of Biological Chemistry, Department of Organic Chemistry, Institute of Chemistry, Universidade Estadual de Campinas, Campinas 13083-862, SP, Brazil
Nataša Avramović
University of Belgrade, Faculty of Medicine, Institute of Medical Chemistry, 11000 Belgrade, Serbia
Folurunsho Bright Omage
Laboratory of Biological Chemistry, Department of Organic Chemistry, Institute of Chemistry, Universidade Estadual de Campinas, Campinas 13083-862, SP, Brazil
Ljubica Tasic
Laboratory of Biological Chemistry, Department of Organic Chemistry, Institute of Chemistry, Universidade Estadual de Campinas, Campinas 13083-862, SP, Brazil
Joyce M. Annichino-Bizzacchi
Laboratory of Hemostasis, Hemocentro-Unicamp, Universidade Estadual de Campinas, Campinas 13083-878, SP, Brazil
Machine learning and artificial intelligence tools were used to investigate the discriminatory potential of blood serum metabolites for thromboembolism and antiphospholipid syndrome (APS). 1H-NMR-based metabonomics data of the serum samples of patients with arterial or venous thromboembolism (VTE) without APS (n = 32), thrombotic primary APS patients (APS, n = 32), and healthy controls (HCs) (n = 32) were investigated. Unique metabolic profiles between VTE and HCs, APS and HCs, and between VTE and triple-positive APS groups were indicative of the significant alterations in the metabolic pathways of glycolysis, the TCA cycle, lipid metabolism, and branched-chain amino acid (BCAA) metabolism, and pointed to the complex pathogenesis mechanisms of APS and VTE. Histidine, 3-hydroxybutyrate, and threonine were shown to be the top three metabolites with the most substantial impact on model predictions, suggesting that these metabolites play a pivotal role in distinguishing among APS, VTE, and HCs. These metabolites might be potential biomarkers to differentiate APS and VTE patients.
