BIOMARK-AI
Application of metabolomics and machine learning in the prediction of biomarkers for Hashimoto’s thyroiditis and periodontitis (IP-UNIST-34)
Project title: Application of metabolomics and machine learning in the prediction of biomarkers for Hashimoto’s thyroiditis and periodontitis (IP-UNIST-34)
Project applicant: University of Split, School of Medicine
Project value: 238.041,20 EUR
Project duration: 01/10/2025 - 30/09/2029
Project leader: Prof. Dr. Sc Vesna Boraska Perica (vboraska@mefst.hr)
Project description:
Metabolomics enables a comprehensive insight into biochemical changes associated with physiological and pathological states of the organism. Within this project, the metabolome of patients with Hashimoto’s thyroiditis (HT) and periodontitis (PD), two chronic inflammatory diseases that share a number of immunological and environmental risk factors, will be analysed,. The aim is to identify metabolic biomarkers characteristics of each disease individually, as well as shared metabolites that may indicate related pathophysiological mechanisms.
Metabolites will be quantified using an advanced platform capable of measuring 5,400 metabolites. Statistical methods will be applied to identify metabolites with significant differences in expression between healthy and affected individuals, as well as those associated with clinical phenotypes. By applying machine learning algorithms, particularly the Boruta feature selection method, predictive models will be developed to identify key metabolites associated with HT and PD and their progression.
The project brings together scientists of different profiles and encourages collaboration among University constituents, thereby ensuring knowledge transfer and the development of competencies. Special emphasis is placed on the use of advanced research infrastructure and digital technologies, enabling the processing and analysis of large datasets. Expected results include the publication of scientific papers, the development of new methodological approaches and the strengthening of digital capacities. The project also foresees sustainability of results through open access to data and continued use of developed resources after the completion of the project.
Project objectives:
Work package 1 (Objective 1): Identification of metabolic markers for HT
Work package 2 (Objective 2): Identification of metabolic markers for PD
Work package 3 (Objective 3): Integrated approach to determine metabolites common to HT and PD
Work package 4 (Objective 4): Application of machine learning in determining predictive markers for the presence and severity of HT and PD
Collaborators:
HT group:
Prof. Dr. Sc. BORASKA PERICA VESNA
Dr. Sc. KALIČANIN DEAN
Prof. Dr. Sc. DRMIĆ HOFMAN IRENA
Prof. Dr. Sc. MARKOTIĆ ANITA
Asst. Prof. Dr. Sc. MASTELIĆ ANGELA
Asst. Prof.. dr. Sc. TANDARA LEIDA
Asst. Prof. Dr. Sc. BARIĆ ŽIŽIĆ ANA
Prof. Dr. Sc. RADMAN MAJA
Assoc. Prof. Dr. Sc. BRATANIĆ ANDRE
Assoc. Prof. Dr. Sc. BONACIN DAMIR
Asst. Prof. Dr. Sc. ŠUNDOV DINKA
Asst. Prof. Dr. Sc. ZEKIĆ TOMAŠ SANDRA
Assoc. Prof. Dr. Sc. FRANIĆ TOMISLAV
Assoc. Prof. Dr. Sc.. BOBAN NATAŠA
Asst. Prof.. Dr. Sc. BAČIĆ BORIS
Asst. Prof.. Dr. Sc. MEŠTROVIĆ ZORAN
Assoc. Prof. Dr. Sc.LEDINA DRAGAN
Assoc. Prof. Dr. Sc. BOBAN MARIJO
Assoc. Prof. Dr. Sc. PETRIĆ MIŠE BRANKA
Assoc. Prof. Dr. Sc. LOZIĆ BERNARDA
PD group:
Asst. Prof.. Dr. Sc. ROGULJIĆ MARIJA
Assoc. Prof. Dr. Sc. KERO DARKO
Dr. Sc. DUPLANČIĆ ROKO
Assoc. Prof. Dr. Sc. TADIN ANTONIJA
Assoc. Prof. Dr. Sc. REŽIĆ MUŽINIĆ NIKOLINA
Dr. Sc. LOZIĆ MIRELA
Prof. dr. sc. GOIĆ BARIŠIĆ IVANA
Asst. Prof. Dr. Sc. NOVAK ANITA
Assoc. Prof. Dr. Sc. ŠTULA IVANA
Assoc. Prof. Dr. Sc. LOVRIĆ KOJUNDŽIĆ SANJA
“Funded by the European Union - NextGenerationEU.”
“The views and opinions expressed are solely those of the author and do not necessarily reflect the official positions of the European Union or the European Commission. Neither the European Union nor the European Commission can be held responsible for them.”
Print page
