ML-BCR - Machine Learning - Biomarkers of Cardiovascular Response

Major Depressive Disorder (MDD) is a complex and multifactorial psychiatric condition. In more severe cases, patients with MDD may develop suicidal behavior, a complex phenomenon influenced by biological, psychological, social, and environmental factors, and it is the fourth leading cause of death among young people. The frequent association between psychiatric disorders, such as MDD, and suicidal behavior highlights the urgency of understanding the underlying factors of this condition. Studies suggest that epigenetic mechanisms, such as microRNAs, histone modifications, and circular RNAs, may be crucial for understanding suicidal behavior, helping to clarify the relationship between these phenomena and identify new biomarkers. Therefore, our objective is to investigate the impact of molecular mechanisms on susceptibility to MDD and suicide using advanced machine learning techniques to identify potential biomarkers, followed by validation in a cohort of Brazilian and Canadian patients with MDD and suicide attempts. For this, we rely on a Brazil-Canada collaboration that ensures access to data for computational analysis and the infrastructure needed for the experimental validation of potential molecular markers identified. The methodology is divided into two main approaches: (1) Multi-omic data screening from already sequenced data for the application of machine learning techniques and identification of potential molecular markers associated with the conditions of interest, and (2) Experimental validation of molecular markers identified by the literature and in the screening phase using biochemical and molecular biology techniques. We aim to provide a deeper understanding of the molecular mechanisms underlying the interaction between MDD and suicide and the commonalities between these phenomena. The identification and experimental validation of biomarkers for a better understanding of the pathophysiology of MDD and susceptibility to suicidal behavior will assist in the development of more effective therapeutic interventions, improving patient outcomes.