Psychotic disorders, like Schizophrenia and Bipolar disorder, affect a significant portion of the population and cause severe disability. They impose a heavy burden on patients, families, and society due to their early onset, chronicity, and associated costs. Efforts to identify reliable clinical predictors for these disorders are crucial for prevention, diagnosis, therapy, and monitoring. Unfortunately, existing diagnostic methods rely on clinical interviews and the appearance of symptoms over time. To address this, this project proposes investigating the pathophysiology and neuropathology of these disorders, focusing on facial biomarkers as potential indicators of brain dysmorphogenesis. By combining Phenomic, Genomic, and Machine Learning approaches, researchers aim to understand the genetic and neuroanatomical factors related to facial dysmorphologies in a large dataset of patients with Schizophrenia and Bipolar Disorder, as well as healthy individuals. The goal is to develop a multimodal biomarker that combines facial, brain, and genetic information to enhance diagnostic accuracy. Ultimately, the aim is to create a low-cost, non-invasive diagnostic tool called BEGiN based on facial biomarkers, which can improve early diagnosis of psychotic disorders.