Acute Lymphoblastic Leukemias are the type of cancer with the highest incidence in children. Although 80% of patients are cured with current therapeutic approaches, a fraction of patients still relapse and die because of the disease. Standard management of the disease requires a risk classification in three groups depending on several factors and a therapy that consists of three stages: induction, consolidation and maintenance, each with specific combinations of different drugs. We intend to use mathematical algorithms to improve patient classification, identify relapse risk and design personalized treatments by better using the large amount of data available.