Cancer is a health challenge for modern societies, as it affects millions of people every year and brings a heavy burden in terms of treatment costs, the population’s quality of life and survivability. For oncologists, the treatment approach is also surrounded by uncertainties due to the unknown phenomena related to patients’ response, and precision medicine plays a significant role in defining the best therapeutics. This paper proposes to leverage network science and machine learning techniques in an integrated approach to provide a wide spectrum of information—from qualitative networked analysis to treatment response predictions—in order to assist practitioners’ decision for a neoadjuvant-based scheme when treating gastric cancer patients. As a caveat, the framework also tackles the challenges of implementation in a real case scenario by using data from the oncology clinical practice in A.C. Camargo Cancer Center, a leading institution for cancer treatment in Brazil. Put in context, this work is part of an undergoing project towards a comprehensive AI-based decision support system for neoadjuvant treatment applied to gastric cancer.