Developments and adoptions of machine learning in bioinformatics and medicine have led to increasingly complex and accurate models. Machine learning models, while becoming increasingly accurate, often suffer from a lack of transparency and interpretability, hindering the adoption of such models in fields such as bioinformatics and medicine. The field of Explainable AI (XAI) addresses these challenges by aiming to develop methods and techniques to make AI models interpretable, providing understandable explanations of their predictions. The present research aims to develop advanced XAI methods for the interpretation of machine learning models specifically designed for bioinformatics and medicine, in order to provide clear, understandable and reliable explanations of predictions.