Drug Response Analysis Interface Powered by Deep Learning Models

Cancer is a complex disease that affects millions of people worldwide. Despite significant advances in cancer research, there is still a need for more effective treatments. One promising approach is to use drug combinations that target multiple pathways or mechanisms of cancer growth. However, identifying effective drug combinations is challenging, as different drugs may interact in ways that can be difficult to predict. Our proposed system intends to help researchers by creating an interface of research expansion. The system performs feature selection using recommended algorithms, and a variety of deep learning models are defined for the specific purpose of returning predictions of drug synergies alongside evaluation of the models in use. The results are stored in a JSON file that can be accessed by the intended medical researcher for additional study. The results shown in the project are purely experimental and are not to be used as reference by medical practitioners during their diagnosis of patients and their recommendations, and the project is purely for research only.