This project is a part of the bioinformatics class at Chulalongkorn Univerisity
Binding affinity can indicate the effectiveness of the specific medication and the specific protein. However, this value is influenced by many intermolucular interaction. The problem of this project is to find a binding affinity between protein and ligand. We proporsed a novel way to processing the input from three dimentional image to two dimentional image and implemeented a simple deep convolutional model to proof its effectiveness.
The result shows that the model can reach the state-of-the-art performance at that time.
The preprocessing method can be found at https://github.com/Sav-eng/protein-ligand-term-project/blob/main/Generate_features.ipynb.
The code of the model can be found at https://github.com/Sav-eng/protein-ligand-term-project/blob/main/Model.ipynb.