TPgraph (GConvNet)

Drug–target interaction prediction

Identifying the interactions between drugs and target proteins is a key step in drug discovery. This not only aids to understand the disease mechanism, but also helps to identify unexpected therapeutic activity or adverse side effects of drugs. Hence, drug-target interaction prediction becomes an essential tool in the field of drug repurposing.

RUN:

drug.py
protein.py
main.py

Place all PDB files (3D protein structures) in the DBP folder before running

The main core: GConvNet

Install with pip:

pip install GConvNet

GConvNet is a PyTorch module for graph convolution using triplet-based edge structures and dynamic node filtering. It enables higher-order neighborhood modeling via (3×1) convolution over node triplets, and selectively retains important nodes based on degree centrality.