# DTI

**Repository Path**: ntdai/dti

## Basic Information

- **Project Name**: DTI
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-01-21
- **Last Updated**: 2026-01-21

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# CBKG-DTI
This repository is the implementation of CBKG-DTI:
CBKG-DTI: multi-level knowledge distillation and biomedical knowledge graph for drug-target interaction prediction

CBKG-DTI consists of three components: HAKE-based teacher model, HGAT-based student model, and multi-level knowledge distillation.

1. Desritory is organised as follows:
dataset : biomedical knowledge graph (MAN-KG), training, validing and testing data in the 5-fold cv.
model:

2. Requirements
The code has been tested running under Python 3.6, with the following packages installed (along with their dependencies):
pytorch ==1.10.0
cuda == 1.0.2
dgl ==0.7.1
dgllife == 0.3.2
scikit-learn == 0.24.1
numpy == 1.23.5
tokenizers == 0.12.1

3 Usage
 use PyCharm to run main.py