# DBG-DDA

**Repository Path**: Tomhappy/DBG-DDA

## Basic Information

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

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-09-19
- **Last Updated**: 2026-09-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

Code for paper: DBG-DDA: a dual-branch graph learning method for drug-disease associations prediction.

This repository provides a clean, research‑ready implementation of DBG‑DDA, a dual‑branch graph representation learning framework for drug–disease association (DDA) prediction. The pipeline first learns low‑level structural features through a Graph‑Attention‑Transformer (GATT) module and high‑level semantic features through a meta‑path aggregation module (TAHIN), then fuses them and uses an Extreme Learning Machine (ELM) classifier for final prediction.