This repository contains source code and datasets for "PresRecRF: Herbal prescription recommendation via the representation fusion of large TCM semantics and molecular knowledge".

In this study, we proposed a novel herbal Prescription Recommendation model with the Representation Fusion of large TCM semantics and molecular knowledge (termed PresRecRF, See graphical abstract figure below). The entire process of the proposed PresRecRF model closely mirrors the actual diagnosis and treatment procedures carried out by doctors, which are better applied in real clinical scenarios.

Fig1. Framework of PresRecRF. The model integrates large-scale TCM semantics and molecular knowledge for enhanced representation. PresRecRF comprises three key modules, namely knowledge representation learning, representation fusion, and prescription recommendation with precise herbal dosages. This approach seeks to enhance patient characterization and achieve precise herbal prescription recommendations.

$ conda create -n presrecrf_env python=3.9
$ conda activate presrecrf_env
$ pip install -r requirements.txt

The relevant data required by the model are uniformly placed in the "data" folder. This folder contains the following data files:

The python script file of the model is shown in this project, including the following files:

Yang K, Dong X, Zhang S, Yu H, Zhong L, Zhang L, Zhao H, Hou Y, Song X, Zhou X. PresRecRF: Herbal prescription recommendation via the representation fusion of large TCM semantics and molecular knowledge. Phytomedicine. 2024 Oct 1; 135: 156116.

@article{yang2024presrecrf,
  title={PresRecRF: Herbal prescription recommendation via the representation fusion of large TCM semantics and molecular knowledge},
  author={Yang, Kuo and Dong, Xin and Zhang, Shuhan and Yu, Haibin and Zhong, Liqun and Zhang, Lei and Zhao, He and Hou, Yutong and Song, Xinpeng and Zhou, Xuezhong},
  journal={Phytomedicine},
  volume={135},
  pages={156116},
  year={2024},
  publisher={Elsevier}
}