Graph deep learning paradigm integrating biomedical networks for phenotypic drug discovery and target prioritization.

The source data and code of the paper "Graph deep learning paradigm integrating biomedical networks for phenotypic drug discovery and target prioritization". ## KGDRP: Interpretable drug response prediction with biomedical networks accelerates phenotypic drug discovery and drug target prioritization We present a knowledge graph-based multimodal data fusion framework for predicting drug responses, named KGDRP. This framework seamlessly integrates multiple omics data, including network data containing biological system information, gene expression data coupled with phenotypic information, and sequence data incorporating chemical molecular structures, within a heterogeneous graph structure. ## System Requirements The source code developed in Python 3.6.13 using PyTorch 1.10.1. The required python dependencies are given below. KGDRP is supported for any standard computer and operating system with enough RAM to run. There is no additional non-standard hardware requirements. ``` torch = 1.10.1 dgl = 0.8.2 numpy = 1.19.5 scikit-learn = 0.24.2 pandas = 1.1.5 tqdm = 4.64.0 scipy = 1.5.4 optuna = 2.10.1 ``` ## Instructions for Use ##### Knowledge graph and drug response data used in this work provided in the ./data/ folder + Knowledge graph: dppc_kg.csv + CV folds of drug response data: + ./data/cv_mix/ + ./data/cv_cell/ + ./data/cv_drug/ + ./data/cv_both/ + Drug ID map file: cid_infor.csv + Feature of cell-lines: rna_input.csv + Edges of gene-cell-lines for KG construction: rna_triples.csv + Feature of drugs: bdki_db_gdsc_fp.csv + Negative samples of protein-pathway: pro_path_neg_sp.csv + Negative samples of protein-pathway: neg_dpi_df_t10.csv #### Hyper-parameter The hyper-parameter script is located in the ./src/ folder. **Noted:** To implement heterogeneous message passing, replace the hetero.py file located at ./anaconda3/envs/env_name/lib/python3.6/site-packages/dgl/nn/pytorch/hetero.py with the version provided in the ./src/ folder. The script is compatible with both CPU and GPU architectures. A single run of the script typically requires approximately 30 minutes to complete. ## License [MIT](https://choosealicense.com/licenses/mit/)