BIB | Molormer: A Lightweight Self-Attention-Based Method Focused on Spatial Structure of Molecular Graph for Drug-Drug Interactions Prediction
This repository contains the source code of Molormer (https://doi.org/10.1093/bib/bbac296).
Setup
A conda environment can be created with
conda create --name molormer python=3.7
conda activate molegent
conda update -n base conda
conda env create -f environment.yaml
Training
To train of the models run:
python train.py
Predicting
To prediction of the models run:
python predict.py
Cite:
Xudong Zhang, Gan Wang, Xiangyu Meng, Shuang Wang, Ying Zhang, Alfonso Rodriguez-Paton, Jianmin Wang, Xun Wang, Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug–drug interactions prediction, Briefings in Bioinformatics, 2022;, bbac296, https://doi.org/10.1093/bib/bbac296