DeepDrug is a deep learning framework, using residual graph convolutional networks (RGCNs) and convolutional networks (CNNs) to learn the comprehensive structural and sequential representations of drugs and proteins in order to boost the drug-drug interactions(DDIs) and drug-target interactions(DTIs) prediction accuracy. DeepDrug is available at https://github.com/wanwenzeng/deepdrug.
This repository includes processed Datasets for DeepDrug.
Each dataset folder is constructed by :
Drug/ : drug SMILEs (drug.csv) and processed graph featrues (processed/data.pt).
Target/ (only for DTI task) : target sequences (target.csv) and processed graph featrues (processed/data.pt).
Binary_1vsX/ or mutliclass/ or regression/ : DDI or DTI pairs (entry_pairs.csv), corresponding labels (pair_labels.csv) and 5-fold cross validation used in the research (cv_5fold.pkl).
Funding
National Key Research and Development Program of China (Nos. 2018YFC0910404 and 2020YFA0712402)
National Natural Science Foundation of China (Nos. 61873141, 61721003, 62003178)