KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction

Authors: Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma, Xiangxiang Zeng

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have implemented our method and conducted experiments based on several widely-used datasets. Empirical results show that KGNN outperforms the classic and state-of-the-art models.
Researcher Affiliation Academia 1College of Information Science and Engineering, Hunan University 2College of Computer Science, Chongqing University
Pseudocode Yes Algorithm 1 shows the pseudo-codes of applying KGNN for topological neighborhood representation between given drug pairs.
Open Source Code Yes We evaluate our proposed KGNN1 by using two datasets. 1https://github.com/xzenglab/KGNN
Open Datasets Yes We evaluate our proposed KGNN1 by using two datasets. (1) Drug Bank: we parse the verified DDIs of the provided profile from Drug Bank (V5.1.4)... (2) KEGG-drug: we parse the sources from KEGG and map it to Drug Bank identifiers (IDs)...
Dataset Splits Yes For both datasets, we randomly divide all approved DDIs as positive samples into training, validation and testing sets in a 8/1/1 ratio
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as CPU or GPU models, or cloud computing instances.
Software Dependencies No The paper mentions tools like 'Bio2RDF' and algorithms like 'Adam algorithm' but does not specify version numbers for general software dependencies such as programming languages, libraries (e.g., PyTorch, TensorFlow), or operating systems.
Experiment Setup Yes Parameter Setting Batch size 4096 Dimension 32 Learning rate 1e-2 Number of depth 2 L2 weight 1e-7 Neighborhood size 16