Multi-view Contrastive Learning Hypergraph Neural Network for Drug-Microbe-Disease Association Prediction

Authors: Luotao Liu, Feng Huang, Xuan Liu, Zhankun Xiong, Menglu Li, Congzhi Song, Wen Zhang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that MCHNN achieves satisfactory performance in DMD association prediction and, more importantly, demonstrate the effectiveness of our devised the multi-view CL on the sparse DMD hypergraph.
Researcher Affiliation Academia College of Informatics, Huazhong Agricultural University, Wuhan 430070, China {luotaoliu, fhuang233, lx666, xiongzk, mengluli, song cz }@webmail.hzau.edu.cn, zhangwen@mail.hzau.edu.cn
Pseudocode No The paper describes the model architecture and methods in text and using mathematical equations, but does not include any clearly labeled 'Pseudocode' or 'Algorithm' blocks.
Open Source Code Yes More detailed settings, source code, data set, and additional results of MCHNN are presented in Supplementary materials1. 1https://github.com/Liuluotao/MCHNN
Open Datasets Yes The drugmicrobe associations are collected from MDAD [Sun et al., 2018], a Biofilm [Rajput et al., 2018], and Drug Virus [Andersen et al., 2020], and the microbe-disease associations are obtained from HMDAD [Ma et al., 2017], Disbiome [Janssens et al., 2018], gut MDisorder [Cheng et al., 2020], and Peryton [Skoufos et al., 2021].
Dataset Splits Yes We randomly split the dataset into a 90% cross-validation (CV) set and a 10% independent test set. On the CV set, the 5-fold CV is implemented.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running experiments were found in the paper.
Software Dependencies No The paper mentions software components like 'Deep Chem package' and 'GIN' but does not provide specific version numbers for any software dependencies required to replicate the experiments.
Experiment Setup Yes The number of GIN layer k for drug node attributes and HGNN layer l for hypergraph encoding are both set to 3. In DMD association prediction, the scoring function is a 3-layer MLP with Dropout. We fix α to 0.8 as they produced the best performance in hyper-parameter optimization. Moreover, we employ Adam with a learning rate of 0.005 to optimize the model and adopt early stopping to control the training epochs based on validation loss.