IHRW: An Improved Hypergraph Random Walk Model for Predicting Three-Drug Therapy
Wang, Q.; Yan, G.
Show abstract
Drug combination therapy is a well-established concept in the treatment of complex diseases due to its fewer side effects, lower toxicity, and better efficacy. However, it is challenging to identify efficacious drug combinations from many drug candidates. Computational models could greatly reduce the cost, but most models did not use data for more than two-drug combinations and could not predict three-drug therapy. However, three-drug combinations account for about 21% of the known combinations, which is a very important type of treatment. Here, we utilized higher-order information and developed an improved hypergraph random walk model (IHRW) for three-drug therapy prediction. This is the first method to explore the combination of three drugs. As a result, the case studies of breast cancer, lung cancer, and colon cancer showed that IHRW had a powerful ability to predict potential efficacious three-drug combinations, which provides new prospects for complex disease treatment. The code of IHRW is freely available at https://github.com/wangqi27/IHRW.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Predicting Adverse Drug Effects: A Heterogeneous Graph Convolution Network with a Multi-layer Perceptron Approach 97%
- Improving prediction of drug-target interactions based on fusing multiple features with data balancing and feature selection techniques 96%
- Targeting Oncogenic Mutations in Colorectal Cancer using Cryptotanshinone 96%
Similar papers in this journal
- MeSHHeading2vec: A new method for representing MeSH headings as feature vectors based on graph embedding algorithm 98%
- Predicting drug-target interactions using multi-label learning with community detection method (DTI-MLCD) 96%
- A geometric deep learning framework for drug repositioning over heterogeneous information networks 96%
Similar papers in this journal
- A new machine learning method for cancer mutation analysis 96%
- TranSynergy: Mechanism-Driven Interpretable Deep Neural Network for the Synergistic Prediction and Pathway Deconvolution of Drug Combinations 96%
- GCNCDA: A New Method for Predicting CircRNA-Disease Associations Based on Graph Convolutional Network Algorithm 95%
Similar papers in this journal
- Combining Multi-Dimensional Molecular Fingerprints to Predict hERG Cardiotoxicity of Compounds 95%
- AE-LGBM: Sequence-Based Novel Approach To Detect Interacting Protein Pairs via Ensemble of Autoencoder and LightGBM. 94%
- Decoding Clinical Biomarker Space of COVID-19: Exploring Matrix Factorization-based Feature Selection Methods 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.