Abstract
Drug repositioning is used to find new uses for existing drugs, effectively shortening the drug research and development cycle and reducing costs and risks. A new model of drug repositioning based on ensemble learning is proposed. This work develops a novel computational drug repositioning approach called CMAF to discover potential drug-disease associations. First, for new drugs and diseases or unknown drug-disease pairs, based on their known neighbor information, an association probability can be obtained by implementing the weighted K nearest known neighbors (WKNKN) method and improving the drug-disease association information. Then, a new drug similarity network and new disease similarity network can be constructed. Three prediction models are applied and ensembled to enable the final association of drug-disease pairs based on improved drug-disease association information and the constructed similarity network. The experimental results demonstrate that the developed approach outperforms recent state-of-the-art prediction models. Case studies further confirm the predictive ability of the proposed method. Our proposed method can effectively improve the prediction results.
Highlights
Traditional drug discovery is a high-risk, high-investment, and long-term process (Li et al, 2015)
We develop a new drug repositioning model, CMAF, which integrates three methods to obtain the final prediction result
The drug similarity is computed by the Chemical Development Kit (CDK) (Steinbeck et al, 2006) in terms of SMILES (Weininger, 1988) chemical structures, and the similarity between drug pairs is denoted as the Tanimoto score (Tanimoto, 1958) of their 2D chemical fingerprints
Summary
Traditional drug discovery is a high-risk, high-investment, and long-term process (Li et al, 2015). Many computational drug repositioning techniques, such as machine learning-based models, have been used to identify potential drug-disease interactions (Li et al, 2015). The network-based method discovered potential drug–disease associations by propagating information in a heterogeneous biological network containing some information about diseases, drugs, or targets (Luo et al, 2018). The matrix factorization-based method has been successfully applied to biological association prediction, such as lncRNA-disease (Fu et al, 2017; Lan et al, 2020), drug-target (Liu et al, 2016b; Shi et al, 2018), and drug-disease (Zhang et al, 2018). We develop a new drug repositioning model, CMAF, which integrates three methods (matrix factorizationbased, label propagation-based, and network consistency projection-based methods) to obtain the final prediction result. The experimental results demonstrate that CMAF obtained better results than the other four recent models in predicting potential drug-disease associations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
