A drug repositioning algorithm based on a deep autoencoder and adaptive fusion

Topic: Genetics and APOE

In this study, a drug repositioning algorithm based on a deep autoencoder and adaptive fusion was proposed to mitigate the problems of decreased precision and low-efficiency multisource data fusion caused by data sparseness. Specifically, a drug is repositioned by fusing drug-disease associations, drug target proteins, drug chemical structures and drug side effects. First, drug feature data integrated by drug target proteins and chemical structures were processed with dimension reduction via a deep autoencoder to characterize feature representations more densely and abstractly. Then, disease similarity was computed using drug-disease association data, while drug similarity was calculated with drug feature and drug-side effect data. Predictions of drug-disease associations were also calculated using a top-k neighbor method that is commonly used in predictive drug repositioning studies. Finally, a predicted matrix for drug-disease associations was acquired after fusing a wide variety of data via adaptive fusion. Based on experimental results, the proposed algorithm achieves a higher precision and recall rate than the DRCFFS, SLAMS and BADR algorithms with the same dataset. The proposed algorithm contributes to investigating the novel uses of drugs, as shown in a case study of Alzheimer's disease. Therefore, the proposed algorithm can provide an auxiliary effect for clinical trials of drug repositioning.

Key findings

• In this study, a drug repositioning algorithm based on a deep autoencoder and adaptive fusion was proposed to mitigate the problems of decreased precision and low-efficiency multisource data fusion caused by data sparseness.
• Specifically, a drug is repositioned by fusing drug-disease associations, drug target proteins, drug chemical structures and drug side effects.
• First, drug feature data integrated by drug target proteins and chemical structures were processed with dimension reduction via a deep autoencoder to characterize feature representations more densely and abstractly.
• Then, disease similarity was computed using drug-disease association data, while drug similarity was calculated with drug feature and drug-side effect data.
• Predictions of drug-disease associations were also calculated using a top-k neighbor method that is commonly used in predictive drug repositioning studies.

New to this subject? Start with our plain-English guide: Treatments →

Study details

• Evidence strengthLow

Read the original

• DOI: 10.1186/s12859-021-04406-y
• PubMed: 34717542
• Original source →

Free copy unknown: no free-copy check has an answer for this record yet. That does not mean it is paywalled.

@article{chen2021-34717542,
  author  = {Chen, Peng and Bao, Tianjiazhi and Yu, Xiaosheng and Liu, Zhongtu},
  title   = {{A drug repositioning algorithm based on a deep autoencoder and adaptive fusion}},
  journal = {BMC bioinformatics},
  year    = {2021},
  doi     = {10.1186/s12859-021-04406-y},
  pmid    = {34717542},
  url     = {https://doi.org/10.1186/s12859-021-04406-y}
}

Related studies in Drug development

• deepDR: a network-based deep learning approach to in silico drug repositioning Bioinformatics (Oxford, England) · 2019-12-01 · usefulness score 38/100
• Drug repositioning based on the heterogeneous information fusion graph convolutional network Briefings in bioinformatics · 2021-11-05 · usefulness score 41/100
• Drug repositioning for diabetes based on 'omics' data mining PloS one · 2015-05-06 · usefulness score 46/100
• A Proteotranscriptomic-Based Computational Drug-Repositioning Method for Alzheimer's Disease Frontiers in pharmacology · 2020-01-29 · usefulness score 39/100
• Drug Repositioning for Alzheimer's Disease Based on Systematic 'omics' Data Mining PloS one · 2016-12-22 · usefulness score 38/100
• Drug repositioning for Alzheimer's disease Nature reviews. Drug discovery · 2012-11-01 · usefulness score 64/100

Similar studies

• Generating new drug repurposing hypotheses using disease-specific hypergraphs 2024 · Drug development
• Integrating Comorbidity Knowledge for Alzheimer's Disease Drug Repurposing using Multi-task Graph Neural Network 2023 · Drug development
• Recent advances in drug repurposing using machine learning 2021 · Drug development
• Drug repositioning in drug discovery of T2DM and repositioning potential of antidiabetic agents 2022 · Drug development
• Interpretable deep learning translation of GWAS and multi-omics findings to identify pathobiology and drug repurposing in Alzheimer's disease 2022 · Genetics
• Machine learning identifies candidates for drug repurposing in Alzheimer's disease 2021 · Drug development

More on Drug development

• A review that covers this ground Drug Repositioning: A Monetary Stratagem to Discover a New Application of Drugs Current drug discovery technologies · 2024 · usefulness score 43/100
• Newest in this subject The metabolic-brain axis: GLP-1 signaling, insulin resistance, and obesity pharmacotherapy in neurodegeneration Metabolism: clinical and experimental · 2026-10-30 · Peer-reviewed · usefulness score 45/100
• Newest in this subject Effect of Metformin on tau pathology and proteostasis in cellular and a Drosophila model of Tauopathy Research Square · 2026-10-29 · Preprint — not yet peer-reviewed · usefulness score 16/100

See all studies in Drug development →