CoChat
Sign Up
Cited by 8Computational Drug Discovery MethodsBiomedical Text Mining and OntologiesBioinformatics and Genomic Networks

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

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

Open access
Chen, Peng, Bao, Tianjiazhi, Yu, Xiaosheng, Liu, Zhongtu·2021·BMC Bioinformatics
DOI 10.1186/s12859-021-04406-yPMC PMC8556784
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Drug repositioning has caught the attention of scholars at home and abroad due to its effective reduction of the development cost and time of new drugs. However, existing drug repositioning methods that are based on computational analysis are limited by sparse data and classic fusion methods; thus, we use autoencoders and adaptive fusion methods to calculate drug repositioning. Results: 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. Conclusion: 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s12859-021-04406-y

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Framework of the drug repositioning algorithm based on a deep autoencoder and adaptive fusion, including four types of origin data and three types of data for experiments
Fig. 1 Framework of the drug repositioning algorithm based on a deep autoencoder and adaptive fusion, including four types of origin data and three types of data for experimentsCC BY · PubMed Central
Fig. 2 A schematic diagram of a deep autoencoder framework for drug feature data dimensionality reduction. There are two sections in the overall structure: the encoder, and the decoder. The encoder contains four layers: an input layer, two building layers and an encoding layer. The decoder includes four layers: an encoding layer, two building layers, and an output layer. The building layer is composed of a dense and dropout layer
Fig. 2 A schematic diagram of a deep autoencoder framework for drug feature data dimensionality reduction. There are two sections in the overall structure: the encoder, and the decoder. The encoder contains four layers: an input layer, two building layers and an encoding layer. The decoder includes four layers: an encoding layer, two building layers, and an output layer. The building layer is composed of a dense and dropout layerCC BY · PubMed Central
Fig. 3 Sigmoid function image
Fig. 3 Sigmoid function imageCC BY · PubMed Central
Fig. 4 The number of diseases that can be treated by each drug in the drug-disease associated data
Fig. 4 The number of diseases that can be treated by each drug in the drug-disease associated dataCC BY · PubMed Central
Fig. 5 Changes in the AUCs of the three data sources with different numbers of neighbors (30–120). Via comparison, we find that although the AUC values of three data sources are the highest under 30 neighbors, drug repositioning is a prediction task rather than a simple classification task, and we need more neighbors to provide information. Thus, we choose 50 as the number of neighbors
Fig. 5 Changes in the AUCs of the three data sources with different numbers of neighbors (30–120). Via comparison, we find that although the AUC values of three data sources are the highest under 30 neighbors, drug repositioning is a prediction task rather than a simple classification task, and we need more neighbors to provide information. Thus, we choose 50 as the number of neighborsCC BY · PubMed Central
Fig. 6 a PR curves of the DRDA algorithm and the other three algorithms. The PR curve of DRDA wraps the PR curves of the other three algorithms; thus, the effect is the best. b ROC of the four algorithms. Comparing the curve and AUC value, DADR and DRCFFS have the best effect
Fig. 6 a PR curves of the DRDA algorithm and the other three algorithms. The PR curve of DRDA wraps the PR curves of the other three algorithms; thus, the effect is the best. b ROC of the four algorithms. Comparing the curve and AUC value, DADR and DRCFFS have the best effectCC BY · PubMed Central
Fig. 7 a Correct prediction of the drug-disease associated number with known treatment relationships for the four algorithms at different thresholds. b Proportion of the number of drug-disease associations correctly predicted by the four algorithms with known treatment relationships at different thresholds to all drug-disease with known treatment relationships
Fig. 7 a Correct prediction of the drug-disease associated number with known treatment relationships for the four algorithms at different thresholds. b Proportion of the number of drug-disease associations correctly predicted by the four algorithms with known treatment relationships at different thresholds to all drug-disease with known treatment relationshipsCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 2 references

Research works printed but not linked: 28

  1. Booth B, Zemmel R. Quest for the best. Nat Rev Drug Discov. 2003;2(10):838–41. · DOI
  2. Sardana D, Zhu C, Zhang M, et al. Drug repositioning for orphan diseases. Brief Bioinform. 2011;12(4):346–56. · DOI · Paper page
  3. Nwose OM, Jones MR. Atypical mechanism of glucose modulation by colesevelam in patients with type 2 diabetes. Clin Med Insights: Endocrinol Diabetes. 2013;6(6):75–9.
  4. Cheng F, Zhao J, Fooksa M, et al. A network-based drug repositioning infrastructure for precision cancer medicine through targeting significantly mutated genes in the human cancer genomes. J Am Med Inform Assoc. 2016;23(4):681–91. · DOI
  5. Zhang P, Agarwal P, Obradovic Z. Computational drug repositioning by ranking and integrating multiple data sources. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Berlin, Heidelberg, 2013: 579–594. · DOI
  6. Zhang J, Li C, Lin Y, et al. Computational drug repositioning using collaborative filtering via multi-source fusion. Expert Syst Appl. 2017;84:281–9. · DOI
  7. Luo H, Wang J, Li M, et al. Drug repositioning based on comprehensive similarity measures and bi-random walk algorithm. Bioinformatics. 2016;32(17):2664–71. · DOI
  8. Zeng X, Zhu S, Liu X, et al. deepDR: a network-based deep learning approach to in silico drug repositioning. Bioinformatics. 2019;35(24):5191–8. · DOI
  9. Zhou Y, Hou Y, Shen J, Huang Y, Martin W, Cheng F. Network-based drug repurposing for human coronavirus. 2020. https://doi.org/10.1101/2020.02.03.20020263. · DOI
  10. Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 2006;313(5786):504–7. · DOI · Paper page
  11. Ward R, Wu X, Bottou L. Adagrad stepsizes: Sharp convergence over nonconvex landscapes, from any initialization. arXiv preprint arXiv. 2018.
  12. Moridi M, Ghadirinia M, Sharifi-Zarchi A, et al. The assessment of efficient representation of drug features using deep learning for drug repositioning. BMC Bioinformatics. 2019;20(1):577. · DOI
  13. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. J Mach Learn Res. 2010;9:249–56.
  14. Dudley JT, Deshpande T, Butte AJ. Exploiting drug-disease relationships for computational drug repositioning. Brief Bioinform. 2011;12(4):303–11. · DOI
  15. Li J, Zhu X, Chen JY, et al. Building disease-specific drug–protein connectivity maps from molecular interaction networks and PubMed abstracts. PLoS Comput Biol. 2009;5(7):631–41. · DOI
  16. Wang Y, Xiao J, Suzek T O, et al. PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic Acids Research, 2009, 37(Web Server):W623-W633. · DOI
  17. Rolf A, Amos B, Wu CH, et al. UniProt: the Universal Protein knowledgebase. Nucleic Acids Research, 2004, 32(Data Issue):D115-D119. · DOI
  18. Kuhn M, Campillos M, Letunic I, et al. A side effect resource to capture phenotypic effects of drugs. Mol Syst Biol. 2010;6(01):343–343. · DOI · Paper page
  19. Chiang AP, Butte AJ. Systematic evaluation of drug-disease relationships to identify leads for novel drug uses. Clin Pharmacol Ther. 2009;86(5):507–10. · DOI
  20. Bodenreider O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Research, 2004, 32(suppl_1): D267-D70. · DOI · Paper page
  21. Lin Y, Zhang J, Lin M, et al. Drug repositioning algorithm based on collaborative filtering. J Nanjing Univ (Natl Sci). 2015;51(04):834–41.
  22. Brown AS, Patel CJ. A standard database for drug repositioning. Sci Data. 2017;4(01):1–7. · DOI
  23. Choi Y, Jeong HJ, Liu QF, et al. Clozapine improves memory impairment and reduces Aβ level in the Tg-APPswe/PS1dE9 mouse model of Alzheimer’s disease. Mol Neurobiol. 2017;54(01):450–60. · DOI · Paper page
  24. Zhou Y, Long M, Ran H. Clinical trial of donepezil hydrochloride tablets combined with clozapine dispersible tablets in the treatment of elderly Alzheimer’s disease with behavioral disorder. Chin J Clin Pharmacol. 2017;33(19):1897–9.
  25. Bennett J, Burns J, Welch P, et al. Safety and tolerability of R (+) pramipexole in mild-to-moderate Alzheimer’s disease. J Alzheimers Dis. 2016;49(4):1179–87. · DOI
  26. Wu Y, Xu W, Liu X, et al. Efficacy and safety of olanzapine combined with repetitive transcranial magnetic stimulation in the treatment of behavioral and psychological symptoms of Alzheimer’s desease. Herald Med. 2016;35(10):1069–72.
  27. Zhang L, Wang L, Wang R, et al. Evaluating the effectiveness of GTM-1, rapamycin, and carbamazepine on autophagy and Alzheimer disease. Med Sci Monit: Int Med J Experim Clin Res. 2017;23:801–8. · DOI
  28. Sorial ME, El Sayed NSED. Protective effect of valproic acid in streptozotocin-induced sporadic Alzheimer’s disease mouse model: possible involvement of the cholinergic system. Naunyn Schmiedebergs Arch Pharmacol. 2017;390(6):581–93. · DOI

Cited by

Sorted by citations

See all 8

Metadata

Authors
Chen, P., Bao, T., Yu, X., & Liu, Z.
Affiliations
China Three Gorges University (CN)
Corresponding author
Liu, Zhongtu
ORCID
Venue
BMC Bioinformatics
Publisher
Springer Science and Business Media LLC
Published
2021-10-30
Volume
22
Issue
1
Pages
532-532
ISSN
1471-2105 (ISSN-L)
DOI
10.1186/s12859-021-04406-y
PMC
PMC8556784
OpenAlex
W3116547330
Cited by
8
References
2
Citations by year
2026: 2 · 2025: 3 · 2023: 3
FWCI
1.05
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Bioinformatics (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • The National Key Research and Development Program of China (2016YFC0802500)
  • Research Fund for Excellent Dissertation of China Three Gorges University (2020SSPY075)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
Keywords
drug repurposing, deep autoencoder, adaptive fusion, multi-source data fusion, drug-disease association prediction, drug target proteins, drug chemical structure, adverse drug reactions, disease similarity, drug similarity, Alzheimer's disease, data sparsity
MeSH terms
Algorithms, Alzheimer Disease, Humans, Computational Biology, Drug Repositioning, Drug-Related Side Effects and Adverse Reactions

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A drug repositioning algorithm based on a deep autoencoder and adaptive fusion. https://app.cochat.ai/papers/10.1186/s12859-021-04406-y
The paper
Chen, P., Bao, T., Yu, X., & Liu, Z. (2021). A drug repositioning algorithm based on a deep autoencoder and adaptive fusion. BMC Bioinformatics. https://doi.org/10.1186/s12859-021-04406-y