NTD-DR: Nonnegative tensor decomposition for drug repositioning

Jamali, Ali Akbar; Tan, Yuting; Kusalik, Anthony; Wu, Fang‐Xiang

doi:10.1371/journal.pone.0270852

Cited by 4 publications

(4 citation statements)

References 69 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jamali et al [ 37 ] proposed non-negative tensor decomposition for drug repositioning (NTD-DR), which uses pairwise associations of drug–disease, drug–target, and target–disease to construct a three-dimensional association tensor and decompose it into three-factor matrices. The objective function of tensor decomposition is as follows:

where A , B , and C are non-negative factor matrices;

is the least square criterion;

is the function for third-order tensor decomposition;

is the function for similarities of drug–drug, target–target, and disease–disease; and

is the function for drug–target, drug–disease, and target–disease pairwise associations.…”

Section: Review Of Network-based Drug-repositioning Approachesmentioning

confidence: 99%

Drug-Disease Association Prediction Using Heterogeneous Networks for Computational Drug Repositioning

et al. 2022

View full text Add to dashboard Cite

Drug repositioning, which involves the identification of new therapeutic indications for approved drugs, considerably reduces the time and cost of developing new drugs. Recent computational drug repositioning methods use heterogeneous networks to identify drug–disease associations. This review reveals existing network-based approaches for predicting drug–disease associations in three major categories: graph mining, matrix factorization or completion, and deep learning. We selected eleven methods from the three categories to compare their predictive performances. The experiment was conducted using two uniform datasets on the drug and disease sides, separately. We constructed heterogeneous networks using drug–drug similarities based on chemical structures and ATC codes, ontology-based disease–disease similarities, and drug–disease associations. An improved evaluation metric was used to reflect data imbalance as positive associations are typically sparse. The prediction results demonstrated that methods in the graph mining and matrix factorization or completion categories performed well in the overall assessment. Furthermore, prediction on the drug side had higher accuracy than on the disease side. Selecting and integrating informative drug features in drug–drug similarity measurement are crucial for improving disease-side prediction.

show abstract

where A , B , and C are non-negative factor matrices;

is the least square criterion;

is the function for third-order tensor decomposition;

is the function for similarities of drug–drug, target–target, and disease–disease; and

is the function for drug–target, drug–disease, and target–disease pairwise associations.…”

Section: Review Of Network-based Drug-repositioning Approachesmentioning

confidence: 99%

Drug-Disease Association Prediction Using Heterogeneous Networks for Computational Drug Repositioning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Based on the prediction scores of the selected drug-disease pairs, we assessed the performance of the GTD, MLP, and their ensemble models using AUC and NDCG@n. The NDCG@n metric evaluates the accuracy of the top n associations based on their prediction scores. The results of the proposed approaches were compared with those of NTD-DR [34], which is a conventional tensor decomposition method for drug repositioning.…”

Section: Predicting Drug-gene-disease Triple Associationsmentioning

confidence: 99%

“…For example, Wang et al [33] constructed a drug-target-disease tensor by combining drugdisease, drug-target, and disease-target associations and predicted drug-target-disease associations through tensor decomposition. NTD-DR [34] performed non-negative tensor decomposition on a drug-target-disease tensor for drug repositioning. Non-negative tensor decomposition was enhanced with additional constraints based on similarities and associations between drugs, targets, and diseases.…”

Section: Introductionmentioning

confidence: 99%

Predicting Drug–Gene–Disease Associations by Tensor Decomposition for Network-Based Computational Drug Repositioning

Kim

Cho

2023

Biomedicines

View full text Add to dashboard Cite

Drug repositioning offers the significant advantage of greatly reducing the cost and time of drug discovery by identifying new therapeutic indications for existing drugs. In particular, computational approaches using networks in drug repositioning have attracted attention for inferring potential associations between drugs and diseases efficiently based on the network connectivity. In this article, we proposed a network-based drug repositioning method to construct a drug–gene–disease tensor by integrating drug–disease, drug–gene, and disease–gene associations and predict drug–gene–disease triple associations through tensor decomposition. The proposed method, which ensembles generalized tensor decomposition (GTD) and multi-layer perceptron (MLP), models drug–gene–disease associations through GTD and learns the features of drugs, genes, and diseases through MLP, providing more flexibility and non-linearity than conventional tensor decomposition. We experimented with drug–gene–disease association prediction using two distinct networks created by chemical structures and ATC codes as drug features. Moreover, we leveraged drug, gene, and disease latent vectors obtained from the predicted triple associations to predict drug–disease, drug–gene, and disease–gene pairwise associations. Our experimental results revealed that the proposed ensemble method was superior for triple association prediction. The ensemble model achieved an AUC of 0.96 in predicting triple associations for new drugs, resulting in an approximately 7% improvement over the performance of existing models. It also showed competitive accuracy for pairwise association prediction compared with previous methods. This study demonstrated that incorporating genetic information leads to notable advancements in drug repositioning.

show abstract

“…Chen et al use Bayesian NMF for predicting disease-related biomarkers (miRNA) [127]. Furthermore, Ding et al develop a deep belief network-based matrix factorization model with multiple layers and nonlinear transformation for predicting diseaserelated biomarkers (miRNA) [128]. Networks with one or two types of vertices can be represented by planar graphs and their adjacent matrices are two-dimensional tensors.…”

Section: A Uv T a Uv Tmentioning

confidence: 99%

Network Learning for Biomarker Discovery

Ding¹,

Fu²,

Luo³

et al. 2023

IJNDI

Self Cite

View full text Add to dashboard Cite

Survey/review study Network Learning for Biomarker Discovery Yulian Ding 1, Minghan Fu 1, Ping Luo 2, and Fang-Xiang Wu 1,3,4,* 1 Division of Biomedical Engineering, University of Saskatchewan, S7N 5A9, Saskatoon, Canada 2 Princess Margaret Cancer Centre, University Health Network, Toronto, ON M5G 1L7, Canada 3 Department of Computer Sciences, University of Saskatchewan, S7N 5A9, Saskatoon, Canada 4 Department of Mechanical Engineering, University of Saskatchewan, S7N 5A9, Saskatoon, Canada * Correspondence: faw341@mail.usask.ca Received: 14 October 2022 Accepted: 5 December 2022 Published: Abstract: Everything is connected and thus networks are instrumental in not only modeling complex systems with many components, but also accommodating knowledge about their components. Broadly speaking, network learning is an emerging area of machine learning to discover knowledge within networks. Although networks have permeated all subjects of sciences, in this study we mainly focus on network learning for biomarker discovery. We first overview methods for traditional network learning which learn knowledge from networks with centrality analysis. Then, we summarize the network deep learning, which are powerful machine learning models that integrate networks (graphs) with deep neural networks. Biomarkers can be placed in proper biological networks as vertices or edges and network learning applications for biomarker discovery are discussed. We finally point out some promising directions for future work about network learning.

show abstract

NTD-DR: Nonnegative tensor decomposition for drug repositioning

Cited by 4 publications

References 69 publications

Drug-Disease Association Prediction Using Heterogeneous Networks for Computational Drug Repositioning

Drug-Disease Association Prediction Using Heterogeneous Networks for Computational Drug Repositioning

Predicting Drug–Gene–Disease Associations by Tensor Decomposition for Network-Based Computational Drug Repositioning

Network Learning for Biomarker Discovery

Contact Info

Product

Resources

About