A network-based drug repurposing method via non-negative matrix factorization

Sadeghi, Seyedeh Shaghayegh; Lü, Jianguo; Ngom, Alioune

doi:10.1093/bioinformatics/btab826

Cited by 24 publications

(11 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, matrix completion or matrix factorization methods use ‘submatrix simulation’ techniques, which are more flexible in integrating a priori information and do not rely heavily on predefined labels or negative samples. Instead, these methods extract implicit patterns from existing data matrices, capture the original matrix information through submatrices and generate low-rank simulation matrices to fill in the missing portions of the original association matrices [ 14 , 34 ]. This approach does not require prior knowledge of extensive association information for predictions and has the advantages of adapting to sparse data, adapting to heterogeneous data, and scalability.…”

Section: Discussionmentioning

confidence: 99%

A comparative benchmarking and evaluation framework for heterogeneous network-based drug repositioning methods

Li,

Yang,

Tong

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Computational drug repositioning, which involves identifying new indications for existing drugs, is an increasingly attractive research area due to its advantages in reducing both overall cost and development time. As a result, a growing number of computational drug repositioning methods have emerged. Heterogeneous network-based drug repositioning methods have been shown to outperform other approaches. However, there is a dearth of systematic evaluation studies of these methods, encompassing performance, scalability and usability, as well as a standardized process for evaluating new methods. Additionally, previous studies have only compared several methods, with conflicting results. In this context, we conducted a systematic benchmarking study of 28 heterogeneous network-based drug repositioning methods on 11 existing datasets. We developed a comprehensive framework to evaluate their performance, scalability and usability. Our study revealed that methods such as HGIMC, ITRPCA and BNNR exhibit the best overall performance, as they rely on matrix completion or factorization. HINGRL, MLMC, ITRPCA and HGIMC demonstrate the best performance, while NMFDR, GROBMC and SCPMF display superior scalability. For usability, HGIMC, DRHGCN and BNNR are the top performers. Building on these findings, we developed an online tool called HN-DREP (http://hn-drep.lyhbio.com/) to facilitate researchers in viewing all the detailed evaluation results and selecting the appropriate method. HN-DREP also provides an external drug repositioning prediction service for a specific disease or drug by integrating predictions from all methods. Furthermore, we have released a Snakemake workflow named HN-DRES (https://github.com/lyhbio/HN-DRES) to facilitate benchmarking and support the extension of new methods into the field.

show abstract

Section: Discussionmentioning

confidence: 99%

A comparative benchmarking and evaluation framework for heterogeneous network-based drug repositioning methods

Li,

Yang,

Tong

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…One is the combination of various methods, such as the use of text mining and network analysis, and the creation of statistical models for predicting semantic link association to assess the relationship between pharmacological target pairings ( Chen et al, 2012 ); text analysis combined with machine learning ( Zhu et al, 2020 ) to develop drugs for Parkinson’s disease; prediction of new DTIs using data from multiple databases ( Olayan et al, 2018 ); and the obtained relocated anticancer drugs were verified by cross-validation, literature, and experimental verification ( Cheng et al, 2021 ). Second, the most advanced algorithms are applied and improved, such as matrix decomposition ( Xuan et al, 2019 ; Huang et al, 2020 ; Meng et al, 2021 ; Tang et al, 2021 ; Sadeghi et al, 2022 ) and matrix completion ( Luo et al, 2018 ; Yan et al, 2022 ) and deep learning ( Aliper et al, 2016 ; Zeng et al, 2019 ; Chiu et al, 2020 ; Stokes et al, 2020 ; Lee and Chen, 2021 ; Liu et al, 2021 ).…”

Section: Discussionmentioning

confidence: 99%

Drug repositioning: A bibliometric analysis

Sun¹,

Dong²,

Dong³

et al. 2022

Front. Pharmacol.

View full text Add to dashboard Cite

Drug repurposing has become an effective approach to drug discovery, as it offers a new way to explore drugs. Based on the Science Citation Index Expanded (SCI-E) and Social Sciences Citation Index (SSCI) databases of the Web of Science core collection, this study presents a bibliometric analysis of drug repurposing publications from 2010 to 2020. Data were cleaned, mined, and visualized using Derwent Data Analyzer (DDA) software. An overview of the history and development trend of the number of publications, major journals, major countries, major institutions, author keywords, major contributors, and major research fields is provided. There were 2,978 publications included in the study. The findings show that the United States leads in this area of research, followed by China, the United Kingdom, and India. The Chinese Academy of Science published the most research studies, and NIH ranked first on the h-index. The Icahn School of Medicine at Mt Sinai leads in the average number of citations per study. Sci Rep, Drug Discov. Today, and Brief. Bioinform. are the three most productive journals evaluated from three separate perspectives, and pharmacology and pharmacy are unquestionably the most commonly used subject categories. Cheng, FX; Mucke, HAM; and Butte, AJ are the top 20 most prolific and influential authors. Keyword analysis shows that in recent years, most research has focused on drug discovery/drug development, COVID-19/SARS-CoV-2/coronavirus, molecular docking, virtual screening, cancer, and other research areas. The hotspots have changed in recent years, with COVID-19/SARS-CoV-2/coronavirus being the most popular topic for current drug repurposing research.

show abstract

“…FLQ were initially discovered for malaria in 1962. Later only in the 1980s, quinolones were demonstrated to be useful for the treatment of TB [35]. A new generation of FLQ, ciprofloxacin, and moxifloxacin have also been reported to be useful for MDR-TB.…”

Section: Pathogen-targeted Therapymentioning

confidence: 99%

An overview of current strategies and future prospects in drug repurposing in tuberculosis

Singh

Chawla

2023

Exploration of Medicine

View full text Add to dashboard Cite

A large number of the population faces mortality as an effect of tuberculosis (TB). The line of treatment in the management of TB faces a jolt with ever-increasing multi-drug resistance (DR) cases. Further, the drugs engaged in the treatment of TB are associated with different toxicities, such as renal and hepatic toxicity. Different combinations are sought for effective anti-tuberculosis (anti-TB) effects with a decrease in toxicity. In this regard, drug repurposing has been very promising in improving the efficacy of drugs by enhancement of bioavailability and widening the safety margin. The success in drug repurposing lies in specified binding and inhibition of a particular target in the drug molecule. Different drugs have been repurposed for various ailments like cancer, Alzheimer’s disease, acquired immunodeficiency syndrome (AIDS), hair loss, etc. Repurposing in anti-TB drugs holds great potential too. The use of whole-cell screening assays and the availability of large chemical compounds for testing against Mycobacterium tuberculosis poses a challenge in this development. The target-based discovery of sites has emerged in the form of phenotypic screening as ethionamide R (EthR) and malate synthase inhibitors are similar to pharmaceuticals. In this review, the authors have thoroughly described the drug repurposing techniques on the basis of pharmacogenomics and drug metabolism, pathogen-targeted therapy, host-directed therapy, and bioinformatics approaches for the identification of drugs. Further, the significance of repurposing of drugs elaborated on large databases has been revealed. The role of genomics and network-based methods in drug repurposing has been also discussed in this article.

show abstract

A network-based drug repurposing method via non-negative matrix factorization

Cited by 24 publications

References 49 publications

A comparative benchmarking and evaluation framework for heterogeneous network-based drug repositioning methods

A comparative benchmarking and evaluation framework for heterogeneous network-based drug repositioning methods

Drug repositioning: A bibliometric analysis

An overview of current strategies and future prospects in drug repurposing in tuberculosis

Contact Info

Product

Resources

About