A Fused Deep Learning Approach to Transform Novel Drug Repositioning DOI Creative Commons
Dongsheng Cao, Kun Li, Jiacai Yi

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 27, 2024

Abstract Drug repositioning holds significant promise for discovering new therapeutic applications of existing drugs, thereby accelerating drug development, reducing associated costs, and improving overall efficiency. However, current methodologies encounter difficulties in effectively managing diverse network representations, tackling cold start issues, handling intrinsic attribute representations. In this study, we introduce UKEDR, a fused deep learning framework that seamlessly integrates knowledge graph embedding, sophisticated pre-training strategies, recommendation systems to address these challenges repositioning. straightforward yet effective semantic similarity-driven embedding approach leverages both pre-trained embeddings structure was proposed overcome the intractable issue. Our comprehensive evaluations reveal UKEDR outperforms various state-of-the-art baselines, including classical machine learning, network-based approaches. scenario simulating real-world discovery, achieves 24.2% higher AUPR compared latest state-of-the-art, highlighting its superior capability unseen nodes generalizing novel compounds. Furthermore, demonstrate effectiveness through repurposing case studies diseases such as falciparum malaria, prostate cancer so on. Finally, model interpretability is enhanced visualization, providing valuable insights into process.

Language: Английский

Computational drug repurposing in Parkinson’s disease: Omaveloxolone and cyproheptadine as promising therapeutic candidates DOI Creative Commons
Xin Guo, Jie Wang, Hongyang Fan

et al.

Frontiers in Pharmacology, Journal Year: 2025, Volume and Issue: 16

Published: April 8, 2025

Background: Parkinson's disease (PD), a prevalent and progressive neurodegenerative disorder, currently lacks effective satisfactory pharmacological treatments. Computational drug repurposing represents promising efficient strategy for discovery, aiming to identify new therapeutic indications existing pharmaceuticals. Methods: We employed drug-target network approach computationally repurpose FDA-approved drugs from databases such as DrugBank. A literature review was conducted select candidates not previously reported pharmacoprotective against PD. Subsequent in vitro evaluation utilized Cell Counting Kit-8 (CCK8) assays assess the neuroprotective effects of selected compounds SH-SY5Y cell model induced by 1-methyl-4-phenylpyridinium (MPP+). Furthermore, an vivo mouse 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP) developed investigate mechanisms action potential identified candidates. Results: Our 176 candidates, with 28 their anti-Parkinsonian lack prior PD-related reporting. CCK8 showed significant neuroprotection cells Omaveloxolone Cyproheptadine. In MPTP-induced model, Cyproheptadine inhibited interleukin-6 (IL-6) expression prevented Tyrosine Hydroxylase (TH) downregulation via MAPK/NFκB pathway, while alleviated TH downregulation, potentially through Kelch-like ECH-associated protein 1 (KEAP1)-NF-E2-related factor 2 (Nrf2)/antioxidant response element (ARE) pathway. Both preserved dopaminergic neurons improved neurological deficits PD model. Conclusion: This study elucidates treatment application computational repurposing, thereby underscoring its efficacy discovery strategy.

Language: Английский

Citations

0
From past to future: Digital approaches to success of clinical drug trials for Parkinson's disease DOI Creative Commons
Cen Cong, Madison Milne‐Ives, Ananya Ananthakrishnan

et al.

Journal of Parkinson s Disease, Journal Year: 2025, Volume and Issue: unknown

Published: April 27, 2025

Recent years have seen successes in symptomatic drugs for Parkinson's disease, but the development of treatments stopping disease progression continues to fail clinical drug trials, largely due lack efficacy drugs. This may be related limited understanding mechanisms, data heterogeneity, poor target screening and candidate selection, challenges determining optimal dosage levels, reliance on animal models, insufficient patient participation, adherence trials. Most recent applications digital health technologies artificial intelligence (AI)-based tools focused mainly stages before used AI-based algorithms or models discover novel targets, inhibitors indications, recommend candidates dosage, promote remote collection. paper reviews state literature highlights strengths limitations approaches discovery from 2021 2024, offers recommendations future research practice success

Language: Английский

Citations

0
Knowledge Graphs for drug repurposing: a review of databases and methods DOI Creative Commons
Pablo Perdomo-Quinteiro, Alberto Belmonte-Hernández

Briefings in Bioinformatics, Journal Year: 2024, Volume and Issue: 25(6)

Published: Sept. 12, 2024

Drug repurposing has emerged as a effective and efficient strategy to identify new treatments for variety of diseases. One the most approaches discovering potential drug candidates involves utilization Knowledge Graphs (KGs). This review comprehensively explores some prominent KGs, detailing their structure, data sources, how they facilitate drugs. In addition this paper delves into various artificial intelligence techniques that enhance process repurposing. These methods not only accelerate identification viable but also improve precision predictions by leveraging complex datasets advanced algorithms. Furthermore, importance explainability in is emphasized. Explainability are crucial provide insights reasoning behind AI-generated predictions, thereby increasing trustworthiness transparency process. We will discuss several can be employed validate these ensuring both reliable understandable.

Language: Английский

Citations

3
Research Progresses and Applications of Knowledge Graph Embedding Technique in Chemistry DOI
C. Joanne Wang, Yunqing Yang, Jinshuai Song

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 20, 2024

A knowledge graph (KG) is a technique for modeling entities and their interrelations. Knowledge embedding (KGE) translates these relationships into continuous vector space to facilitate dense efficient representations. In the domain of chemistry, applying KG KGE techniques integrates heterogeneous chemical information coherent user-friendly framework, enhances representation data features, beneficial downstream tasks, such as property prediction. This paper begins with comprehensive review classical contemporary methodologies, including distance-based models, semantic matching neural network-based approaches. We then catalogue primary databases employed in chemistry biochemistry that furnish KGs essential data. Subsequently, we explore latest applications focusing on risk assessment, prediction, drug discovery. Finally, discuss current challenges provide perspective potential future developments.

Language: Английский

Citations

2
PharmaRedefine: A database server for repurposing drugs against pathogenic bacteria DOI

Longxiao Yuan,

Jingjing Guo

Methods, Journal Year: 2024, Volume and Issue: 227, P. 78 - 85

Published: May 14, 2024

Language: Английский

Citations

1
Calculating the similarity between prescriptions to find their new indications based on graph neural network DOI Creative Commons
Xingxing Han,

Xiaoxia Xie,

Ranran Zhao

et al.

Chinese Medicine, Journal Year: 2024, Volume and Issue: 19(1)

Published: Sept. 11, 2024

Language: Английский

Citations

1
A Fused Deep Learning Approach to Transform Novel Drug Repositioning DOI Creative Commons
Dongsheng Cao, Kun Li, Jiacai Yi

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 27, 2024

Abstract Drug repositioning holds significant promise for discovering new therapeutic applications of existing drugs, thereby accelerating drug development, reducing associated costs, and improving overall efficiency. However, current methodologies encounter difficulties in effectively managing diverse network representations, tackling cold start issues, handling intrinsic attribute representations. In this study, we introduce UKEDR, a fused deep learning framework that seamlessly integrates knowledge graph embedding, sophisticated pre-training strategies, recommendation systems to address these challenges repositioning. straightforward yet effective semantic similarity-driven embedding approach leverages both pre-trained embeddings structure was proposed overcome the intractable issue. Our comprehensive evaluations reveal UKEDR outperforms various state-of-the-art baselines, including classical machine learning, network-based approaches. scenario simulating real-world discovery, achieves 24.2% higher AUPR compared latest state-of-the-art, highlighting its superior capability unseen nodes generalizing novel compounds. Furthermore, demonstrate effectiveness through repurposing case studies diseases such as falciparum malaria, prostate cancer so on. Finally, model interpretability is enhanced visualization, providing valuable insights into process.

Language: Английский

Citations

0