1
|
Lei C, Lei X. Predicting Drug-miRNA Associations Combining SDNE with BiGRU. IEEE J Biomed Health Inform 2025; 29:3805-3816. [PMID: 40030943 DOI: 10.1109/jbhi.2024.3525266] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/05/2025]
Abstract
It is well recognized that abnormal miRNA expression can result in drug resistance and pose a challenge to miRNA-based treatments. However, the drug-miRNA associations (DMA) are still incompletely understood. Conventional biological experiments have a high failure rate, lengthy cycle times, and expensive expenditures. Consequently, deep learning-based techniques for predicting DMA have been developed. In this work, we propose a novel method named SDNEDMA for DMA prediction that combines SDNE with BiGRU. The two-channel approach is used to combine the attribute and topological features of miRNAs and drugs. To be more precise, we first model the associations between drugs and miRNAs through the known bipartite network, and then utilize SDNE to obtain the topological features. Meanwhile, BiGRU is employed to acquire miRNA k-mer sequence features and drug ECFP fingerprints. Subsequently, both the topological and attribute features are fused jointly to form final features which is aimed to predict the association score for both them. Multiple features drugs and miRNAs are used at the same time, more information is fused, and the features are more accurate, so the prediction performance is better. The experiments show that SDNEDMA outperforms other state-of-the-art methods, yielding AUC of 0.9641 when we use 5-fold cross-validation on the ncDR dataset. SDNEDMA is additionally employed in a case study, showing how accurate and dependable it is. To sum up, the SDNEDMA has the ability to predict DMA with high accuracy and effectiveness, which is really important for drug development.
Collapse
|
2
|
To KKW, Huang Z, Zhang H, Ashby CR, Fu L. Utilizing non-coding RNA-mediated regulation of ATP binding cassette (ABC) transporters to overcome multidrug resistance to cancer chemotherapy. Drug Resist Updat 2024; 73:101058. [PMID: 38277757 DOI: 10.1016/j.drup.2024.101058] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Revised: 12/27/2023] [Accepted: 01/16/2024] [Indexed: 01/28/2024]
Abstract
Multidrug resistance (MDR) is one of the primary factors that produces treatment failure in patients receiving cancer chemotherapy. MDR is a complex multifactorial phenomenon, characterized by a decrease or abrogation of the efficacy of a wide spectrum of anticancer drugs that are structurally and mechanistically distinct. The overexpression of the ATP-binding cassette (ABC) transporters, notably ABCG2 and ABCB1, are one of the primary mediators of MDR in cancer cells, which promotes the efflux of certain chemotherapeutic drugs from cancer cells, thereby decreasing or abolishing their therapeutic efficacy. A number of studies have suggested that non-coding RNAs (ncRNAs), particularly microRNAs (miRNAs), long non-coding RNAs (lncRNAs) and circular RNAs (circRNAs), play a pivotal role in mediating the upregulation of ABC transporters in certain MDR cancer cells. This review will provide updated information about the induction of ABC transporters due to the aberrant regulation of ncRNAs in cancer cells. We will also discuss the measurement and biological profile of circulating ncRNAs in various body fluids as potential biomarkers for predicting the response of cancer patients to chemotherapy. Sequence variations, such as alternative polyadenylation of mRNA and single nucleotide polymorphism (SNPs) at miRNA target sites, which may indicate the interaction of miRNA-mediated gene regulation with genetic variations to modulate the MDR phenotype, will be reviewed. Finally, we will highlight novel strategies that could be used to modulate ncRNAs and circumvent ABC transporter-mediated MDR.
Collapse
Affiliation(s)
- Kenneth K W To
- School of Pharmacy, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong Special Administrative Region.
| | - Zoufang Huang
- Department of Hematology, The First Affiliated Hospital of Gannan Medical University, Ganzhou 341000, China
| | - Hang Zhang
- School of Pharmacy, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong Special Administrative Region
| | - Charles R Ashby
- Department of Pharmaceutical Sciences, College of Pharmacy and Health Sciences, St. John's University, Queens, NY 11439, United States
| | - Liwu Fu
- State Key Laboratory of Oncology in South China; Collaborative Innovation Center for Cancer Medicine; Sun Yat-sen University Cancer Center, Guangzhou 510060, China.
| |
Collapse
|
3
|
Elgebaly SA, Peacock WF, Christenson RH, Kreutzer DL, Faraag AHI, Sarguos AMM, El-Khazragy N. Integrated Bioinformatics Analysis Confirms the Diagnostic Value of Nourin-Dependent miR-137 and miR-106b in Unstable Angina Patients. Int J Mol Sci 2023; 24:14783. [PMID: 37834231 PMCID: PMC10573268 DOI: 10.3390/ijms241914783] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2023] [Revised: 09/22/2023] [Accepted: 09/27/2023] [Indexed: 10/15/2023] Open
Abstract
The challenge of rapidly diagnosing myocardial ischemia in unstable angina (UA) patients presenting to the Emergency Department (ED) is due to a lack of sensitive blood biomarkers. This has prompted an investigation into microRNAs (miRNAs) related to cardiac-derived Nourin for potential diagnostic application. The Nourin protein is rapidly expressed in patients with acute coronary syndrome (ACS) (UA and acute myocardial infarction (AMI)). MicroRNAs regulate gene expression through mRNA binding and, thus, may represent potential biomarkers. We initially identified miR-137 and miR-106b and conducted a clinical validation, which demonstrated that they were highly upregulated in ACS patients, but not in healthy subjects and non-ACS controls. Using integrated comprehensive bioinformatics analysis, the present study confirms that the Nourin protein targets miR-137 and miR-106b, which are linked to myocardial ischemia and inflammation associated with ACS. Molecular docking demonstrated robust interactions between the Nourin protein and miR137/hsa-miR-106b, involving hydrogen bonds and hydrophobic interactions, with -10 kcal/mol binding energy. I-TASSER generated Nourin analogs, with the top 10 chosen for structural insights. Antigenic regions and MHCII epitopes within the Nourin SPGADGNGGEAMPGG sequence showed strong binding to HLA-DR/DQ alleles. The Cytoscape network revealed interactions of -miR137/hsa-miR--106b and Phosphatase and tensin homolog (PTEN) in myocardial ischemia. RNA Composer predicted the secondary structure of miR-106b. Schrödinger software identified key Nourin-RNA interactions critical for complex stability. The study identifies miR-137 and miR-106b as potential ACS diagnostic and therapeutic targets. This research underscores the potential of miRNAs targeting Nourin for precision ACS intervention. The analysis leverages RNA Composer, Schrödinger, and I-TASSER tools to explore interactions and structural insights. Robust Nourin-miRNA interactions are established, bolstering the case for miRNA-based interventions in ischemic injury. In conclusion, the study contributes to UA and AMI diagnosis strategies through bioinformatics-guided exploration of Nourin-targeting miRNAs. Supported by comprehensive molecular analysis, the hypoxia-induced miR-137 for cell apoptosis (a marker of cell damage) and the inflammation-induced miR-106b (a marker of inflammation) confirmed their potential clinical use as diagnostic biomarkers. This research reinforces the growing role of miR-137/hsa-miR-106b in the early diagnosis of myocardial ischemia in unstable angina patients.
Collapse
Affiliation(s)
- Salwa A. Elgebaly
- Research & Development, Nour Heart, Inc., Vienna, VA 22180, USA
- Department of Surgery, University of Connecticut School of Medicine, Farmington, CT 06032, USA;
| | - W. Frank Peacock
- Department of Emergency Medicine, Baylor College of Medicine, Houston, TX 77057, USA;
| | - Robert H. Christenson
- Department of Pathology, School of Medicine, University of Maryland, Baltimore, MD 2120, USA;
| | - Donald L. Kreutzer
- Department of Surgery, University of Connecticut School of Medicine, Farmington, CT 06032, USA;
| | - Ahmed Hassan Ibrahim Faraag
- Department of Botany and Microbiology, Faculty of Science Helwan University, Cairo 11795, Egypt;
- School of Biotechnology, Badr University, Cairo 11829, Egypt
| | | | - Nashwa El-Khazragy
- Department of Clinical Pathology-Hematology, Ain Shams Medical Research Institute (MASRI), Faculty of Medicine, Ain Shams University, Cairo 11566, Egypt;
- Department of Genetics and Molecular Biology, Egypt Center for Research and Regenerative Medicine (ECRRM), Cairo11599, Egypt
| |
Collapse
|
4
|
Wei MM, Yu CQ, Li LP, You ZH, Ren ZH, Guan YJ, Wang XF, Li YC. LPIH2V: LncRNA-protein interactions prediction using HIN2Vec based on heterogeneous networks model. Front Genet 2023; 14:1122909. [PMID: 36845392 PMCID: PMC9950107 DOI: 10.3389/fgene.2023.1122909] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Accepted: 01/30/2023] [Indexed: 02/12/2023] Open
Abstract
LncRNA-protein interaction plays an important role in the development and treatment of many human diseases. As the experimental approaches to determine lncRNA-protein interactions are expensive and time-consuming, considering that there are few calculation methods, therefore, it is urgent to develop efficient and accurate methods to predict lncRNA-protein interactions. In this work, a model for heterogeneous network embedding based on meta-path, namely LPIH2V, is proposed. The heterogeneous network is composed of lncRNA similarity networks, protein similarity networks, and known lncRNA-protein interaction networks. The behavioral features are extracted in a heterogeneous network using the HIN2Vec method of network embedding. The results showed that LPIH2V obtains an AUC of 0.97 and ACC of 0.95 in the 5-fold cross-validation test. The model successfully showed superiority and good generalization ability. Compared to other models, LPIH2V not only extracts attribute characteristics by similarity, but also acquires behavior properties by meta-path wandering in heterogeneous networks. LPIH2V would be beneficial in forecasting interactions between lncRNA and protein.
Collapse
Affiliation(s)
- Meng-Meng Wei
- School of Information Engineering, Xijing University, Xi’an, China
| | - Chang-Qing Yu
- School of Information Engineering, Xijing University, Xi’an, China,*Correspondence: Chang-Qing Yu, ; Li-Ping Li,
| | - Li-Ping Li
- School of Information Engineering, Xijing University, Xi’an, China,College of Grassland and Environment Sciences, Xinjiang Agricultural University, Urumqi, China,*Correspondence: Chang-Qing Yu, ; Li-Ping Li,
| | - Zhu-Hong You
- School of Computer Science, Northwestern Polytechnical University, Xi’an, China
| | - Zhong-Hao Ren
- School of Information Engineering, Xijing University, Xi’an, China
| | - Yong-Jian Guan
- School of Information Engineering, Xijing University, Xi’an, China
| | | | | |
Collapse
|