1
|
Hu H, Cai J, Qi D, Li B, Yu L, Wang C, Bajpai AK, Huang X, Zhang X, Lu L, Liu J, Zheng F. Identification of Potential Biomarkers for Group I Pulmonary Hypertension Based on Machine Learning and Bioinformatics Analysis. Int J Mol Sci 2023; 24:ijms24098050. [PMID: 37175757 PMCID: PMC10178909 DOI: 10.3390/ijms24098050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2023] [Revised: 03/20/2023] [Accepted: 03/31/2023] [Indexed: 05/15/2023] Open
Abstract
A number of processes and pathways have been reported in the development of Group I pulmonary hypertension (Group I PAH); however, novel biomarkers need to be identified for a better diagnosis and management. We employed a robust rank aggregation (RRA) algorithm to shortlist the key differentially expressed genes (DEGs) between Group I PAH patients and controls. An optimal diagnostic model was obtained by comparing seven machine learning algorithms and was verified in an independent dataset. The functional roles of key DEGs and biomarkers were analyzed using various in silico methods. Finally, the biomarkers and a set of key candidates were experimentally validated using patient samples and a cell line model. A total of 48 key DEGs with preferable diagnostic value were identified. A gradient boosting decision tree algorithm was utilized to build a diagnostic model with three biomarkers, PBRM1, CA1, and TXLNG. An immune-cell infiltration analysis revealed significant differences in the relative abundances of seven immune cells between controls and PAH patients and a correlation with the biomarkers. Experimental validation confirmed the upregulation of the three biomarkers in Group I PAH patients. In conclusion, machine learning and a bioinformatics analysis along with experimental techniques identified PBRM1, CA1, and TXLNG as potential biomarkers for Group I PAH.
Collapse
Affiliation(s)
- Hui Hu
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Jie Cai
- Department of Cardial Surgery, Zhongnan Hospital of Wuhan University, Wuhan 430060, China
| | - Daoxi Qi
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Boyu Li
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Li Yu
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Chen Wang
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Akhilesh K Bajpai
- Department of Genetics, Genomics and Informatics, University of Tennessee Health Sciences Center, Memphis, TN 38163, USA
| | - Xiaoqin Huang
- Department of Ophthalmology, University of Tennessee Health Science Center, Memphis, TN 38163, USA
| | - Xiaokang Zhang
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| | - Lu Lu
- Department of Genetics, Genomics and Informatics, University of Tennessee Health Sciences Center, Memphis, TN 38163, USA
| | - Jinping Liu
- Department of Cardial Surgery, Zhongnan Hospital of Wuhan University, Wuhan 430060, China
| | - Fang Zheng
- Center for Gene Diagnosis, Department of Clinical Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan 430071, China
| |
Collapse
|
2
|
Duan T, Kuang Z, Deng L. SVMMDR: Prediction of miRNAs-drug resistance using support vector machines based on heterogeneous network. Front Oncol 2022; 12:987609. [PMID: 36338674 PMCID: PMC9632662 DOI: 10.3389/fonc.2022.987609] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Accepted: 09/14/2022] [Indexed: 11/21/2022] Open
Abstract
In recent years, the miRNA is considered as a potential high-value therapeutic target because of its complex and delicate mechanism of gene regulation. The abnormal expression of miRNA can cause drug resistance, affecting the therapeutic effect of the disease. Revealing the associations between miRNAs-drug resistance can help in the design of effective drugs or possible drug combinations. However, current conventional experiments for identification of miRNAs-drug resistance are time-consuming and high-cost. Therefore, it’s of pretty realistic value to develop an accurate and efficient computational method to predicting miRNAs-drug resistance. In this paper, a method based on the Support Vector Machines (SVM) to predict the association between MiRNA and Drug Resistance (SVMMDR) is proposed. The SVMMDR integrates miRNAs-drug resistance association, miRNAs sequence similarity, drug chemical structure similarity and other similarities, extracts path-based Hetesim features, and obtains inclined diffusion feature through restart random walk. By combining the multiple feature, the prediction score between miRNAs and drug resistance is obtained based on the SVM. The innovation of the SVMMDR is that the inclined diffusion feature is obtained by inclined restart random walk, the node information and path information in heterogeneous network are integrated, and the SVM is used to predict potential miRNAs-drug resistance associations. The average AUC of SVMMDR obtained is 0.978 in 10-fold cross-validation.
Collapse
|