利用機器學習分析類風濕性關節炎相關蛋白質資料以探討疾病生物標記

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：12

、訪客IP：13.59.113.183

姓名

楊騏鴻(Chi-Hung Yang) 查詢紙本館藏

畢業系所

生醫科學與工程學系

論文名稱

利用機器學習分析類風濕性關節炎相關蛋白質資料以探討疾病生物標記
(Using machine learning to analyze Rheumatoid Arthritis-related proteomics data for exploring disease biomarkers)

相關論文

★ DeNox：代謝體學與蛋白質體學定量數據的可視化工具

★ MS-Picker：用於 LC-MS/MS 代謝組學數據的準確波峰偵測工具

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2029-8-1以後開放)

摘要(中)

本研究旨在透過分析不同國家及不同物種的類風濕性關節炎相關蛋白質資料，並深入探討其致病機制及潛在生物標記。我們首先從ProteomeXchange網站中蒐集到了五筆公開的蛋白質體資料，包括四筆來自中國北京、中國廣州、荷蘭和巴基斯坦的人類資料，以及一筆來自小鼠的資料。這些資料都是液相層析-串聯質譜儀(LC-MS/MS)所生成的。接著，我們將這些資料丟入FragPipe進行定量分析，再根據分析出的數據進一步利用傳統生物資訊方法與機器學習尋找可能的致病蛋白，最終篩選出三個潛在生物標記，包含：血清澱粉樣蛋白A1 (SAA1)、觸珠蛋白(HPT)及纖維蛋白原α鏈(FIBA)。

摘要(英)

This study aims to explore the pathogenesis of Rheumatoid Arthritis (RA) and identify potential biomarkers associated with RA by analyzing proteomics data from different countries and species. We collected five public proteomics datasets from ProteomeXchange, including four datasets from human in Beijing, Guangzhou, the Netherlands, and Pakistani, as well as one dataset from mice. These datasets were generated using liquid chromatography-tandem mass spectrometry (LC-MS/MS). Next, we processed the data using FragPipe for quantitative analysis, followed by traditional bioinformatics methods and machine learning to identify potential disease-related proteins. These methods led to the identification of three potential biomarkers: serum amyloid A1 (SAA1), haptoglobin (HPT), and fibrinogen alpha chain (FIBA).

關鍵字(中)

★ 類風濕性關節炎
★ 蛋白質體數據
★ LC-MS/MS
★ 機器學習

關鍵字(英)

★ Rheumatoid Arthritis
★ proteomic data
★ LC-MS/MS
★ Machine Learning

論文目次

目錄
中文摘要 i
Abstract ii
致謝 iii
目錄 v
圖目錄 vii
表目錄 viii
一、緒論 1
1-1 類風濕性關節炎 1
1-2 機器學習 3
1-3 差異表達分析 5
1-4 研究動機 7
二、材料方法 9
2-1 類風濕性關節炎蛋白質資料來源 9
2-2 資料預處理與參數設定 12
2-3 差異表達蛋白鑑定 14
2-4 特徵重要性分析與外部驗證 16
三、分析流程 20
四、實驗結果 22
4-1 差異表達分析 22
4-2 富集分析 28
4-3 蛋白質交互作用網絡分析 32
4-4 機器學習相關分析 34
4-4-1 模型評估 34
4-4-2 特徵重要性分析 42
4-4-3 外部驗證 48
4-5 分析總結 54
五、結論 56
六、研究限制 58
七、未來展望 59
參考文獻 60
附錄 64
縮寫表 69

參考文獻

參考文獻
[1] Y. Ao, Z. Wang, J. Hu, M. Yao, and W. J. S. R. Zhang, "Identification of essential genes and immune cell infiltration in rheumatoid arthritis by bioinformatics analysis," vol. 13, no. 1, p. 2032, 2023.
[2] D. Wu et al., "Systemic complications of rheumatoid arthritis: Focus on pathogenesis and treatment," vol. 13, p. 1051082, 2022.
[3] J. Bullock et al., "Rheumatoid arthritis: a brief overview of the treatment," vol. 27, no. 6, pp. 501-507, 2019.
[4] M. Babaahmadi et al., "Rheumatoid arthritis: the old issue, the new therapeutic approach," vol. 14, no. 1, p. 268, 2023.
[5] Y. Guan, Y. Zhang, Y. Zhu, and Y. J. S. R. Wang, "CXCL10 as a shared specific marker in rheumatoid arthritis and inflammatory bowel disease and a clue involved in the mechanism of intestinal flora in rheumatoid arthritis," vol. 13, no. 1, p. 9754, 2023.
[6] S. K. J. J. o. M. C. P. Agarwal, "Biologic agents in rheumatoid arthritis: an update for managed care professionals," vol. 17, no. 9 Supp B, pp. S14-S18, 2011.
[7] G. Litjens et al., "A survey on deep learning in medical image analysis," vol. 42, pp. 60-88, 2017.
[8] M. W. Libbrecht and W. S. J. N. R. G. Noble, "Machine learning applications in genetics and genomics," vol. 16, no. 6, pp. 321-332, 2015.
[9] E. W. Steyerberg, M. J. Eijkemans, F. E. Harrell Jr, and J. D. F. J. S. i. m. Habbema, "Prognostic modelling with logistic regression analysis: a comparison of selection and estimation methods in small data sets," vol. 19, no. 8, pp. 1059-1079, 2000.
[10] R. Diaz-Uriarte and S. A. J. a. p. q.-b. de Andres, "Variable selection from random forests: application to gene expression data," 2005.
[11] C. Ding and X. He, "K-means clustering via principal component analysis," in Proceedings of the twenty-first international conference on Machine learning, 2004, p. 29.
[12] R. Miotto, F. Wang, S. Wang, X. Jiang, and J. T. J. B. i. b. Dudley, "Deep learning for healthcare: review, opportunities and challenges," vol. 19, no. 6, pp. 1236-1246, 2018.
[13] A. E. Johnson, M. M. Ghassemi, S. Nemati, K. E. Niehaus, D. A. Clifton, and G. D. J. P. o. t. I. Clifford, "Machine learning and decision support in critical care," vol. 104, no. 2, pp. 444-466, 2016.
[14] H. Liao et al., "Use of mass spectrometry to identify protein biomarkers of disease severity in the synovial fluid and serum of patients with rheumatoid arthritis," vol. 50, no. 12, pp. 3792-3803, 2004.
[15] N. Jung et al., "LC-MS/MS-based serum proteomics reveals a distinctive signature in a rheumatoid arthritis mouse model after treatment with mesenchymal stem cells," vol. 17, no. 11, p. e0277218, 2022.
[16] J. Kedra, T. Davergne, B. Braithwaite, H. Servy, and L. J. E. R. o. C. I. Gossec, "Machine learning approaches to improve disease management of patients with rheumatoid arthritis: review and future directions," vol. 17, no. 12, pp. 1311-1321, 2021.
[17] D. W. Huang, B. T. Sherman, and R. A. J. N. p. Lempicki, "Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources," vol. 4, no. 1, pp. 44-57, 2009.
[18] W. Xiong et al., "Bioinformatics analysis and experimental validation of differential genes and pathways in bone nonunions," pp. 1-24, 2024.
[19] S. Jahangir et al., "LC-MS/MS-Based Serum Protein Profiling for Identification of Candidate Biomarkers in Pakistani Rheumatoid Arthritis Patients," vol. 12, no. 3, p. 464, 2022.
[20] Y.-J. Chen, W.-A. Chang, L.-Y. Wu, Y.-L. Hsu, C.-H. Chen, and P.-L. J. I. J. o. M. S. Kuo, "Systematic analysis of differential expression profile in rheumatoid arthritis chondrocytes using next-generation sequencing and bioinformatics approaches," vol. 15, no. 11, p. 1129, 2018.
[21] F. Wu, F. Gao, S. He, and Y. J. M. M. R. Xiao, "Identification of hub genes in chronically hypoxic myocardium using bioinformatics analysis," vol. 19, no. 5, pp. 3871-3881, 2019.
[22] Q. Qin, R. Song, P. Du, C. Gao, Q. Yao, and J.-a. J. J. o. I. R. Zhang, "Systemic proteomic analysis reveals distinct exosomal protein profiles in rheumatoid arthritis," vol. 2021, no. 1, p. 9421720, 2021.
[23] J. A. Vizcaino et al., "ProteomeXchange provides globally coordinated proteomics data submission and dissemination," vol. 32, no. 3, pp. 223-226, 2014.
[24] Y. Perez-Riverol et al., "The PRIDE database and related tools and resources in 2019: improving support for quantification data," vol. 47, no. D1, pp. D442-D450, 2019.
[25] J. Ma et al., "iProX: an integrated proteome resource," vol. 47, no. D1, pp. D1211-D1217, 2019.
[26] P. Downton et al., "Chronic inflammatory arthritis drives systemic changes in circadian energy metabolism," vol. 119, no. 18, p. e2112781119, 2022.
[27] P. Han et al., "Serum antigenome profiling reveals diagnostic models for rheumatoid arthritis," vol. 13, p. 884462, 2022.
[28] C. Hu et al., "Proteome profiling identifies serum biomarkers in rheumatoid arthritis," vol. 13, p. 865425, 2022.
[29] O. J. Arntz et al., "Profiling of plasma extracellular vesicles identifies proteins that strongly associate with patient’s global assessment of disease activity in rheumatoid arthritis," vol. 10, p. 1247778, 2024.
[30] D. Kessner, M. Chambers, R. Burke, D. Agus, and P. J. B. Mallick, "ProteoWizard: open source software for rapid proteomics tools development," vol. 24, no. 21, pp. 2534-2536, 2008.
[31] L. Kall, J. D. Canterbury, J. Weston, W. S. Noble, and M. J. J. N. m. MacCoss, "Semi-supervised learning for peptide identification from shotgun proteomics datasets," vol. 4, no. 11, pp. 923-925, 2007.
[32] A. T. Kong, F. V. Leprevost, D. M. Avtonomov, D. Mellacheruvu, and A. I. J. N. m. Nesvizhskii, "MSFragger: ultrafast and comprehensive peptide identification in mass spectrometry–based proteomics," vol. 14, no. 5, pp. 513-520, 2017.
[33] F. da Veiga Leprevost et al., "Philosopher: a versatile toolkit for shotgun proteomics data analysis," vol. 17, no. 9, pp. 869-870, 2020.
[34] F. Yu, S. E. Haynes, A. I. J. M. Nesvizhskii, and C. Proteomics, "IonQuant enables accurate and sensitive label-free quantification with FDR-controlled match-between-runs," vol. 20, 2021.
[35] G. Van Rossum and F. L. Drake, An introduction to Python. Network Theory Ltd. Bristol, 2003.
[36] S. J. L. J. o. R. i. S. N. Kappal and Formal, "Data normalization using median median absolute deviation MMAD based Z-score for robust predictions vs. min–max normalization," vol. 19, no. 4, pp. 39-44, 2019.
[37] S. Liu et al., "Fibrinogen-like protein 1 is a novel biomarker for predicting disease activity and prognosis of rheumatoid arthritis," vol. 11, p. 579228, 2020.
[38] B. J. Almokhtar and A. Elengoe, "Determination of the EGFR Gene Role in Lung Cancer Pathway using STRING and Cytoscape Software," 2024.
[39] H. Cao, Y. Fu, Z. Zhang, and W. J. F. i. P. Guo, "Unbiased transcriptome mapping and modeling identify candidate genes and compounds of osteoarthritis," vol. 13, p. 888533, 2022.
[40] T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 2016, pp. 785-794.
[41] A. Taherkhani, G. Cosma, and T. M. J. N. McGinnity, "AdaBoost-CNN: An adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning," vol. 404, pp. 351-366, 2020.
[42] L. J. M. l. Breiman, "Random forests," vol. 45, pp. 5-32, 2001.
[43] C.-Y. J. Peng, K. L. Lee, and G. M. J. T. j. o. e. r. Ingersoll, "An introduction to logistic regression analysis and reporting," vol. 96, no. 1, pp. 3-14, 2002.
[44] M.-C. Popescu, V. E. Balas, L. Perescu-Popescu, N. J. W. T. o. C. Mastorakis, and Systems, "Multilayer perceptron and neural networks," vol. 8, no. 7, pp. 579-588, 2009.
[45] V. J. S. o. E. Jakkula, Washington State University, "Tutorial on support vector machine (svm)," vol. 37, no. 2.5, p. 3, 2006.
[46] S. G. Zikiryayevna, P. U. Sunatovich, K. U. J. E. J. o. M. Azimovich, and N. Sciences, "RELATIONSHIP BETWEEN ANEMIA AND HAPTOGLOBIN GENOTYPE IN PATIENTS WITH RHEUMATOID ARTHRITIS," vol. 4, no. 10, pp. 26-32, 2024.
[47] Y. Okuda et al., "Serum amyloid A (SAA) 1, SAA 2 and apolipoprotein E isotype frequencies in rheumatoid arthritis patients with AA amyloidosis," vol. 39, no. 1, pp. 3-10, 1999.
[48] E. L. Leung et al., "Roles of serum amyloid A 1 protein isoforms in rheumatoid arthritis," vol. 10, pp. 174-182, 2022.
[49] D. Davalos and K. Akassoglou, "Fibrinogen as a key regulator of inflammation in disease," in Seminars in immunopathology, 2012, vol. 34, pp. 43-62: Springer.

指導教授

張彙音(Hui-Yin Chang)

審核日期

2025-1-2

推文