學術產出-Theses
Article View/Open
Publication Export
-
題名 糖質體學資料探勘與自動化分析
Data Mining and Automated Analysis in Glycomics作者 曾偉綱
Kang, Tseng Wei貢獻者 張家銘
chang, jia-ming
曾偉綱
Tseng Wei Kang關鍵詞 人工智慧
資料探勘
質譜儀
機器學習
分子結構預測
Artificial Intelligence
Data Mining
Mass Spectrometry
Machine Learning
Molecular Structure Prediction日期 2024 上傳時間 1-Mar-2024 13:41:06 (UTC+8) 摘要 本研究致力於透過液相層析串聯質譜(LC-MS/MS)自動識別與分析醣鏈結構。應用資料探勘和機器學習技術,我們分析了斑馬魚腦與卵巢組織的數據集。相較於人工分析,我們的方法顯著提高了從龐大數據中定位樣本的效率,證明了其可行性。特別是,我們的方法大幅縮短了生物學家進行分析的時間,將原本需要30小時的任務縮減至幾秒內完成。這一成就強調了我們方法提升效率的潛力。最終,我們驗證了隨機森林模型在此問題上為各類別提供了最合適的模型,並具有跨組織樣本識別能力。它能有效識別訓練數據中未出現的組織中的醣鏈,證明了這一工具的實用應用性。總之,這項研究為深入理解和分析質譜儀產生的醣數據提供了一種快速且實用的工具,為未來研究的應用和方法的改進開辟了新的途徑。
This study focused on automatically identifying and analyzing glycan structures based on liquid chromatography/tandem mass spectrometry (LC-MS/MS). By applying data mining and machine learning techniques, we analyzed the zebrafish Brain and Ovary tissue datasets. Our methods enhanced the efficiency of targeting samples from vast data compared to human efforts, thus demonstrating their viability. Specifically, our approach has significantly expedited the time-consuming analysis process for a biologist, reducing tasks that traditionally took 30 hours to mere seconds. This achievement underscores the efficiency-enhancing potential of our method. Ultimately, we have validated that the Random Forest model in this problem offers a generally most suitable model for various categories and possesses cross-tissue sample identification capabilities. It can effectively recognize glycans in tissues not present in the training data, proving the practical applicability of this tool. In summary, the research provides a rapid and pragmatic tool for a deeper understanding and analysis of glycan data produced by mass spectrometers, promising new avenues for future research application and refinement of this method.參考文獻 1. Interpreting Mass Spectra Retrieved January 2, 2024, from Spectrahttps://chem.libretexts.org/Courses/Athabasca_University/Chemistry_350 %3A_Organic_Chemistry_I/12%3A_Structure_Determination- _Mass_Spectrometry_and_Infrared_Spectroscopy/12.02%3A_Interpreting_Mass_Spectra 2. Urban, J., Jin, C., Thomsson, K. A., Karlsson, N. G., Ives, C. M., Fadda, E., & Bojar, D. (2023). Predicting glycan structure from tandem mass spectrometry via deep learning. bioRxiv. https://doi.org/10.1101/2023.06.13.544793 3. Burkholz, R., Quackenbush, J., & Bojar, D. (2021). Using graph convolutional neural networks to learn a representation for glycans. Elsevier, Volume 35, Issue 11, 15 June 2021, 109251. 4. weka.classifiers.rules OneR Retrieved July 26, 2023, from https://weka.sourceforge.io/doc.dev/weka/classifiers/rules/OneR.html 5. Glycoworkbench. (n.d.). Retrieved July 26, 2023, from https://code.google.com/archive/p/glycoworkbench/ 6. Ceroni, A., Maass, K., Geyer, H., Geyer, R., Dell, A., Haslam, SM. GlycoWorkbench: a tool for the computer-assisted annotation of mass spectra of glycans. Journal of Proteome Research. 2008 Apr;7(4):1650-9. doi: 10.1021/pr7008252. Epub 2008 Mar 1. PMID: 18311910. https://pubmed.ncbi.nlm.nih.gov/18311910/ 7. Varki, A., Cummings, R. D., Esko, J. D., Stanley, P., Hart, G. W., Aebi, M., Darvill, A. G., Kinoshita, T., Packer, N. H., Prestegard, J. H., Schnaar, R. L., & Seeberger, P. H. (2015). Essentials of Glycobiology. Cold Spring Harbor Laboratory Press. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4104780/ 描述 碩士
國立政治大學
資訊科學系
108753122資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108753122 資料類型 thesis dc.contributor.advisor 張家銘 zh_TW dc.contributor.advisor chang, jia-ming en_US dc.contributor.author (Authors) 曾偉綱 zh_TW dc.contributor.author (Authors) Tseng Wei Kang en_US dc.creator (作者) 曾偉綱 zh_TW dc.creator (作者) Kang, Tseng Wei en_US dc.date (日期) 2024 en_US dc.date.accessioned 1-Mar-2024 13:41:06 (UTC+8) - dc.date.available 1-Mar-2024 13:41:06 (UTC+8) - dc.date.issued (上傳時間) 1-Mar-2024 13:41:06 (UTC+8) - dc.identifier (Other Identifiers) G0108753122 en_US dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150165 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 108753122 zh_TW dc.description.abstract (摘要) 本研究致力於透過液相層析串聯質譜(LC-MS/MS)自動識別與分析醣鏈結構。應用資料探勘和機器學習技術,我們分析了斑馬魚腦與卵巢組織的數據集。相較於人工分析,我們的方法顯著提高了從龐大數據中定位樣本的效率,證明了其可行性。特別是,我們的方法大幅縮短了生物學家進行分析的時間,將原本需要30小時的任務縮減至幾秒內完成。這一成就強調了我們方法提升效率的潛力。最終,我們驗證了隨機森林模型在此問題上為各類別提供了最合適的模型,並具有跨組織樣本識別能力。它能有效識別訓練數據中未出現的組織中的醣鏈,證明了這一工具的實用應用性。總之,這項研究為深入理解和分析質譜儀產生的醣數據提供了一種快速且實用的工具,為未來研究的應用和方法的改進開辟了新的途徑。 zh_TW dc.description.abstract (摘要) This study focused on automatically identifying and analyzing glycan structures based on liquid chromatography/tandem mass spectrometry (LC-MS/MS). By applying data mining and machine learning techniques, we analyzed the zebrafish Brain and Ovary tissue datasets. Our methods enhanced the efficiency of targeting samples from vast data compared to human efforts, thus demonstrating their viability. Specifically, our approach has significantly expedited the time-consuming analysis process for a biologist, reducing tasks that traditionally took 30 hours to mere seconds. This achievement underscores the efficiency-enhancing potential of our method. Ultimately, we have validated that the Random Forest model in this problem offers a generally most suitable model for various categories and possesses cross-tissue sample identification capabilities. It can effectively recognize glycans in tissues not present in the training data, proving the practical applicability of this tool. In summary, the research provides a rapid and pragmatic tool for a deeper understanding and analysis of glycan data produced by mass spectrometers, promising new avenues for future research application and refinement of this method. en_US dc.description.tableofcontents Table of Contents 1. Introduction 1 1.1 Glycomics 1 1.2 Tandem Mass Spectrometry 1 1.4 Automated Approach to Glycomics3 2. Related work 4 3. Method 6 3.1 Datasets 6 3.2 Tools 9 3.3 Data Exploration 10 3.4 Evaluation Metrics 12 4. Data Processing 13 4.1 Feature Selection 13 4.2 Mass Error Calibration 14 4.3 Applying Biological Knowledge-based Formulas 16 4.4 Log Normalization 17 5. Results 18 5.1 Rule-based Model 18 5.2 OneR Model 20 5.3 Model Selection 23 5.4 Random Forest 24 6. Conclusion 29 References 30 zh_TW dc.format.extent 1935747 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108753122 en_US dc.subject (關鍵詞) 人工智慧 zh_TW dc.subject (關鍵詞) 資料探勘 zh_TW dc.subject (關鍵詞) 質譜儀 zh_TW dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) 分子結構預測 zh_TW dc.subject (關鍵詞) Artificial Intelligence en_US dc.subject (關鍵詞) Data Mining en_US dc.subject (關鍵詞) Mass Spectrometry en_US dc.subject (關鍵詞) Machine Learning en_US dc.subject (關鍵詞) Molecular Structure Prediction en_US dc.title (題名) 糖質體學資料探勘與自動化分析 zh_TW dc.title (題名) Data Mining and Automated Analysis in Glycomics en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Interpreting Mass Spectra Retrieved January 2, 2024, from Spectrahttps://chem.libretexts.org/Courses/Athabasca_University/Chemistry_350 %3A_Organic_Chemistry_I/12%3A_Structure_Determination- _Mass_Spectrometry_and_Infrared_Spectroscopy/12.02%3A_Interpreting_Mass_Spectra 2. Urban, J., Jin, C., Thomsson, K. A., Karlsson, N. G., Ives, C. M., Fadda, E., & Bojar, D. (2023). Predicting glycan structure from tandem mass spectrometry via deep learning. bioRxiv. https://doi.org/10.1101/2023.06.13.544793 3. Burkholz, R., Quackenbush, J., & Bojar, D. (2021). Using graph convolutional neural networks to learn a representation for glycans. Elsevier, Volume 35, Issue 11, 15 June 2021, 109251. 4. weka.classifiers.rules OneR Retrieved July 26, 2023, from https://weka.sourceforge.io/doc.dev/weka/classifiers/rules/OneR.html 5. Glycoworkbench. (n.d.). Retrieved July 26, 2023, from https://code.google.com/archive/p/glycoworkbench/ 6. Ceroni, A., Maass, K., Geyer, H., Geyer, R., Dell, A., Haslam, SM. GlycoWorkbench: a tool for the computer-assisted annotation of mass spectra of glycans. Journal of Proteome Research. 2008 Apr;7(4):1650-9. doi: 10.1021/pr7008252. Epub 2008 Mar 1. PMID: 18311910. https://pubmed.ncbi.nlm.nih.gov/18311910/ 7. Varki, A., Cummings, R. D., Esko, J. D., Stanley, P., Hart, G. W., Aebi, M., Darvill, A. G., Kinoshita, T., Packer, N. H., Prestegard, J. H., Schnaar, R. L., & Seeberger, P. H. (2015). Essentials of Glycobiology. Cold Spring Harbor Laboratory Press. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4104780/ zh_TW