English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 45065/58241 (77%)
造訪人次 : 2245850      線上人數 : 495
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://libir.tmu.edu.tw/handle/987654321/61232


    題名: 建立隨機森林模型以全基因體定序資料預測沙門氏菌抗藥性
    Using Random Forest to Predict Antimicrobial Resistance for Salmonella Based on Whole Genome Sequencing Data
    作者: 周哲宇
    CHOU, CHE-YU
    貢獻者: 大數據科技及管理研究所碩士班
    童俊維
    關鍵詞: 沙門氏菌抗藥性;全基因體定序;隨機森林;機器學習
    Antimicrobial resistance;Machine learning;Random forest;Salmonella;Whole-genome sequencing
    日期: 2021-07-09
    上傳時間: 2021-12-29 15:09:15 (UTC+8)
    摘要: 近年來抗生素濫用的問題日益嚴重導致各種致病細菌的抗藥性提升,沙門氏菌 (Salmonellaenterica) 是在全球常見的腸胃道感染菌種,若是感染沙門氏菌會有急性腸胃炎的症狀產生,在世界衛生組織 (World Health Organization, WHO) 的報告中提到每年在世界各國都有大量的沙門氏菌感染確診個數,多個研究顯示許多沙門氏菌已經對多個抗生素產生抗藥性。目前國際上在生物資訊領域越來越多使用全基因體定序(Whole-genome-sequencing, WGS) 資料分析的研究,使得全基因體定序資料應用的領域越來越廣,在細菌抗藥性的研究中也會透過全基因體定序了解菌種的基因片段資訊,並從基因片段資訊中得到細菌與抗生素的關聯性。本研究以國內蒐集的 321 筆沙門氏菌菌株全基因體資料與 24 個抗生素對各菌株的最小抑制濃度 (Minimum inhibitory concentration, MIC) 來建構機器學習模型,以全基因體資料萃取的特徵預測 MIC 值,利用訓練資料建立針對各抗生素的 24 個隨機森林 (Random Forest) 模型,並進行獨立測試結果得到預測 MIC 值的平均誤差為 0.919,並且將 MIC 值與國際上抗藥性閾值比較,判斷菌株是否具有抗藥性的平均正確率達 90%以上,也與國際上現行的抗藥性分析方法比較並且有更好的表現;為了使模型能夠應用於實務上,達到快速且有效判斷菌株是否具有抗藥性預測,將計量特徵轉換為二元特徵並且找出少數重要的特徵重新建立模型,也有很好的預測表現,最後藉由兩種資料的模型重要特徵找出共同影響多種抗生素抗藥性的 183 個重要基因。
    Due to the antibiotic abuse problem, the antimicrobial resistance of various pathogenic bacteria has increased in recent years. Salmonella is a species commonly found in the gastrointestinal tract. The WHO report mentioned that there are a large number of people confirmed Salmonella infections around the world every year. Some research indicated that Salmonella has developed resistance to antibiotics. Whole-genome sequencing is a trend in bioinformatics, especially in the research of microbial drug resistance. In this study, we developed machine learning models for predicting antimicrobial resistance based on the whole-genome sequencing data of Salmonella. The independent test results showed an average accuracy rate of over 90%. Models were also used to explore the important gene fragments that affect the antimicrobial resistance of Salmonella. In addition, we compared the developed models with state- of-the-art methods and showed a superior performance of our method. In order to enable the model to be applied in practice and to quickly and effectively determine whether the strain has resistance or not, we converted the measurement features into binary features and further identified important features to retrain the model. The retrained model also has a good predictive performance. Finally, the important features of the models identify 183 important genes that affect multiple antibiotics resistance.
    描述: 碩士
    指導教授:童俊維
    委員:王家琪
    委員:張詠淳
    資料類型: thesis
    顯示於類別:[大數據科技及管理研究所] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML181檢視/開啟


    在TMUIR中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    著作權聲明 Copyright Notice
    • 本平台之數位內容為臺北醫學大學所收錄之機構典藏,包含體系內各式學術著作及學術產出。秉持開放取用的精神,提供使用者進行資料檢索、下載與取用,惟仍請適度、合理地於合法範圍內使用本平台之內容,以尊重著作權人之權益。商業上之利用,請先取得著作權人之授權。

      The digital content on this platform is part of the Taipei Medical University Institutional Repository, featuring various academic works and outputs from the institution. It offers free access to academic research and public education for non-commercial use. Please use the content appropriately and within legal boundaries to respect copyright owners' rights. For commercial use, please obtain prior authorization from the copyright owner.

    • 瀏覽或使用本平台,視同使用者已完全接受並瞭解聲明中所有規範、中華民國相關法規、一切國際網路規定及使用慣例,並不得為任何不法目的使用TMUIR。

      By utilising the platform, users are deemed to have fully accepted and understood all the regulations set out in the statement, relevant laws of the Republic of China, all international internet regulations, and usage conventions. Furthermore, users must not use TMUIR for any illegal purposes.

    • 本平台盡力防止侵害著作權人之權益。若發現本平台之數位內容有侵害著作權人權益情事者,煩請權利人通知本平台維護人員([email protected]),將立即採取移除該數位著作等補救措施。

      TMUIR is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff([email protected]). We will remove the work from the repository.

    Back to Top
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋