Development of a Machine Learning-Based Predictive Model for Helical Antimicrobial Peptides Against Specific Strains

NCU Institutional Repository > 理學院 > 化學研究所 > 博碩士論文 > Item 987654321/91961

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/91961

题名:	Development of a Machine Learning-Based Predictive Model for Helical Antimicrobial Peptides Against Specific Strains
作者:	蔡政庭;Tsai, Cheng-Ting
贡献者:	化學學系
关键词:	機器學習;抗菌肽;三維結構;預測模型;LightGBM;AMP-META;Machine Learning;Antimicrobial peptides;3D structure;Predictive model;LightGBM;AMP-META
日期:	2023-07-13
上传时间:	2024-09-19 14:44:05 (UTC+8)
出版者:	國立中央大學
摘要:	過度使用抗生素已導致多重藥物耐藥（MDR）病原體的出現，對公共衛生造成了重大威脅。從結構和化學上多樣的化合物中衍生出的抗微生物肽（AMPs）為解決這個問題提供了一個有前途的解決方案。然而，由於流體膜中結構-功能關係的動態性質，鑒定有效的 AMPs 一直具有挑戰性。機器學習（ML）算法已被應用來應對這一挑戰，我們使用 ML 基於螺旋狀AMP 序列訓練了一個預測模型，以針對特定的細菌進行靶向。已開發了多種 ML 模型來預測 AMPs。然而，這些方法大多主要依賴於氨基酸序列，對於預測針對特定菌株的抗微生物活性，僅有限地納入了 3D 結構特徵和 ML 模型內的特定相互作用。在本研究中，我們提出了一個線性 AMP 的預測模型，該模型包括以下重要特徵：（i）透過圖論將AMP 的 3D 結構進行比較；（ii）根據分子動力學模擬推導出的特定相互作用的實現；（iii）考慮到細菌的負電性特性的 AMP 膜插入模型。此外，我們的預測模型已經開發出來區分對特定菌株具有活性的肽與其他肽，從而增強了 AMP 開發中的特異性。此外，我們還使用了低序列識別的肽來評估我們模型的準確性。我們的預測模型可以快速設計出有效的 AMPs。設計了 7 個潛在的 AMPs 並進行了體外細胞實驗，顯示成功率高達 71 ％，以提高 AMPs 的抗菌效果。 AMP-META 可免費訪問 http://ai- meta.chem.ncu.edu.tw/amp-meta;Excessive use of antibiotics has led to the emergence of multidrug-resistant (MDR) pathogens, which pose a significant threat to public health. Antimicrobial peptides (AMPs) derived from structurally and chemically diverse compounds offer a promising solution to combat this problem. However, identifying effective AMPs has been challenging due to the dynamic nature of structure-function relationships in fluid membranes. Machine learning (ML) algorithms have been employed to address this challenge, and we trained a predictive model based on helical AMP sequences using ML to target specific bacteria. Various ML models have been developed to predict AMPs. However, most of these methods have primarily relied on amino acid sequences, with limited incorporation of 3D structural features and specific interactions within ML models to predict antimicrobial potency against specific strains. In this study, we present a predictive model for linear AMPs, which incorporates the following significant features: (i) Graph theory considerations, taking into account the native contacts of 3D AMPs; (ii) Implementation of specific interactions derived from molecular dynamics simulations; and (iii) Incorporation of a membrane-insertion model of AMPs that considers the negatively-charged nature of bacteria. Furthermore, our predictive model has been developed to differentiate peptides that are active against particular strains from others, thereby enhancing the specificity in AMP development. Additionally, low-sequence-identified peptides were employed to evaluate the accuracy of our model. Our predictive models enable rapid engineering of potent AMPs. Designed 7 potential AMPs and conducted in vitro cell experiments, showing a success rate of up to 71% to improve the antibacterial effect of AMPs. AMP-META is freely accessible at http://ai-meta.chem.ncu.edu.tw/amp-meta
显示于类别:	[化學研究所] 博碩士論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	21	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....