| 布晓婷,曹隽喆,顾宏.基于多标签直推学习的抗菌肽及其抗菌功能预测[J].,2017,57(3):293-301 |
| 基于多标签直推学习的抗菌肽及其抗菌功能预测 |
| Prediction of antimicrobial peptides and their functional types based on multi-label transductive learning |
| |
| DOI：10.7511/dllgxb201703012 |
| 中文关键词: 抗菌肽 多标签学习 直推学习 K -spaced氨基酸对组成方法 |
| 英文关键词: antimicrobial peptides multi-label learning transductive learning composition of K -spaced amino acid pairs (CKSAAP) |
| 基金项目:国家自然科学基金资助项目(U1560102,61502074)；中国博士后科学基金资助项目(2016M591430)；大连理工大学基本科研业务费资助项目(DUT15RC(3)030). |
|
| 摘要点击次数: 1151 |
| 全文下载次数: 987 |
| 中文摘要: |
| 抗菌肽是广泛存在于生物体内的一类具有广谱抗菌作用的天然多肽，因其不易导致细菌耐药性，已成为医药界开发新型抗菌制剂的主要选择，识别出更多的抗菌肽并预测其抗菌功能具有重要意义．提出了一种基于多标签直推学习的抗菌肽及其抗菌功能的预测方法，该方法利用 K -spaced氨基酸对组成方法提取多肽特征，采用多标签学习框架和加权近邻图构建直推预测模型，通过对有标签训练样本和无标签待测样本的共同学习来提升预测性能．该方法不仅能够识别多肽是否为抗菌肽，还能同时预测出抗菌肽所具有的单种或多种抗菌功能，且适用于对多效抗菌肽和普通抗菌肽的预测．数值实验表明，与已有的iAMP-2L预测方法相比，所提方法在全局预测精度和多标签预测性能上均有较大提升． |
| 英文摘要: |
| Antimicrobial peptides, a type of natural polypeptides with broad-spectrum antimicrobial activity, are widely found in organisms. Because of a slim chance of bacterial resistance, antimicrobial peptides have become a preferred option for the pharmaceutical industry to develop new antibacterial preparations. In this sense, it is of great significance to identify more antimicrobial peptides and then make clear their antimicrobial functional types. In view of this fact, a prediction method based on multi-label transductive learning is proposed to predict antimicrobial peptides and their functional types. This method extracts the polypeptide characteristics by composition of K -spaced amino acid pairs and constructs transductive prediction models by the weighted neighbor graph and multi-label learning framework. Through the study of labeled training data and unlabeled data to be tested, this method can not only predict whether a polypeptide is an antimicrobial peptide, but also predict what type of antimicrobial function a polypeptide would have. In addition, this method is applicable to both multiple-effect antimicrobial peptides and common antimicrobial peptides. Numerical experiments have shown that the proposed method is more accurate than iAMP-2L method in performance in terms of overall prediction and multi-label prediction. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|