Machine learning-guided discovery and design of non-hemolytic peptides.
Machine learning-guided discovery and design of non-hemolytic peptides.
复制标题
DOI：
10.1038/s41598-020-73644-6
复制
发表时间：
2020-10-06
影响因子：
4.6
通讯作者：
Martínez-Hernández C
中科院分区：
文献类型：
--
作者：
Plisson F;Ramírez-Sánchez O;Martínez-Hernández C
减少临床试验的障碍而不损害候选肽的治疗承诺成为基于肽的药物设计的重要步骤。机器学习模型是用于从初级序列预测生物活性的具有成本效益且节省时间的策略。它们的局限性在于这些模型中肽序列和生物信息的多样性。需要额外的离群值检测方法来设置可靠预测的边界;适用性域。抗菌肽（Antimicrobial peptides，AMP）是一种广泛的肽库，为抗耐药菌感染提供了有希望的途径。临床试验中存在的大多数AMP由于其溶血毒性而局部施用。在这里，我们开发了机器学习模型和离群值检测方法，确保对AMP的发现和溶血活性降低的新型肽的设计进行稳健的预测。我们最好的模型，梯度提升分类器，预测任何肽序列的溶血性，准确率为95-97%。近70%的AMP被预测为溶血肽。应用多变量离群值检测模型，我们发现273例AMP（~ 9%）无法可靠预测。我们的组合方法导致了34个高置信度的非溶血性天然AMP的发现，507个非溶血性肽的从头设计，以及非溶血性肽设计的指南。
Reducing hurdles to clinical trials without compromising the therapeutic promises of peptide candidates becomes an essential step in peptide-based drug design. Machine-learning models are cost-effective and time-saving strategies used to predict biological activities from primary sequences. Their limitations lie in the diversity of peptide sequences and biological information within these models. Additional outlier detection methods are needed to set the boundaries for reliable predictions; the applicability domain. Antimicrobial peptides (AMPs) constitute an extensive library of peptides offering promising avenues against antibiotic-resistant infections. Most AMPs present in clinical trials are administrated topically due to their hemolytic toxicity. Here we developed machine learning models and outlier detection methods that ensure robust predictions for the discovery of AMPs and the design of novel peptides with reduced hemolytic activity. Our best models, gradient boosting classifiers, predicted the hemolytic nature from any peptide sequence with 95–97% accuracy. Nearly 70% of AMPs were predicted as hemolytic peptides. Applying multivariate outlier detection models, we found that 273 AMPs (~ 9%) could not be predicted reliably. Our combined approach led to the discovery of 34 high-confidence non-hemolytic natural AMPs, the de novo design of 507 non-hemolytic peptides, and the guidelines for non-hemolytic peptide design.
登录
查看更多内容
影响因子：
14.9
作者：
Gautam A;Chaudhary K;Singh S;Joshi A;Anand P;Tuknait A;Mathur D;Varshney GC;Raghava GP
通讯作者：
Raghava GP
影响因子：
2.8
作者：
Jungo, Florence;Bougueleret, Lydie;Xenarios, Ioannis;Poux, Sylvain
通讯作者：
Poux, Sylvain
影响因子：
5.8
作者：
Hasan, Md. Mehedi;Schaduangrat, Nalini;Manavalan, Balachandran
通讯作者：
Manavalan, Balachandran
影响因子：
5.6
作者：
Guimaraes, Cristiano R. W.;Mathiowetz, Alan M.;Liras, Spiros
通讯作者：
Liras, Spiros
影响因子：
2.9
作者：
Conlon, J. Michael;Mechkarska, Milena;Padgett-Flohr, Gretchen
通讯作者：
Padgett-Flohr, Gretchen