Peptidy：一个用于机器学习中肽表示的轻量级Python库。
peptidy: a light-weight Python library for peptide representation in machine learning.
作者信息
Özçelik Rıza, van Weesep Laura, de Ruiter Sarah, Grisoni Francesca
机构信息
Department of Biomedical Engineering, Institute for Complex Molecular Systems, Eindhoven University of Technology, Eindhoven 5612AZ, Netherlands.
Centre for Living Technologies, Alliance TU/e, WUR, UU, UMC Utrech, Utrecht 3584CB, Netherlands.
出版信息
Bioinform Adv. 2025 Mar 21;5(1):vbaf058. doi: 10.1093/bioadv/vbaf058. eCollection 2025.
MOTIVATION
Peptides are widely used in applications ranging from drug discovery to food technologies. Machine learning has become increasingly prominent in accelerating the search for new peptides, and user-friendly computational tools can further enhance these efforts.
RESULTS
In this work, we introduce peptidy-a lightweight Python library that facilitates converting peptides (expressed as amino acid sequences) to numerical representations suited to machine learning. peptidy is free from external dependencies, integrates seamlessly into modern Python environments, and supports a range of encoding strategies suitable for both predictive and generative machine learning approaches. Additionally, peptidy supports peptides with post-translational modifications, such as phosphorylation, acetylation, and methylation, thereby extending the functionality of existing Python packages for peptides and proteins.
AVAILABILITY AND IMPLEMENTATION
peptidy is freely available with a permissive license on GitHub at the following URL: https://github.com/molML/peptidy.
动机
肽广泛应用于从药物发现到食品技术等诸多领域。机器学习在加速新型肽的搜索方面变得越来越重要，而用户友好的计算工具可以进一步推动这些工作。
结果
在这项工作中，我们介绍了peptidy——一个轻量级的Python库，它有助于将肽（表示为氨基酸序列）转换为适合机器学习的数值表示形式。peptidy没有外部依赖项，能无缝集成到现代Python环境中，并支持一系列适用于预测性和生成性机器学习方法的编码策略。此外，peptidy支持具有翻译后修饰（如磷酸化、乙酰化和甲基化）的肽，从而扩展了现有用于肽和蛋白质的Python软件包的功能。
可用性和实现方式
peptidy可在GitHub上以宽松许可免费获取，网址如下：https://github.com/molML/peptidy 。
Zotero 插件