arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08341q-bio.QMcs.AIcs.LG
收藏

利用蛋白质语言模型探索潜在空间以生成肽类似物

Exploring Latent Space for Generating Peptide Analogs Using Protein Language Models

University of Cincinnati(辛辛那提大学);University of Connecticut(康涅狄格大学)

Po-Yu Liang, Xueting Huang, Tibo Duran, Andrew J. Wiemer, Jun Bai

AI总结:

针对传统肽生成方法依赖大量数据集的问题,提出利用自编码器结构模型探索蛋白质嵌入空间、结合蛋白质语言模型生成肽类似物的新方法,仅需单条目标序列,在多项相似性指标上优于基线,经TIGIT抑制剂验证可提升肽筛选效率。

摘要:

生成具有期望特性的肽对药物发现和生物技术至关重要。传统的基于序列和基于结构的方法通常需要大量数据集,这限制了其有效性。本研究中,我们提出了一种新方法,利用自编码器(autoencoder)结构的模型探索蛋白质嵌入空间,并借助蛋白质语言模型生成新型肽类似物。该方法仅需一条目标序列,无需大型数据集。我们的结果显示,在肽结构、描述符和生物活性的相似性指标上,该方法较基线模型有显著提升。通过对TIGIT抑制剂进行分子动力学模拟验证,我们的方法能生成特性相似却又存在差异的肽类似物,凸显了其增强肽筛选流程的潜力。

英文摘要:

Generating peptides with desired properties is crucial for drug discovery and biotechnology. Traditional sequence-based and structure-based methods often require extensive datasets, which limits their effectiveness. In this study, we proposed a novel method that utilized autoencoder shaped models to explore the protein embedding space, and generate novel peptide analogs by leveraging protein language models. The proposed method requires only a single sequence of interest, avoiding the need for large datasets. Our results show significant improvements over baseline models in similarity indicators of peptide structures, descriptors and bioactivities. The proposed method validated through Molecular Dynamics simulations on TIGIT inhibitors, demonstrates that our method produces peptide analogs with similar yet distinct properties, highlighting its potential to enhance peptide screening processes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑