Feedback-AVPGAN: Feedback-guided generative adversarial network for generating antiviral peptides
Feedback-AVPGAN: Feedback-guided generative adversarial network for generating antiviral peptides
复制标题
Feedback-AVPGAN：反馈引导的生成对抗网络，用于生成抗病毒肽
DOI：
10.1142/s0219720022500263
复制
发表时间：
2022
影响因子：
1
通讯作者：
Kentaro Shimizu
中科院分区：
文献类型：
--
作者：
1.Kano Hasegawa;Yoshitaka Moriwaki;Tohru Terada;Cao Wei;Kentaro Shimizu
在这项研究中，我们提出了Feedback-AVPGAN，一个旨在计算生成新型抗病毒肽（AVP）的系统。该系统依赖于生成对抗网络（GAN）模型和反馈方法的关键前提。GAN是一种使用深度学习方法的生成式建模方法，包括生成器和迭代器。发生器用于生成肽;将生成的蛋白质进料至酶以区分AVP和非AVP。最初的GAN设计使用实际数据来训练神经网络。然而，并没有很多AVP已实验获得。为了解决这个问题，我们使用了反馈方法，允许机器人从现有的以及生成的合成数据中学习。我们使用分类器模块实现了这种方法，该模块将GAN生成器生成的每个肽序列分类为AVP或非AVP。该分类器采用Transformer网络，分类精度高。这种机制使得能够有效地产生具有高概率表现出抗病毒活性的肽。使用反馈方法，我们评估了各种算法及其性能。此外，我们使用AlphaFold 2对生成的肽的结构进行建模，并确定了与已知AVP具有相似的物理化学性质和结构的肽，尽管具有不同的序列。
In this study, we proposeFeedback-AVPGAN, a system that aims to computationally generate novel antiviral peptides (AVPs). This system relies on the key premise of the Generative Adversarial Network (GAN) model and the Feedback method. GAN, a generative modeling approach that uses deep learning methods, comprises a generator and a discriminator. The generator is used to generate peptides; the generated proteins are fed to the discriminator to distinguish between the AVPs and non-AVPs. The original GAN design uses actual data to train the discriminator. However, not many AVPs have been experimentally obtained. To solve this problem, we used the Feedback method to allow the discriminator to learn from the existing as well as generated synthetic data. We implemented this method using a classifier module that classifies each peptide sequence generated by the GAN generator as AVP or non-AVP. The classifier uses the transformer network and achieves high classification accuracy. This mechanism enables the efficient generation of peptides with a high probability of exhibiting antiviral activity. Using the Feedback method, we evaluated various algorithms and their performance. Moreover, we modeled the structure of the generated peptides using AlphaFold2 and determined the peptides having similar physicochemical properties and structures to those of known AVPs, although with different sequences.