The National and Local Joint Engineering Laboratory of Animal Peptide Drug Development, College of Life Sciences, Hunan Normal University, Changsha, 410081, China; Peptide and Small Molecule Drug R&D Plateform, Furong Laboratory, Hunan Normal University, Changsha, 410081, Hunan, China; Institute of Interdisciplinary Studies, Hunan Normal University, Changsha, 410081, China.
The National and Local Joint Engineering Laboratory of Animal Peptide Drug Development, College of Life Sciences, Hunan Normal University, Changsha, 410081, China; Peptide and Small Molecule Drug R&D Plateform, Furong Laboratory, Hunan Normal University, Changsha, 410081, Hunan, China; Institute of Interdisciplinary Studies, Hunan Normal University, Changsha, 410081, China.
Comput Biol Med. 2024 Sep;180:109013. doi: 10.1016/j.compbiomed.2024.109013. Epub 2024 Aug 12.
Antidiabetic peptides (ADPs), peptides with potential antidiabetic activity, hold significant importance in the treatment and control of diabetes. Despite their therapeutic potential, the discovery and prediction of ADPs remain challenging due to limited data, the complex nature of peptide functions, and the expensive and time-consuming nature of traditional wet lab experiments. This study aims to address these challenges by exploring methods for the discovery and prediction of ADPs using advanced deep learning techniques. Specifically, we developed two models: a single-channel CNN and a three-channel neural network (CNN + RNN + Bi-LSTM). ADPs were primarily gathered from the BioDADPep database, alongside thousands of non-ADPs sourced from anticancer, antibacterial, and antiviral peptide datasets. Subsequently, data preprocessing was performed with the evolutionary scale model (ESM-2), followed by model training and evaluation through 10-fold cross-validation. Furthermore, this work collected a series of newly published ADPs as an independent test set through literature review, and found that the CNN model achieved the highest accuracy (90.48 %) in predicting the independent test set, surpassing existing ADP prediction tools. Finally, the application of the model was considered. SeqGAN was used to generate new candidate ADPs, followed by screening with the constructed CNN model. Selected peptides were then evaluated using physicochemical property prediction and structural forecasts for pharmaceutical potential. In summary, this study not only established robust ADP prediction models but also employed these models to screen a batch of potential ADPs, addressing a critical need in the field of peptide-based antidiabetic research.
抗糖尿病肽（ADPs）是具有潜在抗糖尿病活性的肽，在糖尿病的治疗和控制中具有重要意义。尽管它们具有治疗潜力，但由于数据有限、肽功能的复杂性以及传统湿实验室实验昂贵且耗时，ADPs 的发现和预测仍然具有挑战性。本研究旨在通过探索使用先进的深度学习技术发现和预测 ADPs 的方法来解决这些挑战。具体来说，我们开发了两种模型：单通道 CNN 和三通道神经网络（CNN+RNN+Bi-LSTM）。ADPs 主要从 BioDADPep 数据库中收集，同时还从抗癌、抗菌和抗病毒肽数据集中收集了数千种非 ADPs。随后，使用进化尺度模型（ESM-2）进行数据预处理，然后通过 10 倍交叉验证进行模型训练和评估。此外，这项工作通过文献回顾收集了一系列新发表的 ADPs 作为独立测试集，并发现 CNN 模型在预测独立测试集方面达到了最高的准确性（90.48%），超过了现有的 ADP 预测工具。最后，考虑了模型的应用。使用 SeqGAN 生成新的候选 ADPs，然后用构建的 CNN 模型进行筛选。选择的肽然后使用物理化学性质预测和药物潜力的结构预测进行评估。总之，本研究不仅建立了稳健的 ADP 预测模型，还利用这些模型筛选了一批潜在的 ADPs，满足了肽类抗糖尿病研究领域的关键需求。
