Oligomerization plays a crucial role in the structure and function of peptides and proteins, wherein sequence variations can affect the oligomeric stability of the biomolecule. In this study, an artificial neural network classifier that can predict the oligomeric state of peptides is presented, using the p53 tetramerization domain and associated mutants as the model system. The FASGAI vectors were utilized as the peptide descriptors, and the resulting binary classifier exhibits satisfactory predictive ability as demonstrated by a test set accuracy of 86%.

中文翻译：

---

通过化学人工智能预测肽的低聚状态

寡聚化在肽和蛋白质的结构和功能中起关键作用，其中序列变异会影响生物分子的寡聚稳定性。在这项研究中，使用p53四聚体结构域和相关的突变体作为模型系统，提出了一种可以预测肽的寡聚状态的人工神经网络分类器。FASGAI载体被用作肽的描述符，所得到的二元分类器表现出令人满意的预测能力，如86％的测试集准确性所证明。