Abstract：
Recent advancements in biomaterial research conduct artificial intelligence for predicting diverse material properties. However, research predicting the mechanical properties of biomaterial based on amino acid sequences have been notably absent. This research pioneers the use of classification models to predict ultimate tensile strength from silk fiber amino acid sequences, employing logistic regression, support vector machines with various kernels, and a deep neural network (DNN). Remarkably, the model demonstrates a high accuracy of 0.83 during the generalization test. The study introduces an innovative approach to predicting biomaterial mechanical properties beyond traditional experimental methods. Recognizing the limitations of conventional linear prediction models, the research emphasizes the future trajectory toward DNNs that can adeptly capture non-linear relationships with high precision. Moreover, through comprehensive performance comparisons among diverse prediction models, the study offers insights into the effectiveness of specific models for predicting the mechanical properties of certain materials. In conclusion, this study serves as a pioneering contribution, laying the groundwork for future endeavors and advocating for the seamless integration of AI methodologies into materials research.
摘要：
生物材料研究的最新进展为预测各种材料特性提供了人工智能。然而,基于氨基酸序列预测生物材料力学性能的研究一直缺乏。这项研究率先使用分类模型来预测丝纤维氨基酸序列的极限拉伸强度，采用逻辑回归，具有各种内核的支持向量机，和深度神经网络(DNN)。值得注意的是,该模型在泛化测试中表现出0.83的高精度。该研究引入了一种超越传统实验方法的创新方法来预测生物材料力学特性。认识到传统线性预测模型的局限性，该研究强调了未来的DNN轨迹，可以以高精度巧妙地捕获非线性关系。此外，通过不同预测模型之间的综合性能比较，该研究提供了对预测某些材料的机械性能的特定模型的有效性的见解。总之,这项研究是一项开创性的贡献，为未来的努力奠定基础，并倡导将人工智能方法无缝集成到材料研究中。
