Artificial Intelligence Research Center, Chang Gung University, Kweishan District, Taoyuan City 33302, Taiwan.
Department of Computer Science and Information Engineering, Chang Gung University, Kweishan District, Taoyuan City 33302, Taiwan.
Anal Chem. 2022 Jul 26;94(29):10427-10434. doi: 10.1021/acs.analchem.2c01620. Epub 2022 Jul 14.
Recently, the deep learning (DL) dimension of artificial intelligence has received much attention from biochemical researchers and thus has gradually become the key approach adopted in the area of biosensing applications. Studies have shown that the use of DL techniques for sensing can not only shorten the time of data analysis but also significantly increase the accuracy of data analysis and prediction, resulting in the performance improvement of biosensing systems in comparison to conventional methods. However, obtaining reliable equilibrium and rate constants of biomolecular interactions during the detection process remains difficult and time-consuming to date. In this study, we propose a transformed model based on the deep transfer learning and sequence-to-sequence autoencoder that can successfully transfer the SPR sensorgram to the protein-binding constants, that is, the association rate constant () and dissociation rate constant (), which provide crucial information to understand the mechanisms of drug action and the functional structures of biomolecules. Experimentally, we first trained and tested the pre-trained model using the Langmuir model which generated ideal SPR sensorgrams and then we fine-tuned the pre-trained model through the augmented SPR sensorgrams which were synthesized by using the synthesized minority oversampling technique (SMOTE) through the moderate-scale experiment. Next, the fine-tuned model was inputted with a short experimental SPR sensorgram that only needs 110 s, and the sensorgram was directly transformed into a reconstructed ideal sensorgram. Finally, the binding kinetic constants, that is, and , as outputs, were obtained through fitting the reconstructed ideal sensorgram. The results showed that the prediction errors of and obtained by our model were less than 12 and 24%, respectively. Based on the convenience, accuracy, and reliability of the proposed DL approach, we believe our strategy significantly boosts the feasibility to monitor the binding affinity of antibodies online during production.
最近，人工智能的深度学习（DL）维度受到生化研究人员的广泛关注，因此逐渐成为生物传感应用领域的关键方法。研究表明，使用 DL 技术进行传感不仅可以缩短数据分析的时间，而且还可以显著提高数据分析和预测的准确性，从而提高生物传感系统的性能，与传统方法相比。然而，迄今为止，在检测过程中获得可靠的生物分子相互作用平衡和速率常数仍然是困难和耗时的。在本研究中，我们提出了一种基于深度迁移学习和序列到序列自动编码器的转换模型，该模型可以成功地将 SPR 传感器图转换为蛋白质结合常数，即缔合速率常数（）和离解速率常数（），这些常数提供了理解药物作用机制和生物分子功能结构的关键信息。实验上，我们首先使用产生理想 SPR 传感器图的朗缪尔模型来训练和测试预训练模型，然后通过中等规模实验使用合成少数过采样技术（SMOTE）合成的增强 SPR 传感器图来微调预训练模型。接下来，将微调后的模型输入一个仅需要 110 s 的短实验 SPR 传感器图，该传感器图直接转换为重建理想传感器图。最后，通过拟合重建理想传感器图获得结合动力学常数，即输出和。结果表明，我们的模型得到的和的预测误差分别小于 12%和 24%。基于所提出的 DL 方法的便利性、准确性和可靠性，我们相信我们的策略极大地提高了在生产过程中在线监测抗体结合亲和力的可行性。
