Thousands of investigations on quantitative structure–activity/property relationships (QSARs/QSPRs) have been reported. However, few publications can be found that deal with QSARs for aptamers, because calculating two-dimensional and three-dimensional descriptors directly from aptamers (typically with 15–45 nucleotides) is difficult. This paper describes calculating molecular descriptors from amino acid sequences that are translated from DNA aptamer sequences with DNAMAN software, and developing QSAR models for the aptamers’ binding affinity to the influenza virus. General regression neural network (GRNN) based on Parzen windows estimation was used to build the QSAR model by applying six molecular descriptors. The optimal spreading factor σ of Gaussian function of 0.3 was obtained with the circulation method. The correlation coefficients r from the GRNN model were 0.889 for the training set and 0.892 for the test set. Compared with the existing model for aptamers’ binding affinity to the influenza virus, our model is accurate and competes favourably. The feasibility of calculating molecular descriptors from an amino acid sequence translated from DNA aptamer sequences to develop a QSAR model for the anti-influenza aptamers was demonstrated.

关于数量结构-活动/属性关系（QSARs / QSPRs）的研究已经报道了成千上万。但是，几乎没有发现涉及适体QSAR的出版物，因为直接从适体（通常具有15-45个核苷酸）计算二维和三维描述符很困难。本文介绍了使用DNAMAN软件从DNA适体序列翻译而来的氨基酸序列计算分子描述符，以及开发QSAR模型以了解适体对流感病毒的结合亲和力。基于Parzen窗估计的通用回归神经网络（GRNN）通过应用六个分子描述符来构建QSAR模型。最佳扩展因子σ通过循环法获得了0.3的高斯函数。来自GRNN模型的相关系数r对于训练集为0.889，对于测试集为0.892。与现有的适体与流感病毒结合亲和力的模型相比，我们的模型准确且竞争激烈。证明了从DNA适体序列翻译的氨基酸序列计算分子描述符以建立抗流感适体的QSAR模型的可行性。