基于结构特征的药物靶点亲和力预测

Prediction of Drug Target Binding Affinity Based on Structural Features

预测药物与其靶向蛋白的结合亲和力是研发新药的关键步骤。传统的湿实验耗时长,成本高。随着人工智能技术的快速发展,在药物筛选阶段应用深度学习的技术可以大幅度提升研发效率。针对上述问题,提出一种基于卷积神经网络预测药物靶点亲和力的方法。将蛋白质和小分子的结构特征分别转换成对应的三维矩阵,送入对应的三维卷积神经网络中进行训练,然后再通过若干层全连接神经网络提取特征值,得到最终的亲和力值。实验结果表明,该模型可有效地预测药物靶点亲和力,具有良好的应用前景。

Predicting the binding affinity between drugs and their target proteins is a key steps in developing new drugs.Traditional wet experiments are time-consuming and expensive.With the rapid development of artificial intelligence technology,the application of Deep Learning technology in the drug screening phase has the potential to significantly enhance research and development efficiency.A method for predicting drug target binding affinity based on Convolutional Neural Networks is proposed to address the above issues.The structural features of proteins and small molecules are transformed into corresponding three-dimensional matrices,these matrices are fed into respective three-dimensional Convolutional Neural Networks for training.Then,feature values are extracted through several layers of fully connected neural networks to obtain the final binding affinity value.The experimental results indicate that the model can effectively predict the binding affinity of drug targets and has good application prospects.