基于深度学习和骨架结构MHA-RNN的农药分子生成模型  

A pesticide molecular generation model based on deep learning and scaffold structure MHA-RNN

作　　者：袁洪波[1] 周焕笛 霍静倩[2] 张金林[2] 程曼[1] YUAN Hongbo;ZHOU Huandi;HUO Jingqian;ZHANG Jinlin;CHENG Man(College of Mechanical and Electrical Engineering,Hebei Agricultural University,Baoding 071001,China;College of Plant Protection,Hebei Agricultural University,Baoding 071001,China)

机构地区：[1]河北农业大学机电工程学院,保定071001 [2]河北农业大学植物保护学院,保定071001

出　　处：《农业工程学报》2025年第1期200-211,共12页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金项目(32272573)。

摘　　要：近年来,深度学习模型在农药发现和从头分子设计方面取得了显著进展。然而目前用于农药分子设计的深度生成模型中,基于骨架的分子生成模型较少。并且基于骨架的分子生成方法面临着生成分子质量和多样性不足的挑战。为此,该研究提出了一种基于骨架结构的循环神经网络模型(multi head attention-recurrent neural network,MHA-RNN),首先生成简化分子线性输入规范(simplified molecular input line entry system,SMILES)格式的分子骨架,然后对骨架进行装饰以生成新的分子。试验结果表明,模型生成的分子在有效性、新颖性和唯一性方面分别达到了97.18%、99.87%和100.00%。此外,生成分子在脂水分配系数(logarithm of partition coefficient,LogP)、拓扑极性表面积(topological polar surface area,TPSA)、相对分子质量(molecular weight,MW)、类药性(quantitative estimate of drug-likeness,QED)、氢键受体(hydrogen bond acceptor,HBA)、氢键供体(hydrogen bond donor,HBD)、旋转键数(rotatable bonds,RotB)等性质上的分布与现有分子高度相似,研究结果为农药新药研发提供了技术支持与参考。Pesticides to control pests and diseases can play an important role in crop yields in modern agriculture.However,the pesticide translation can be the long-term,expensive development with a low success rate.Fortunately,deep learning can be expected to significantly improve the efficiency of pesticide research and application in recent years.The molecular generation can be fabricated as the atoms,fragments,reactions,and scaffolds,indicating the unique characteristics.Among them,scaffoldbased approaches demonstrate significant potential in drug discovery and compound design.Existing chemical knowledge can be effectively utilized to adjust molecular structures during generation,in order to meet the requirements of different drug targets and biological activity.However,the quality and validity of generated molecules are required to explore new compounds with molecular characteristics.Furthermore,existing models cannot fully capture the complex structural features of molecules during generation.In this study,a scaffold-based generation model of pesticide molecular was proposed,called multihead attention and recurrent neural network(MHA-RNN).The structural features of the molecules were better captured to maintain the rationality and validity of the molecule generation using the molecular scaffold.The uniqueness of the generated molecules was also enhanced significantly.The MHA-RNN model was used to first generate the molecular scaffolds in SMILES format,and then decorate these scaffolds for new molecules.The data preprocessing involved two steps:the first step was to slice the molecules,breaking them down into combinations of scaffolds and decorations;In the second step,data augmentation was applied to expand the dataset of scaffolds and decorations.Multiple representations of a single molecule were learned to enhance the robustness and generalization of the model.The entire model consisted of three parts:an encoder,a multi-head attention layer,and a decoder.Among them,the encoder part was a simple bidirectional RNN en

关 键 词：农药研发 分子生成 分子骨架 循环神经网络 注意力机制 

分 类 号：TQ450.1[化学工程—农药化工]