多级联合图嵌入亲脂性分子分类

doi:10.3969/j.issn.1006-2475.2025.03.003

摘要/Abstract

摘要： 亲脂性分子分类是生物信息学和化学领域的重要研究方向，其目标是根据化学结构和功能特征对分子进行有效的亲脂性分类。然而，由于亲脂性分子的特性复杂且多样，传统的图神经网络分类方法在处理这类问题时，未能有效地提取分子内部的层次关系和充分考虑分子的结构信息，这导致关键原子的信息丢失和全局结构信息缺失。针对上述问题，提出一种多级联合图嵌入网络Mul-JoG。Mul-JoG融合Graph Transformer和图池化策略构建网络层，通过将不同网络层的输出串联，每一层融合以往所有层的信息，从而构成多级联合图嵌入网络。该网络通过从多个视角获取分子的拓扑结构，捕捉分子的全局信息和交互关系，有效建模分子复杂结构，实现亲脂性分子的准确分类。在药物分子数据集上的实验结果显示，Mul-JoG在AUC和ACC上分别达到了97.96%和92.94%。相较于基准方法，AUC提升了1.53个百分点，ACC提升了3.07个百分点。这表明Mul-JoG能够更准确分类亲脂性分子。

关键词: 亲脂性分类, 分子表示学习, 图神经网络, 图池化策略

Abstract: Classification of lipophilic molecules is an important area of research in the fields of bioinformatics and chemistry， where the goal is to efficiently classify molecules in terms of lipophilicity on the basis of their chemical structure and functional characteristics. However， due to the complex and diverse properties of lipophilic molecules， the traditional graph neural network classification methods fail to effectively extract the hierarchical relationships within the molecule and fully consider the structural information of the molecule when dealing with this type of problem， which results in the loss of information about the key atoms and the lack of global structural information. To address the above problems， a Multilevel Joint Graph Embedding Network （Mul-JoG） is proposed. Mul-JoG fuses Graph Transformer and graph pooling strategies to construct network layers， by concatenating the outputs of different network layers， and each layer fuses the information from all previous layers to form a multi-level joint graph embedding network. By obtaining the topological structure of molecules from multiple perspectives， the network captures the global information and interactions of molecules， effectively modeling the complex structure of molecules， and realizing the accurate classification of lipophilic molecules. The experimental results on the drug molecule dataset show that Mul-JoG achieved 97.96% and 92.94% in AUC and ACC， respectively. Compared with the benchmark method， the AUC and ACC is improved by 1.53 and 3.07 percentage points， respectively. The results showed that Mul-JoG is able to accurately classify lipophilic molecules.

Key words: , lipophilicity classification, molecules indicate learning, graph neural network, graph pooling strategy

中图分类号:

TP391

曹璐, 丁苍峰, 马乐荣, 延照耀, 游浩. 多级联合图嵌入亲脂性分子分类[J]. 计算机与现代化, 2025, 0(03): 12-21.

CAO Lu, DING Cangfeng, MA Lerong, YAN Zhaoyao, YOU Hao. Multilevel Joint Graph Embedding for Lipophilic Molecular Classification[J]. Computer and Modernization, 2025, 0(03): 12-21.

参考文献

［1］ VISWANADHAN V N， REDDY M R， BACQUET R J， et al. Assessment of methods used for predicting lipophilicity： Application to nucleosides and nucleoside bases［J］. Journal of computational Chemistry， 1993，14（9）：1019-1026.
［2］ XING L， GLEN R C. Novel methods for the prediction of logP， pKa， and logD［J］. Journal of Chemical Information and Computer Sciences， 2002，42（4）：796-805.
［3］ LIPINSKI C A， LOMBARDO F， DOMINY B W， et al. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings［J］. Advanced Drug Delivery Reviews， 1997，23（1-3）：3-25.
［4］ BREINDL A， BECK B， CLARK T， et al. Prediction of the n-octanol/water partition coefficient， logP， using a combination of semiempirical MO-calculations and a neural network［J］. Molecular Modeling Annual， 1997，3：142-155.
［5］ YAFFE D， COHEN Y， ESPINOSA G， et al. Fuzzy ARTMAP and back-propagation neural networks based quantitative structure-property relationships （QSPRs） for octanol-water partition coefficient of organic compounds［J］. Journal of Chemical Information and Computer Sciences， 2002，42（2）：162-183.
［6］ JALILI S， TAFAZZOLI M， JALALI-HERAVI M. Comparison of multiple linear regression and artificial neural networks in predicting octanol/water partition coefficient of a variety of organic molecules［J］. Journal of Theoretical and Computational Chemistry， 2003，2（3）：335-344.
［7］范梦婷. 有机分子亲脂性的理论研究［D］. 南京：南京大学， 2021.
［8］ ZHOU J， CUI G Q， HU S D， et al. Graph neural networks： A review of methods and applications［J］. AI Open， 2020，1：57-81.
［9］ DUVENAUD D K， MACLAURIN D， IPARRAGUIRRE J， et al. Convolutional networks on graphs for learning molecular fingerprints［J］. arXiv preprint arXiv：1509.09292， 2015.
［10］ GILMER J， SCHOENHOLZ S S， RILEY P F， et al. Neural message passing for quantum chemistry［C］// International Conference on Machine Learning. PMLR， 2017：1263-1272.
［11］ LEE J B， ROSSI R， KONG X. Graph classification using structural attention［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM， 2018：1666-1674.
［12］ SUCH F P， SAH S， DOMINGUEZ M A， et al. Robust spatial filtering with graph convolutional neural networks［J］. IEEE Journal of Selected Topics in Signal Processing， 2017，11（6）：884-896.
［13］ COLEY C W， BARZILAY R， GREEN W H， et al. Convolutional embedding of attributed molecular graphs for physical property prediction［J］. Journal of Chemical Information and Modeling， 2017，57（8）：1757-1772.
［14］ LUSCI A， POLLASTRI G， BALDI P. Deep architectures and deep learning in chemoinformatics： The prediction of aqueous solubility for drug-like molecules［J］. Journal of Chemical Information and Modeling， 2013，53（7）：1563-1575.
［15］ YUN S J， JEONG M， KIM R， et al. Graph transformer networks［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. ACM， 2019：11983-11993.
［16］ LEE J， LEE I， KANG J. Self-attention graph pooling［C］// International Conference on Machine Learning. PMLR， 2019：3734-3743.
［17］ LI G H， XIONG C X， THABET A， et al. DeeperGCN： All you need to train deeper GCNs［J］. arXiv preprint arXiv：2006.07739， 2020.
［18］ LI J C， JIANG X F. Mol-BERT： An effective molecular representation with BERT for molecular property prediction［J］. Wireless Communications and Mobile Computing， 2021，2021：1-7.
［19］ TOUSSI C A， HADDADNIA J， MATTA C F. Drug design by machine-trained elastic networks： Predicting Ser/Thr-protein kinase inhibitors’activities［J］. Molecular Diversity， 2021，25：899-909.
［20］ CHENG J C， ZHANG C K， DONG L F. A geometric-information-enhanced crystal graph network for predicting properties of materials［J］. Communications Materials， 2021，2（1）：1-11.
［21］ WOO G， FERNANDEZ M， HSING M， et al. DeepCOP： Deep learning-based approach to predict gene regulating effects of small molecules［J］. Bioinformatics， 2020，36（3）：813-818.
［22］ WITHNALL M， LINDELÖF E， ENGKVIST O， et al. Building attention and edge message passing neural networks for bioactivity and physical-chemical property prediction［J］. Journal of Cheminformatics， 2020，12（1）：1-18.
［23］ MAZIARKA Ł， DANEL T， MUCHA S， et al. Molecule attention transformer［J］. arXiv preprint arXiv：2002.08264， 2020.
［24］ KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks［J］. arXiv preprint arXiv：1609.02907， 2016.
［25］ MENG M， WEI Z Q， LI Z， et al. Property prediction of molecules in graph convolutional neural network expansion［C］// 2019 IEEE 10th International Conference on Software Engineering and Service Science （ICSESS）. IEEE， 2019：263-266.
［26］ TANG B W， KRAMER S T， FANG M J， et al. A self-attention based message passing neural network for predicting molecular lipophilicity and aqueous solubility［J］. Journal of Cheminformatics， 2020，12（1）：1-9.
［27］ ZHANG Z H， HUANG J， TAN Q. SR-HGAT： Symmetric relations based heterogeneous graph attention network［J］. IEEE Access， 2020，8：165631-165645.
［28］ GAO H Y， JI S W. Graph U-Nets［C］// International Conference on Machine Learning. PMLR， 2019：2083-2092.
［29］ WEININGER D. SMILES， a chemical language and information system.1. Introduction to methodology and encoding rules［J］. Journal of Chemical Information and Computer Sciences， 1988，28（1）：31-36.
［30］ WANG C， WANG W Y， LU K， et al. Predicting drug-target interactions with electrotopological state fingerprints and amphiphilic pseudo amino acid composition［J］. International Journal of Molecular Sciences， 2020，21（16）. DOI：10.3390/ijms21165694.
［31］ KINGMA D P， BA J. Adam： A method for stochastic optimization［J］. arXiv preprint arXiv：1412.6980， 2014.
［32］ PASZKE A， GROSS S， MASSA F， et al. Pytorch： An imperative style， high-performance deep learning library［J］. arXiv preprint arXiv：1912.01703， 2019.
［33］ FEY M， LENSSEN J E. Fast graph representation learning with PyTorch Geometric［J］. arXiv preprint arXiv：1903.02428， 2019.
［34］ STONE M. Cross-validatory choice and assessment of statistical predictions［J］. Journal of the Royal Statistical Society： Series B （Methodological）， 1974，36（2）：111-133.
［35］ VELICKOVIC P， CUCURULL G， CASANOVA A， et al. Graph attention networks［J］. arXiv preprint arXiv：1710.10903， 2017.
［36］ HAMILTON W， YING Z， LESKOVEC J. Inductive representation learning on large graphs［J］. arXiv preprint arXiv：1706.02216， 2017.
［37］ BRODY S， ALON U， YAHAV E. How attentive are graph attention networks?［J］. arXiv preprint arXiv：2105.14491， 2021.
［38］ LI F， CHEN Z R， WANG P J， et al. Graph intention network for click-through rate prediction in sponsored search［C］// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM， 2019：961-964.
［39］ FANG X M， LIU L H， LEI J， et al. Geometry-enhanced molecular representation learning for property prediction［J］. Nature Machine Intelligence， 2022，4（2）：127-134.
［40］ LIU Z Q， ZHANG W， XIA Y C， et al. MolXPT： Wrapping molecules with text for generative pre-training［J］. arXiv preprint arXiv：2305.10688， 2023.
［41］ AHMAD W， TAYARA H， CHONG K T. Attention-based graph neural network for molecular solubility prediction［J］. ACS Omega， 2023，8（3）：3236-3244.
［42］ JI Y， WAN G J， ZHAN Y B， et al. Metapath-fused heterogeneous graph network for molecular property prediction［J］. Information Sciences， 2023，629：155-168.

[1]	马钰, 杨勇, 任鸽, 帕力旦·吐尔逊. 基于GCN和微调BERT的作文自动评分方法[J]. 计算机与现代化, 2024, 0(09): 33-37.
[2]	黄政霖, 董宝良. 基于语义和结构增强的时序知识图谱问答方法[J]. 计算机与现代化, 2024, 0(03): 15-23.
[3]	陈俊义. 基于图节点动静态特征的健康事件预测模型[J]. 计算机与现代化, 2023, 0(10): 39-44.
[4]	夏义春, 李汪根, 李豆豆, 葛英奎, 王志格. 结合注意力机制和图神经网络的CTR预估模型[J]. 计算机与现代化, 2023, 0(03): 29-37.
[5]	姚春华, 张学磊, 宋馨宇, 张举, 蔡佳志, 冯翱. 一种基于图卷积神经网络和依存分析的财经新闻情感分析方法[J]. 计算机与现代化, 2022, 0(05): 33-39.