基于图神经网络的植物间相互作用预测方法

崔子文; 王欢; 李函; 韦乐

doi:10.13300/j.cnki.hnlkxb.2025.02.031

您当前的位置：

首页 >

文章列表页 >

基于图神经网络的植物间相互作用预测方法

技术与方法 | 更新时间：2026-11-05

- 基于图神经网络的植物间相互作用预测方法
- A graph neural network-based method for predicting interactions between plants
- 华中农业大学学报 2025年44卷第2期页码：301-310
- 作者机构：
  
  华中农业大学信息学院，武汉430070
- 作者简介：
  
  崔子文，E-mail：cuiziwen@webmail.hzau.edu.cn
  王欢，E-mail：hwang@mail.hzau.edu.cn
- 基金信息：
  
  教育部“春晖计划”合作科研项目(202201700);“一带一路”创新人才交流外国专家项目(DL2023157004L);农作物育种数据融合共享与支撑体系建设项目(2023ZD0406101-3)
- DOI：10.13300/j.cnki.hnlkxb.2025.02.031
  中图分类号： TP18
- 收稿：2024-08-19，
  
  纸质出版：2025-03-06
- 稿件说明：
移动端阅览
崔子文，王欢，李函，等.基于图神经网络的植物间相互作用预测方法［J］.华中农业大学学报，2025，44（2）：301‐310.

CUI Ziwen,WANG Huan,LI Han,et al.A graph neural network-based method for predicting interactions between plants[J].Journal of Huazhong Agricultural University,2025,44(02):301-310.
崔子文，王欢，李函，等.基于图神经网络的植物间相互作用预测方法［J］.华中农业大学学报，2025，44（2）：301‐310. DOI： 10.13300/j.cnki.hnlkxb.2025.02.031.

CUI Ziwen,WANG Huan,LI Han,et al.A graph neural network-based method for predicting interactions between plants[J].Journal of Huazhong Agricultural University,2025,44(02):301-310. DOI： 10.13300/j.cnki.hnlkxb.2025.02.031.

摘要

针对如何精准地根据先验知识预测植物间的抑制与促进相互作用问题，构建基于植物间相互作用的异质网络，提出一种基于图神经网络的相互作用预测方法。该方法主要由表征学习器、作用识别器和类型分类器三大模块构成。表征学习器负责提取植物间相互作用特征，作用识别器与表征学习器共同预测植物节点之间是否产生相互作用，并对类型分类器施加干扰，以最大程度地获得在不同类型相互作用间可迁移的特征。类型分类器旨在准确区分植物间相互作用的类型，以避免受到作用识别器的干扰。最后，基于三大模块之间的相互对抗关系来增强对植物间抑制与促进相互作用类型差异的鲁棒性，从而有效应对目标植物间相互作用的预测问题。该方法在伴生植物数据集上的AUC、精确率（precision）和准确率（accuracy）的表现相较于现有的SEAL、GATNE、HeGAN、PME、SVM和RF方法中的最优方法SVM分别提高了7.74、1.61和8.62百分点，分别达到了92.00%、80.12%和86.21%。结果表明，该方法通过降低目标类型差异的干扰，可以精准地预测植物间的相互作用，可以应用于优化农业生产实践。

Abstract

A heterogeneous network-based on interactions between plants was constructed，and a graph neural network-based method for predicting interactions between plants was proposed to solve the problem of accurately predicting inhibitory and promotive interactions between plants based on prior knowledge.The method is primarily composed of three modules including a representation learner，an interaction identifier，and a type classifier.The representation learner is responsible for extracting representations of interactions.The interaction identifier collaborates with the representation learner to predict whether an interaction exists on types of targeted plant and applies perturbations to the type classifier to maximally acquire transferable features across different types of interaction.The type classifier is designed to accurately distinguish types of interactions between plants to avoid being affected by the interaction identifier.The inter adversarial relationship among the three modules is leveraged to enhance robustness against the differences in the types of inhibitory and promotive interactions between plants，thereby effectively solving the problem of accurately predicting targeted interactions between plants.The AUC，precision，and accuracy of this method on the dataset of companion plant improved by 7.74，1.61，and 8.62 per cent，respectively compared with the best method SVM that of existing methods including SEAL，GATNE，HeGAN，PME，SVM，and RF，reaching 92.00%，80.12%，and 86.21%，respectively.The results indicate that the proposed method effectively mitigates the interference caused by target interaction type differences，enabling accurate prediction of plant interactions.This approach can be applied to optimize agricultural production practices.

关键词

Keywords

references

JACQUET F，JEUFFROY M H，JOUAN J，et al.Pesticide-free agriculture as a new paradigm for research［J/OL］.Agronomy for sustainable development，2022，42（1）：8［2024-08-19］. https：//doi.org/10.1007/s13593-021-00742-8.

DELUCA T H，ZACKRISSON O，NILSSON M C，et al.Quantifying nitrogen-fixation in feather moss carpets of boreal forests［J］.Nature，2002，419（6910）：917-920.

金殿玉，谢立勇，赵洪亮，等.大气CO 2 浓度升高条件下稻稗共生系统中稗草对水稻光合生理的影响［J］.中国农业气象，2022，43（3）：204-214.JIN D Y，XIE L Y，ZHAO H L，et al.Impacts of barnyard grass on photosynthesis and physiology of rice under elevated atmospheric CO 2 concentration［J］.Chinese journal of agrometeorology，2022，43（3）：204-214 （in Chinese with English abstract） .

王海光.智慧植保及其发展建议［J］.中国农业大学学报，2022，27（10）：1-21.WANG H G.Smart phytoprotection and suggestions for its development［J］.Journal of China Agricultural University，2022，27（10）：1-21 （in Chinese with English abstract） .

LIU W B，WANG Z D，LIU X H，et al.A survey of deep neural network architectures and their applications［J］.Neurocomputing，2017，234：11-26.

LI P，HAO H，ZHANG Z，et al.A field study to estimate heavy metal concentrations in a soil-rice system： application of graph neural networks［J/OL］.Science of the total environment，2022，832： 155099［2024-08-19］.https：//doi.org/10.1016/j.scitotenv.2022.155099.

YANG F，ZHANG D，ZHANG Y，et al.Prediction of corn variety yield with attribute-missing data via graph neural network［J/OL］.Computers and electronics in agriculture，2023，211： 108046［2024-08-19］.https：//doi.org/10.1016/j.compag.2023.108046.

EL-SHAWA S.Exploring and predicting plant-arthropod interactions： hierarchical modelling of species communities and graph neural network approaches［D］.Guelph：University of Guelph，2023.

KUSHARKI M B，MUHAMMAD-BELLO B L.AIoT-enabled precision agriculture for sustainable crop disease management： advancing SDGs through graph attention neural networks［M］//MOHIUDDIN A，ABU S M，RAJU C，et al.Artificial intelligence of things for achieving sustainable development goals.Cham： Springer Nature Switzerland， 2024： 143-160.

LEI L，YANG Q，YANG L，et al.Deep learning implementation of image segmentation in agricultural applications： a comprehensive review［J/OL］.Artificial intelligence review，2024，57（6）： 149［2024-08-19］.https：//doi.org/10.1007/s10462-024-10775-6.

FANG Y.Smart agriculture： advancements on plant disease detection with big data and deep learning［D］.Melbourne：Deakin University，2022.

SERIN E A R，NIJVEEN H，HILHORST H W M，et al.Learning from co-expression networks：possibilities and challenges［J/OL］.Frontiers in plant science，2016，7：444［2024-08-19］.https：//doi.org/10.3389/fpls.2016.00444.

DENG Z Y，ZHANG J M，LI J Y，et al.Application of deep learning in plant-microbiota association analysis［J/OL］.Frontiers in genetics，2021，12：697090［2024-08-19］.https：//doi.org/10.3389/fgene.2021.697090.

AYOUB SHAIKH T，RASOOL T，RASHEED LONE F.Towards leveraging the role of machine learning and artificial intelligence in precision agriculture and smart farming［J/OL］.Computers and electronics in agriculture，2022，198：107119［2024-08-19］.https：//doi.org/10.1016/j.compag.2022.107119.

SHAH T M，NASIKA D P B，OTTERPOHL R.Plant and weed identifier robot as an agroecological tool using artificial neural networks for image identification［J/OL］.Agriculture，2021，11（3）：222［2024-08-19］.https：//doi.org/10.3390/agriculture11030222.

LOSAPIO G，MONTESINOS-NAVARRO A，SAIZ H.Perspectives for ecological networks in plant ecology［J］.Plant ecology & diversity，2019，12（2）：87-102.

LI B T，PI D C.Network representation learning：a systematic literature review［J］.Neural computing and applications，2020，32（21）：16647-16679.

侯祥英，崔运鹏，刘娟.深度学习在植物基因组学与作物育种中的应用现状与展望［J］.农业图书情报学报，2022，34（8）：4-18.HOU X Y，CUI Y P，LIU J.Applications and prospect analysis of deep learning in plant genomics and crop breeding［J］.Journal of library and information science in agriculture，2022，34（8）：4-18 （in Chinese with English abstract） .

GROVER A，LESKOVEC J.Node2vec：scalable feature learning for networks［J］.KDD：proceedings international conference on knowledge discovery & data mining，2016，2016：855-864.

PENG H，LI J X，YAN H，et al.Dynamic network embedding via incremental skip-gram with negative sampling［J/OL］.Science China information sciences，2020，63（10）：202103［2024-08-19］.https：//doi.org/10.1007/s11432-018-9943-9.

O’SHEA K，NASH R.An introduction to convolutional neural networks［DB/OL］.arXiv，2015：1511.08458［2024-08-19］.https：//doi.org/10.48550/arXiv.1511.08458.

LI L，DOROSLOVAČKI M，LOEW M H.Approximating the gradient of cross-entropy loss function［J］.IEEE access，2020，8：111626-111635.

BARRON J T.A general and adaptive robust loss function［C］//LARRY D，PHILIP T，ZHU S C.Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Long Beach，CA，USA：IEEE，2019：4331-4339.

WANG H，CUI Z W，LIU R G，et al.A multi-type transferable method for missing link prediction in heterogeneous social networks［J］.IEEE transactions on knowledge and data engineering，2023，35（11）：10981-10991.

HE Z W，ZHANG L.Multi-adversarial faster-RCNN for unrestricted object detection［C］//JINWOO S，SANG U L，IN S K.2019 IEEE/CVF international conference on computer vision （ICCV）.Seoul，Korea （South）：IEEE，2019：6667-6676.

AI J，LIU Y Y，SU Z，et al.Link prediction in recommender systems based on multi-factor network modeling and community detection［J/OL］.EPL （europhysics letters），2019，126（3）：38003［2024-08-19］.https：//doi.org/10.1209/0295-5075/126/38003.

WU Q，ZHAO W，LI Z，et al.Nodeformer：a scalable graph structure learning transformer for node classification［J］.Advances in neural information processing systems，2022，35：27387-27401.

ZHANG M，CHEN Y.Link prediction based on graph neural networks［J］.Advances in neural information processing systems，2018：31［2024-08-19］.https：//dl.acm.org/doi/10.5555/3327345.3327423.

CEN Y K，ZOU X，ZHANG J W，et al.Representation learning for attributed multiplex heterogeneous network［C］//ANKUR T，VIPIN K，LIRÓMER R，et al.Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining.Anchorage AK USA：ACM，2019：1358-1368.

HU B B，FANG Y，SHI C.Adversarial learning on heterogeneous information networks［C］//ANKUR T，VIPIN K，LIRÓMER R，et al.Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining.Anchorage AK USA：ACM，2019：120-129.

CHEN H X，YIN H Z，WANG W Q，et al.PME：projected metric embedding on heterogeneous networks for link prediction［C］//Proceedings of the 24th ACM SIGKDD International conference on knowledge discovery & data mining.London： ACM，2018：1177-1186.

NOBLE W S.What is a support vector machine？［J］.Nature biotechnology，2006，24（12）：1565-1567.

BIAU G，SCORNET E.A random forest guided tour［J］.Test，2016，25：197-227.

ZHAO Z L，GOU Z Y，DU Y H，et al.A novel link prediction algorithm based on inductive matrix completion［J/OL］.Expert systems with applications，2022，188：116033［2024-08-19］.https：//doi.org/10.1016/j.eswa.2021.116033.

NASIRI E，BERAHMAND K，LI Y F.Robust graph regularization nonnegative matrix factorization for linkprediction in attributed networks［J］.Multimedia tools and applications，2023，82（3）：3745-3768.

SHABAZ M，GARG U.Predicting future diseases based on existing health status using link prediction［J］.World journal of engineering，2022，19（1）：29-32.

UGOLINI L，MARTINI C，LAZZERI L，et al.Control of postharvest grey mould on strawberries by glucosinolate-derived allyl-isothiocyanate treatments［J］.Postharvest biology and technology，2014，90：34-39.

MACÍAS F A，DURÁN A G，MOLINILLO J M G.Allelopathy：the chemical language of plants［J］.Progress in the chemistry of organic natural products，2020，112：1-84.

XIE Y Q，TIAN L B，HAN X，et al.Research advances in allelopathy of volatile organic compounds （VOCs） of plants［J/OL］.Horticulturae，2021，7（9）：278［2024-08-19］.https：//doi.org/10.3390/horticulturae7090278.

ZHANG D Q，YAN D D，CHENG H Y，et al.Effects of multi-year biofumigation on soil bacterial and fungal communities and strawberry yield［J/OL］.Environmental pollution，2020，256：113415［2024-08-19］.https：//doi.org/10.1016/j.envpol.2019.113415.

KAZAK C，KARUT K，DÖKER İ.Important pests in vegetable crops［M］//HUI Y H.Handbook of vegetable preservation and processing，Boca Raton： CRC Press，2015：134-157.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

畜禽废水来源地衣芽孢杆菌WS4-CotA漆酶的异源表达、酶学性质及底物选择性

大豆灰斑病病原变异、抗性挖掘与智能防控

不同杀菌剂对百合炭腐病菌的毒力和防效评价

芥菜自交系重要农艺性状的遗传多样性分析

蚯蚓粪-生物炭复配育苗基质对5种作物种子萌发与幼苗生长的影响