计算机科学 ›› 2026, Vol. 53 ›› Issue (4): 101-111.doi: 10.11896/jsjkx.250500097
高泰, 任艳璋, 王会青, 李颖, 王彬
GAO Tai, REN Yanzhang, WANG Huiqing, LI Ying, WANG Bin
摘要： 基因调控网络(Gene Regulatory Network,GRN)推断对于解析细胞发育机制及推动精准医学研究至关重要,但是现有深度学习方法面临计算复杂度高与全局特征捕捉不足的挑战。为此,提出一种融合Kolmogorov-Arnold 网络(KAN)驱动的图卷积网络(KGCN)与 Mamba 模块的高效预测模型。首先,以 KAN特有的可学习样条函数,取代图卷积网络中的多层感知器(MLP)模块。该改进在完整保留邻居节点局部特征提取能力的基础上,通过重构计算逻辑降低特征处理的冗余度,使模型计算复杂度较传统图卷积架构实现显著优化。其次,创新性地引入 Mamba 模块,通过其选择性机制优先关注对全局调控起关键作用的基因节点。两者结合实现了局部特征提取效率与全局依赖建模能力的协同优化。在公开数据集上与另外6种深度学习模型进行实验比较,结果显示,该模型在AUC和AUPR性能指标上都优于其他模型,同时展现出显著的鲁棒性优势和计算效率。
中图分类号:
| [1]NGUYEN H,TRAN D,TRAN B,et al.A comprehensive survey of regulatory network inference methods using single cell RNA sequencing data[J].Briefings in Bioinformatics,2021,22(3):bbaa190. [2]MARBACH D,COSTELLO J C,KÜFFNER R,et al.Wisdomof crowds for robust gene network inference[J].Nature Methods,2012,9(8):796-804. [3]RICE J J,TU Y,STOLOVITZKY G.Reconstructing biological networks using conditional correlation analysis[J].Bioinformatics,2005,21(6):765-773. [4]FAITH J J,HAYETE B,THADEN J T,et al.Large-scale mapping and validation of Escherichia coli transcriptional regulation from a compendium of expression profiles[J].PLoS Biology,2007,5(1):54-66. [5]FRIEDMAN N.Inferring cellular networks using probabilisticgraphical models[J].Science,2004,303(5659):799-805. [6]JI R,GENG Y,QUAN X.Inferring gene regulatory networks with graph convolutional network based on causal feature reconstruction[J].Scientific Reports,2024,14(1):21342. [7]WEI P J,GUO Z,GAO Z,et al.Inference of gene regulatory networks based on directed graph convolutional networks[J].Briefings in Bioinformatics,2024,25(4):bbae309. [8]KOMMU S,WANG Y,WANG Y,et al.Gene Regulatory Network Inference with Joint Representation from Graph Neural Network and Single-Cell Foundation Model[J/OL].https://www.biorxiv.org/content/10.1101/2024.12.16.628715v1.full.pdf. [9]LIU Z,WANG Y,VAIDYA S,et al.Kan:Kolmogorov-Arnold networks[J].arXiv:2404.19756,2024. [10]GU A,DAO T.Mamba:Linear-time sequence modeling with selective state spaces[J].arXiv:2312.00752,2023. [11]YANG B,XU Y,MAXWELL A,et al.MICRAT:a novel algorithm for inferring gene regulatory networks using time series gene expression data[J].BMC Systems Biology,2018,12:19-29. [12]LI L,SUN L,CHEN G,et al.LogBTF:gene regulatory network inference using Boolean threshold network model from single-cell gene expression data[J].Bioinformatics,2023,39(5):btad256. [13]HUYNH-THU V A,GEURTS P.dynGENIE3:dynamical GENIE3 for the inference of gene networks from time series expression data[EB/OL].Scientific Reports,2018,8:3384.https://www.nature.com/articles/s41598-018-21715-0. [14]MARGOLIN A A,NEMENMAN I,BASSO K,et al.ARAC-NE:an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context[C]//BMC Bioinformatics.2006:1-15. [15]ZENG Y,HE Y,ZHENG R,et al.Inferring single-cell gene regulatory network by non-redundant mutual information[J].Briefings in Bioinformatics,2023,24(5):bbad326. [16]ZHANG Y,WANG M,WANG Z,et al.MetaSEM:gene regulatory network inference from single-cell RNA data by meta-learning[J].International Journal of Molecular Sciences,2023,24(3):2595. [17]MA M Y,SUN J X,HU C L.Modeling Gene Regulatory Networks with Global Coupling Parameters[J].Computer Science,2023,50(S2):138-144. [18]HUYNH-THU V A,IRRTHUM A,WEHENKEL L,et al.Inferring regulatory networks from expression data using tree-based methods[J].PloS One,2010,5(9):e12776. [19]LI Z J,LIAO S,LIU A F,et al.Gene Association Analysis Algorithm for GeneRegulatory Network[J].Computer Engineering and Applications,2025,61(3):155-165. [20]ZHAO M,HE W,TANG J,et al.A hybrid deep learning framework for gene regulatory network inference from single-cell transcriptomic data[J].Briefings in Bioinformatics,2022,23(2):bbab568. [21]YUAN Y,BAR-JOSEPH Z.Deep learning for inferring gene relationships from single-cell expression data[J].Proceedings of the National Academy of Sciences,2019,116(52):27151-27158. [22]CHEN J,CHEONG C W,LAN L,et al.DeepDRIM:a deep neural network to reconstruct cell-type-specific gene regulatory network using single-cell RNA-seq data[J].Briefings in Bioinformatics,2021,22(6):bbab325. [23]SHU H,DING F,ZHOU J,et al.Boosting single-cell gene regulatory network reconstruction via bulk-cell transcriptomic data[J].Briefings in Bioinformatics,2022,23(5):bbac389. [24]XU J,ZHANG A,LIU F,et al.STGRNS:an interpretabletransformer-based method for inferring gene regulatory networks from single-cell transcriptomic data[J].Bioinformatics,2023,39(4):btad165. [25]HAMILTON W,YING Z,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.2017:1025-1035. [26]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017. [27]BRODY S,ALON U,YAHAV E.How attentive are graph attention networks?[J].arXiv:2105.14491,2021. [28]SOMVANSHI S,JAVED S A,ISLAM M M,et al.A survey on Kolmogorov-Arnold network[J].arXiv:2411.06078,2024. [29]SU Z,CHEN M,AI J,et al.Research on Recommendation Algorithm Based on Kolmogorov-Arnold Network-driven Scoring and Review Fusion[J].Journal of Chinese Computer Systems.2025,46(11):2600-2609. [30]CHEON M.Kolmogorov-Arnold network for satellite imageclassification in remote sensing[J].arXiv:2406.00600,2024. [31]JIANG W,CHEN T,GAO X,et al.Epidemiology-informed network for robust rumor detection[C]//Proceedings of the ACM on Web Conference 2025.2025:3618-3627. [32]XU K,CHEN L,WANG S.Kolmogorov-Arnold Networks for Time Series:Bridging Predictive Power and Interpretability[J].arXiv:2406.02496,2024. [33]GU A,GOEL K,RÉ C.Efficiently modeling long sequences with structured state spaces[J].arXiv:2111.00396,2021. [34]SMITH J T H,WARRINGTON A,LINDERMAN S W.Simplified state space layers for sequence modeling[J].arXiv:2208.04933,2022. [35]MEHTA H,GUPTA A,CUTKOSKY A,et al.Long range language modeling via gated state spaces[J].arXiv:2206.13947,2022. [36]QU H,NING L,AN R,et al.A survey of Mamba[J].arXiv:2408.01129,2024. [37]PRATAPA A,JALIHAL A P,LAW J N,et al.Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data[J].Nature Methods,2020,17(2):147-154. [38]MOORE J E,PURCARO M J,PRATT H E,et al.Expanded encyclopaedias of DNA elements in the human and mouse genomes[J].Nature,2020,583(7818):699-710. [39]GARCIA-ALONSO L,HOLLAND C H,IBRAHIM M M,et al.Benchmark and integration of resources for the estimation of human transcription factor activities[J].Genome Research,2019,29(8):1363-1375. [40]SZKLARCZYK D,GABLE A L,LYON D,et al.STRING v11:protein-protein association networks with increased coverage,supporting functional discovery in genome-wide experimental datasets[J].Nucleic Acids Research,2019,47(D1):D607-D613. [41]XU H,BAROUKH C,DANNENFELSER R,et al.ESCAPE:database for integrating high-content published data collected from human and mouse embryonic stem cells[J].Database,2013,2013:bat045. [42]ZHU X,JING X Y,ZHANG F,et al.Distance learning by mining hard and easy negative samples for person re-identification[J].Pattern Recognition,2019,95:211-222. [43]MAO G,PANG Z,ZUO K,et al.Predicting gene regulatorylinks from single-cell RNA-seq data using graph neural networks[J].Briefings in Bioinformatics,2023,24(6):bbad414. [44]KC K,LI R,CUI F,et al.GNE:a deep learning framework for gene network inference by aggregating biological information[J].BMC Systems Biology,2019,13:1-14. [45]ARISDAKESSIAN C,POIRION O,YUNITS B,et al.DeepImpute:an accurate,fast,and scalable deep neural network method to impute single-cell RNA-seq data[J].Genome Biology,2019,20:1-14. [46]HAN H,CHO J W,LEE S,et al.TRRUST v2:an expanded ref-erence database of human and mouse transcriptional regulatory interactions[J].Nucleic Acids Research,2018,46(D1):D380-D386. |
| [1] | 彭菊红, 张正悦, 丁子胥, 范馨予, 胡长玉, 赵明俊. 融合局部多视角语言特征和全局特征的对话情感四元组抽取 Multi-view Local Language Feature and Global Feature Fusion for Conversational Aspect-based Sentiment Quadruple Analysis 计算机科学, 2026, 53(4): 384-392. https://doi.org/10.11896/jsjkx.250900032 |
| [2] | 郑诚, 班晴晴. 知识辅助和强化句法驱动的方面级情感分析 Knowledge-assisted and Reinforced Syntax-driven for Aspect-based Sentiment Analysis 计算机科学, 2026, 53(4): 406-414. https://doi.org/10.11896/jsjkx.250600117 |
| [3] | 尹创, 刘建毅, 张茹. 跨模态融合的少样本勒索软件分类器:基于预训练模型的多模态编码 Cross-modal Fusion Few-sample Ransomware Classifier:Multimodal Encoding Based on Pre-trained Models 计算机科学, 2026, 53(4): 435-444. https://doi.org/10.11896/jsjkx.250500078 |
| [4] | 张雪芹, 王智能, 李晋生, 陆一松, 罗飞. 基于深度学习和多特征融合的时序社交网络关键节点识别 Key Node Identification in Temporal Social Networks Based on Deep Learning and Multi-feature Fusion 计算机科学, 2026, 53(4): 143-154. https://doi.org/10.11896/jsjkx.250300147 |
| [5] | 辜波凯, 刘盾, 孙扬. STWD-DLFRD:基于序贯三支决策与深度学习的多粒度虚假评论检测方法 STWD-DLFRD:Multi-granularity Fake Review Detection via Sequential Three-way Decisions and Deep Learning 计算机科学, 2026, 53(4): 188-196. https://doi.org/10.11896/jsjkx.250500088 |
| [6] | 王静红, 李鹏超, 米据生, 王威. 基于WL图核的多通道图Kolmogorov-Arnold网络 Multi-channel Graph Kolmogorov-Arnold Network Based on WL Graph Core 计算机科学, 2026, 53(4): 224-234. https://doi.org/10.11896/jsjkx.250600033 |
| [7] | 李泽群, 丁飞. 基于双分支融合与分段域适应迁移学习的疲劳驾驶检测 Fatigue Driving Detection Based on Dual-branch Fusion and Segmented Domain AdaptationTransfer Learning 计算机科学, 2026, 53(3): 78-87. https://doi.org/10.11896/jsjkx.250500025 |
| [8] | 王静红, 李鹏超, 王熙照, 张自立. 基于KAN的双通道图神经网络 Dual-channel Graph Neural Network Based on KAN 计算机科学, 2026, 53(3): 188-196. https://doi.org/10.11896/jsjkx.250600067 |
| [9] | 付昱凯, 李庆珍, 董志学, 师冬丽, 赵鹏. 基于少量目标数据和深度学习的行人重识别方法 Pedestrian Re-identification Methods Based on Limited Target Data and Deep Learning 计算机科学, 2026, 53(3): 287-294. https://doi.org/10.11896/jsjkx.260100073 |
| [10] | 喻定, 李章维. 基于Transformer架构的RNA二级结构预测方法 Prediction Method of RNA Secondary Structure Based on Transformer Architecture 计算机科学, 2026, 53(3): 375-382. https://doi.org/10.11896/jsjkx.250100005 |
| [11] | 杜剑彤, 管泽礼, 薛哲. 基于多任务学习的眼科视频特征融合与多维画像 Multi-task Learning-based Ophthalmic Video Feature Fusion and Multi-dimensional Profiling 计算机科学, 2026, 53(3): 383-391. https://doi.org/10.11896/jsjkx.260200058 |
| [12] | 苏睿韬, 任炯炯, 陈少真. 基于深度学习的GIFT-128与ASCON算法神经差分区分器研究 Deep Learning-based Neural Differential Distinguishers for GIFT-128 and ASCON 计算机科学, 2026, 53(3): 453-458. https://doi.org/10.11896/jsjkx.250600176 |
| [13] | 陈海涛, 梁俊威, 陈晨, 王宇帆, 周宇. 基于多模态体育教育数据的图空间融合动作识别方法 Multimodal Physical Education Data Fusion via Graph Alignment for Action Recognition 计算机科学, 2026, 53(2): 89-98. https://doi.org/10.11896/jsjkx.250800007 |
| [14] | 黄靖, 王腾, 刘健, 胡凯, 彭鑫, 黄亚敏, 文元桥. 多模态水声图像目标视觉检测 Multimodal Visual Detection for Underwater Sonar Target Images 计算机科学, 2026, 53(2): 227-235. https://doi.org/10.11896/jsjkx.241200082 |
| [15] | 刘晨红, 李凤莲, 阳佳, 王夙喆, 陈桂军. 聚焦边界和多尺度特征融合的脑卒中病灶分割 Boundary-focused Multi-scale Feature Fusion Network for Stroke Lesion Segmentation 计算机科学, 2026, 53(2): 264-272. https://doi.org/10.11896/jsjkx.250300137 |
|
||
首页