Screening biomarkers for spinal cord injury using weighted gene co-expression network analysis and machine learning

Immune changes and inflammatory responses have been identified as central events in the pathological process of spinal co rd injury.They can greatly affect nerve regeneration and functional recovery.However,there is still limited understanding of the peripheral immune inflammato ry response in spinal cord inju ry.In this study.we obtained microRNA expression profiles from the peripheral blood of patients with spinal co rd injury using high-throughput sequencing.We also obtained the mRNA expression profile of spinal cord injury patients from the Gene Expression Omnibus(GEO)database(GSE151371).We identified 54 differentially expressed microRNAs and 1656 diffe rentially expressed genes using bioinformatics approaches.Functional enrichment analysis revealed that various common immune and inflammation-related signaling pathways,such as neutrophil extracellular trap formation pathway,T cell receptor signaling pathway,and nuclear factor-κB signal pathway,we re abnormally activated or inhibited in spinal cord inju ry patient samples.We applied an integrated strategy that combines weighted gene co-expression network analysis,LASSO logistic regression,and SVM-RFE algorithm and identified three biomarke rs associated with spinal cord injury:ANO10,BST1,and ZFP36L2.We verified the expression levels and diagnostic perfo rmance of these three genes in the original training dataset and clinical samples through the receiver operating characteristic curve.Quantitative polymerase chain reaction results showed that ANO20 and BST1 mRNA levels were increased and ZFP36L2 mRNA was decreased in the peripheral blood of spinal cord injury patients.We also constructed a small RNA-mRNA interaction network using Cytoscape.Additionally,we evaluated the proportion of 22 types of immune cells in the peripheral blood of spinal co rd injury patients using the CIBERSORT tool.The proportions of naive B cells,plasma cells,monocytes,and neutrophils were increased while the proportions of memory B cells,CD8^(+)T cells,resting natural killer cells,resting dendritic cells,and eosinophils were markedly decreased in spinal cord injury patients increased compared with healthy subjects,and ANO10,BST1 and ZFP26L2we re closely related to the proportion of certain immune cell types.The findings from this study provide new directions for the development of treatment strategies related to immune inflammation in spinal co rd inju ry and suggest that ANO10,BST2,and ZFP36L2 are potential biomarkers for spinal cord injury.The study was registe red in the Chinese Clinical Trial Registry(registration No.ChiCTR2200066985,December 12,2022).

scLink:Inferring Sparse Gene Co-expression Networks fromSingle-cell Expression Data

A system-level understanding of the regulation and coordination mechanisms of gene expression is essential for studying the complexity of biological processes in health and disease.With the rapid development of single-cell RNA sequencing technologies,it is now possible to investigate gene interactions in a cell type-specific manner.Here we propose the scLink method,which uses statistical network modeling to understand the co-expression relationships among genes and construct sparse gene co-expression networks from single-cell gene expression data.We use both simulation and real data studies to demonstrate the advantages of scLink and its ability to improve single-cell gene network analysis.The scLink R package is available at https://github.com/Vivianstats/scLink.

Target Entrapment Based on Adaptive Transformation of Gene Regulatory Networks

The complexity of unknown scenarios and the dynamics involved in target entrapment make designing control strategies for swarm robots a formidable task,which in turn impacts their efficiency in complex and dynamic settings.To address these challenges,this paper introduces an adaptive swarm robot entrapment control model grounded in the transformation of gene regulatory networks(AT-GRN).This innovative model enables swarm robots to dynamically adjust entrap-ment strategies by assessing current environmental conditions via real-time sensory data.Further-more,an improved motion control model for swarm robots is designed to dynamically shape the for-mation generated by the AT-GRN.Through two sets of rigorous experimental environments,the proposed model significantly enhances the trapping performance of swarm robots in complex envi-ronments,demonstrating remarkable adaptability and stability.

Identify the signature genes for diagnose of uveal melanoma by weight gene co-expression network analysis

AIM: To identify and understand the relationship between co-expression pattern and clinic traits in uveal melanoma, weighted gene co-expression network analysis(WGCNA) is applied to investigate the gene expression levels and patient clinic features. Uveal melanoma is the most common primary eye tumor in adults. Although many studies have identified some important genes and pathways that were relevant to progress of uveal melanoma, the relationship between co-expression and clinic traits in systems level of uveal melanoma is unclear yet. We employ WGCNA to investigate the relationship underlying molecular and phenotype in this study.METHODS: Gene expression profile of uveal melanoma and patient clinic traits were collected from the Gene Expression Omnibus(GEO) database. The gene co-expression is calculated by WGCNA that is the R package software. The package is used to analyze the correlation between pairs of expression levels of genes.The function of the genes were annotated by gene ontology(GO).RESULTS: In this study, we identified four co-expression modules significantly correlated with clinictraits. Module blue positively correlated with radiotherapy treatment. Module purple positively correlates with tumor location(sclera) and negatively correlates with patient age. Module red positively correlates with sclera and negatively correlates with thickness of tumor. Module black positively correlates with the largest tumor diameter(LTD). Additionally, we identified the hug gene(top connectivity with other genes) in each module. The hub gene RPS15 A, PTGDS, CD53 and MSI2 might play a vital role in progress of uveal melanoma.CONCLUSION: From WGCNA analysis and hub gene calculation, we identified RPS15 A, PTGDS, CD53 and MSI2 might be target or diagnosis for uveal melanoma.

Identification of key genes involved in axon regeneration and Wallerian degeneration by weighted gene co-expression network analysis

Peripheral nerve injury repair requires a certain degree of cooperation between axon regeneration and Wallerian degeneration.Therefore,investigating how axon regeneration and degeneration work together to repair peripheral nerve injury may uncover the molecular mechanisms and signal cascades underlying peripheral nerve repair and provide potential strategies for improving the low axon regeneration capacity of the central nervous system.In this study,we applied weighted gene co-expression network analysis to identify differentially expressed genes in proximal and distal sciatic nerve segments from rats with sciatic nerve injury.We identified 31 and 15 co-expression modules from the proximal and distal sciatic nerve segments,respectively.Functional enrichment analysis revealed that the differentially expressed genes in proximal modules promoted regeneration,while the differentially expressed genes in distal modules promoted neurodegeneration.Next,we constructed hub gene networks for selected modules and identified a key hub gene,Kif22,which was up-regulated in both nerve segments.In vitro experiments confirmed that Kif22 knockdown inhibited proliferation and migration of Schwann cells by modulating the activity of the extracellular signal-regulated kinase signaling pathway.Collectively,our findings provide a comparative framework of gene modules that are co-expressed in injured proximal and distal sciatic nerve segments,and identify Kif22 as a potential therapeutic target for promoting peripheral nerve injury repair via Schwann cell proliferation and migration.All animal experiments were approved by the Institutional Animal Ethics Committee of Nantong University,China(approval No.S20210322-008)on March 22,2021.

Weighted Gene Co-expression Network Analysis of Gene Modules for the Prognosis of Esophageal Cancer

Esophageal cancer is a common malignant tumor, whose pathogenesis and prognosis factors are not fully understood. This study aimed to discover the gene clusters that have similar functions and can be used to predict the prognosis of esophageal cancer. The matched microarray and RNA sequencing data of 185 patients with esophageal cancer were downloaded from The Cancer Genome Atlas(TCGA), and gene co-expression networks were built without distinguishing between squamous carcinoma and adenocarcinoma. The result showed that 12 modules were associated with one or more survival data such as recurrence status, recurrence time, vital status or vital time. Furthermore, survival analysis showed that 5 out of the 12 modules were related to progression-free survival(PFS) or overall survival(OS). As the most important module, the midnight blue module with 82 genes was related to PFS, apart from the patient age, tumor grade, primary treatment success, and duration of smoking and tumor histological type. Gene ontology enrichment analysis revealed that 'glycoprotein binding' was the top enriched function of midnight blue module genes. Additionally, the blue module was the exclusive gene clusters related to OS. Platelet activating factor receptor(PTAFR) and feline Gardner-Rasheed(FGR) were the top hub genes in both modeling datasets and the STRING protein interaction database. In conclusion, our study provides novel insights into the prognosis-associated genes and screens out candidate biomarkers for esophageal cancer.

Identification of Potential Therapeutic Targets of Alzheimer's Disease By Weighted Gene Co-Expression Network Analysis

Objective Alzheimer's disease(AD)is the most common cause of dementia.The pathophysiology of the disease mostly remains unearthed,thereby challenging drug development for AD.This study aims to screen high throughput gene expression data using weighted co-expression network analysis(WGCNA)to explore the potential therapeutic targets.Methods The dataset of GSE36980 was obtained from the Gene Expression Omnibus(GEO)database.Normalization,quality control,filtration,and soft-threshold calculation were carried out before clustering the co-expressed genes into different modules.Furthermore,the correlation coefiidents between the modules and clinical traits were computed to identify the key modules.Gene ontology and pathway enrichment analyses were performed on the key module genes.The STRING database was used to construct the protein-protein interaction(PPI)networks,which were further analyzed by Cytoscape app(MCODE).Finally,validation of hub genes was conducted by external GEO datasets of GSE 1297 and GSE 28146.Results Co-expressed genes were clustered into 27 modules,among which 6 modules were identified as the key module relating to AD occurrence.These key modules are primarily involved in chemical synaptic transmission(G0:0007268),the tricarboxylic acid(TCA)cycle and respiratory electron transport(R-HSA-1428517).WDR47,OXCT1,C3orfl4,ATP6V1A,SLC25A14,NAPB were found as the hub genes and their expression were validated by external datasets.Conclusions Through modules co-expression network analyses and PPI network analyses,we identified the hub genes of AD,including WDR47,0XCT1,C3orfl4i ATP6V1A,SLC25A14 and NAPB.Among them,three hub genes(ATP6V1A,SLC25A14,OXCT1)might contribute to AD pathogenesis through pathway of TCA cycle.

Weighted gene co-expression network analysis reveals similarities and differences of molecular features between dilated and ischemic cardiomyopathies

Cardiomyopathies represent the most common clinical and genetic heterogeneous group of diseases that affect the heart function.Though progress has been made to elucidate the process,molecular mechanisms of different classes of cardiomyopathies remain elusive.This paper aims to describe the similarities and differences in molecular features of dilated cardiomyopathy(DCM)and ischemic cardiomyopathy(ICM).We firstly detected the co-expressed modules using the weighted gene co-expression network analysis(WGCNA).Significant modules associated with DCM/ICM were identified by the Pearson correlation coefficient(PCC)between the modules and the phenotype of DCM/ICM.The differentially expressed genes in the modules were selected to perform functional enrichment.The potential transcription factors(TFs)prediction was conducted for transcription regulation of hub genes.Apoptosis and cardiac conduction were perturbed in DCM and ICM,respectively.TFs demonstrated that the biomarkers and the transcription regulations in DCM and ICM were different,which helps make more accurate discrimination between them at molecular levels.In conclusion,comprehensive analyses of the molecular features may advance our understanding of DCM and ICM causes and progression.Thus,this understanding may promote the development of innovative diagnoses and treatments.

Identification of Differentially Expressed Genes in Grape Skin at Veraison and Maturity and Construction of Co-expression Network

The ripening process of grape is an important stage during grape growth and development. During this process, color of grape skin is the most obvious change. The molecular mechanism for the ripening of grape(a non-climacteric fruit, which ripens without ethylene and respiration bursts) is still unclear. Although numerous studies have been done on the changes in the contents of metabolites during grape ripening, the differentially expressed genes at veraison and maturity stages have not been systematically analyzed. In this study, 1 524 genes that are significantly differentially expressed in grape(Pinot Noir) skin at veraison and maturity stages were identified, and a co-expression network of these genes was built. Some of the eight co-expression modules we identified may be closely related to the synthesis or metabolism of anthocyanins, sugar acids, and other flavor substances. The transcription factor families WRKY, b ZIP, HSF and WOX may play an important role in the regulation of anthocyanin synthesis or metabolism. The results provide a foundation for further study of the molecular mechanism of grape ripening.

Identification of Potential Zinc Deficiency Responsive Genes and Regulatory Pathways in Rice by Weighted Gene Co-expression Network Analysis

Zinc(Zn)malnutrition is a major public health issue.Genetic biofortification of Zn in rice grain can alleviate global Zn malnutrition.Therefore,elucidating the genetic mechanisms regulating Zn deprivation response in rice is essential to identify elite genes useful for breeding high grain Zn rice varieties.Here,a meta-analysis of previous RNA-Seq studies involving Zn deficient conditions was conducted using the weighted gene co-expression network analysis(WGCNA)and other in silico prediction tools to identify modules(denoting cluster of genes with related expression pattern)of co-expressed genes,modular genes which are conserved differentially expressed genes(DEGs)across independent RNA-Seq studies,and the molecular pathways of the conserved modular DEGs.WGCNA identified 16 modules of co-expressed genes.Twenty-eight and five modular DEGs were conserved in leaf and crown,and root tissues across two independent RNA-Seq studies.Functional enrichment analysis showed that 24 of the 28 conserved modular DEGs from leaf and crown tissues significantly up-regulated 2 Kyoto Encyclopedia of Genes and Genomes(KEGG)pathways and 15 Gene Ontology(GO)terms,including the substrate-specific transmembrane transporter and the small molecule metabolic process.Further,the well-studied transcription factors(OsWOX11 and OsbHLH120),protein kinase(OsCDPK20 and OsMPK17),and miRNAs(OSA-MIR397A and OSA-MIR397B)were predicted to target some of the identified conserved modular DEGs.Out of the 24 conserved and up-regulated modular DEGs,19 were yet to be experimentally validated as Zn deficiency responsive genes.Findings from this study provide a comprehensive insight on the molecular mechanisms of Zn deficiency response and may facilitate gene and pathway prioritization for improving Zn use efficiency and Zn biofortification in rice.

Co-expression Network Analysis Identifies Fourteen Hub Genes Associated with Prognosis in Clear Cell Renal Cell Carcinoma

Summary:Renal cancer is a common genitourinary malignance,of which clear cell renal cell carcinoma(ccRCC)has high aggressiveness and leads to most cancer-related deaths.Identification of sensitive and reliable biomarkers for predicting tumorigenesis and progression has great significance in guiding the diagnosis and treatment of ccRCC.Here,we identified 2397 common difTerentially expressed genes(DEGs)using paired normal and tumor ccRCC tissues from GSE53757 and The Cancer Genome Atlas(TCGA).Then,we performed weighted gene co-expression network analysis and protein-protein interaction network analysis,17 candidate hub genes were identified.These candidate hub genes were further validated in GSE36895 and Oncomine database and 14 real hub genes were identified.All the hub genes were up-regulated and significantly positively correlated with pathological stage and histologic grade of ccRCC.Survival analysis showed that the higher expression level of each hub gene tended to predict a worse clinical outcome.ROC analysis showed that all the hub genes can accurately distinguish between tumor and normal samples,and between early stage and advanced stage ccRCC.Moreover,all the hub genes were positively associated with distant metastasis,lymph node infiltration,tumor recurrence and the expression of MKi67,suggesting these genes might promote tumor proliferation,invasion and metastasis.Furthermore,the functional annotation demonstrated that most genes were enriched in cell-cycle related biological function.In summary,our study identified 14 potential biomarkers for predicting tumorigenesis and progression,which might contribute to early diagnosis,prognosis prediction and therapeutic intervention.

Identification of potential key molecules and signaling pathways for psoriasis based on weighted gene co-expression network analysis

BACKGROUND Psoriasis is a chronic inflammatory skin disease,the pathogenesis of which is more complicated and often requires long-term treatment.In particular,moderate to severe psoriasis usually requires systemic treatment.Psoriasis is also associated with many diseases,such as cardiometabolic diseases,malignant tumors,infections,and mood disorders.Psoriasis can appear at any age,and lead to a substantial burden for individuals and society.At present,psoriasis is still a treatable,but incurable,disease.Previous studies have found that micro RNAs(mi RNAs)play an important regulatory role in the progression of various diseases.Currently,mi RNAs studies in psoriasis and dermatology are relatively new.Therefore,the identification of key mi RNAs in psoriasis is helpful to elucidate the molecular mechanism of psoriasis.AIM To identify key molecular markers and signaling pathways to provide potential basis for the treatment and management of psoriasis.METHODS The mi RNA and m RNA data were obtained from the Gene Expression Omnibus database.Then,differentially expressed m RNAs(DEm RNAs)and differentially expressed mi RNAs(DEmi RNAs)were screened out by limma R package.Subsequently,DEm RNAs were analyzed for Gene Ontology and Kyoto Encyclopedia of Genes and Genomics functional enrichment.The“WGCNA”R package was used to analyze the co-expression network of all mi RNAs.In addition,we constructed mi RNA-m RNA regulatory networks based on identified hub mi RNAs.Finally,in vitro validation was performed.All experimental procedures were approved by the ethics committee of Chinese PLA General Hospital(S2021-012-01).RESULTS A total of 639 DEm RNAs and 84 DEmi RNAs were identified.DEm RNAs screening criteria were adjusted P(adj.P)value<0.01 and|log Fold Change|(|log FC|)>1.DEmi RNAs screening criteria were adj.P value<0.01 and|logFC|>1.5.KEGG functional analysis demonstrated that DEm RNAs were significantly enriched in immune-related biological functions,for example,tolllike receptor signaling pathway,cytokine-cytokine receptor interaction,and chemokine signaling pathway.In weighted gene co-expression network analysis,turquoise module was the hub module.Moreover,10 hub mi RNAs were identified.Among these 10 hub mi RNAs,only 8 hub mi RNAs predicted the corresponding target m RNAs.97 negatively regulated mi RNA-m RNA pairs were involved in the mi RNA-m RNA regulatory network,for example,hsa-mi R-21-5 pclaudin 8(CLDN8),hsa-mi R-30 a-3 p-interleukin-1 B(IL-1 B),and hsa-mi R-181 a-5 p/hsa-mi R-30 c-2-3 p-C-X-C motif chemokine ligand 9(CXCL9).Real-time polymerase chain reaction results showed that IL-1 B and CXCL9 were up-regulated and CLDN8 was down-regulated in psoriasis with statistically significant differences.CONCLUSION The identification of potential key molecular markers and signaling pathways provides potential research directions for further understanding the molecular mechanisms of psoriasis.This may also provide new research ideas for the prevention and treatment of psoriasis in the future.

3-80 Identify the Signature Genes for Diagnose of Uveal Melanoma by Weight Gene Co-expression Network Analysis

Weighted Gene Co-expression Network Analysis (WGCNA) is a powerful tool which is applied to investigate the relationship between gene expression levels and patient clinic traits[1;2]. In this study, we identified four co-expression modules significantly correlated with clinic traits. Module blue positively correlated with radiotherapy treatment;module purple positively correlates with tumor location (sclera) and negatively correlates with patient age;

Co-expression network analysis of virulence genes exoS and exoU of pseudomonas aeruginosa in lower respiratory tract based on histological data expression profiles

Objective:To use the gene chip of pseudomonas aeruginosa as a research sample and to explore it at an omics level,aiming at elucidating the co-expression network characteristics of the virulence genes exoS and exoU of pseudomonas aeruginosa in the lower respiratory tract from the perspective of molecular biology and identifying its key regulatory genes.Methods:From March 2016 to May 2018,312 patients infected with pseudomonas aeruginosa in the lower respiratory tract who were admitted to Department of Respiratory Medicine of Baogang Hospital and given follow-up treatments in the hospital were selected as subjects by use of cluster sampling.Alveolar lavage fluid and sputum collected from those patients were used as biological specimens.The genes of pseudomonas aeruginosa were detected with the help of oligonucleotide probes to make a pre-processing of chip data.A total of 8 common antibiotics(ceftazidime,gentamicin,piperacillin,amikacin,ciprofloxacin,levofloxacin,doripenem and ticarcillin)against Gram-negative bacteria were selected to determine the drug resistance of biological specimens.MCODE algorithm was used to construct a co-expression network model of the drug-resistance genes focused on exoS/exoU.Results:The expression level of exoS/exoU in the drug-resistance group was significantly higher than that in the non-resistance group(p<0.05).The top 5 differentially expressed genes in the alveolar lavage fluid specimens from the drug-resistance group were RAC1,ITGB1,ITGB5,CRK and IGF1R in the order from high to low.In the sputum specimens,the top 5 differentially expressed genes were RAC1,CRK,IGF1R,ITGB1 and ITGB5.In the alveolar lavage fluid specimens,only RAC1 had a positive correlation with the expression of exoS and exoU(p<0.05).In the sputum specimens,RAC1,ITGB1,ITGB5,CRK and IGF1R were positively correlated with the expression of exoS and exoU(p<0.05).The genes included in the co-expression network contained exoS,exoU,RAC1,ITGB1,ITGB5,CRK,CAMK2D,RHOA,FLNA,IGF1R,TGFBR2 and FOS.Among them,RAC1 had a highest score in the aspect of regulatory ability(72.00)and the largest number of regulatory genes(6);followed by ITGB1,ITGB5 and CRK genes.Conclusions:The high expression of exoS and exoU in the sputum specimens suggests that pseudomonas aeruginosa has a higher probability to get resistant to antibiotics;RAC1,ITGB1,ITGB5 and CRK genes may be the key genes that can regulate the expression of exoS and exoU.

Discovering hidden information of gene ontology based on complex networks analysis

To resolve the ontology understanding problem, the structural features and the potential important terms of a large-scale ontology are investigated from the perspective of complex networks analysis. Through the empirical studies of the gene ontology with various perspectives, this paper shows that the whole gene ontology displays the same topological features as complex networks including ＂small world＂ and ＂scale-free＂,while some sub-ontologies have the ＂scale-free＂ property but no ＂small world＂ effect.The potential important terms in an ontology are discovered by some famous complex network centralization methods.An evaluation method based on information retrieval in MEDLINE is designed to measure the effectiveness of the discovered important terms.According to the relevant literature of the gene ontology terms,the suitability of these centralization methods for ontology important concepts discovering is quantitatively evaluated.The experimental results indicate that the betweenness centrality is the most appropriate method among all the evaluated centralization measures.

Fluctuation Resonance of Feed Forward Loops in Gene Regulatory Networks

The feed forward loop （FFL）, wherein a gene X can regulate target gene Z alone or cooperatively with gene Y, is one of the most important motifs in gene regulatory networks. Gene expression often involves a small number of reactant molecules and thus internal molecular fluctuation is considerable. Here we studied how an FFL responds to small external signal inputs at gene X, with particular attention paid to the fluctuation resonance （FR） phenomenon of gene Z. We found that for all coherent FFLs, where the sign of the direct regulation path from X to Z is the same as the overall sign of the indirect path via Y, the FR shows a regular single peak, while for incoherent FFLs, the FR exhibits distinct bimodal shapes. The results indicate that one could use small external signals to help identify the regulatory structure of an unknown FFL in complex gene networks.

Predicting Arabidopsis thaliana Gene Function by Transitiving Co-expression in Shortest-path

The present paper predicted the function of unknow genes by analyzing the co-expression data of Arabidopsis thaliana from biological pathway based on the shortest-path algorithm. This paper proposed that transitive co-expression among genes can be used as an important attribute to link genes of the same biological pathway. The genes from the same biological pathway with similar functions are strongly correlated in expression. Moreover,the function of unknown genes can be predicted by the known genes where they are strongly correlated in expression lying on the same shortest-path from the biological pathway. Analyzing the Arabidopsis thaliana from the biological pathway,this study showed that this method can reliably reveal function of the unknown Arabidopsis thaliana genes and the approach of predicting gene function by transitiving co-expression in shortest-path is feasible and effective.

Reconstruction of Gene Regulatory Networks Based on Two-Stage Bayesian Network Structure Learning Algorithm

In the post-genomic biology era,the reconstruction of gene regulatory networks from microarray gene expression data is very important to understand the underlying biological system,and it has been a challenging task in bioinformatics.The Bayesian network model has been used in reconstructing the gene regulatory network for its advantages,but how to determine the network structure and parameters is still important to be explored.This paper proposes a two-stage structure learning algorithm which integrates immune evolution algorithm to build a Bayesian network.The new algorithm is evaluated with the use of both simulated and yeast cell cycle data.The experimental results indicate that the proposed algorithm can find many of the known real regulatory relationships from literature and predict the others unknown with high validity and accuracy.

Reconstructing gene regulatory networks in single-cell transcriptomic data analysis

Gene regulatory networks play pivotal roles in our understanding of biological processes/mechanisms at the molecular level.Many studies have developed sample-specific or cell-type-specific gene regulatory networks from single-cell transcriptomic data based on a large amount of cell samples.Here,we review the state-of-the-art computational algorithms and describe various applications of gene regulatory networks in biological studies.

Combination of Neuro-Fuzzy Network Models with Biological Knowledge for Reconstructing Gene Regulatory Networks

Inferring gene regulatory networks from large-scale expression data is an important topic in both cellular systems and computational biology. The inference of regulators might be the core factor for understanding actual regulatory conditions in gene regulatory networks, especially when strong regulators do work significantly. In this paper, we propose a novel approach based on combining neuro-fu^zy network models with biological knowledge to infer strong regulators and interrelated fuzzy rules. The hybrid neuro-fuzzy architecture can not only infer the fuzzy rules, which are suitable for describing the regulatory conditions in regulatory nctworks＋ but also explain the meaning of nodes and weight value in the neural network. It can get useful rules automatically without lhctitious judgments. At the same time, it does not add recursive layers to the model, and the model can also strengthen the relationships among genes and reduce calculation. We use the proposed approach to reconstruct a partial gene regulatory network of yeast, The results show that this approach can work effectively.