A Novel Deep Learning-Based Model for Classification of Wheat Gene Expression

Deep learning(DL)plays a critical role in processing and converting data into knowledge and decisions.DL technologies have been applied in a variety of applications,including image,video,and genome sequence analysis.In deep learning the most widely utilized architecture is Convolutional Neural Networks(CNN)are taught discriminatory traits in a supervised environment.In comparison to other classic neural networks,CNN makes use of a limited number of artificial neurons,therefore it is ideal for the recognition and processing of wheat gene sequences.Wheat is an essential crop of cereals for people around the world.Wheat Genotypes identification has an impact on the possible development of many countries in the agricultural sector.In quantitative genetics prediction of genetic values is a central issue.Wheat is an allohexaploid(AABBDD)with three distinct genomes.The sizes of the wheat genome are quite large compared to many other kinds and the availability of a diversity of genetic knowledge and normal structure at breeding lines of wheat,Therefore,genome sequence approaches based on techniques of Artificial Intelligence(AI)are necessary.This paper focuses on using the Wheat genome sequence will assist wheat producers in making better use of their genetic resources and managing genetic variation in their breeding program,as well as propose a novel model based on deep learning for offering a fundamental overview of genomic prediction theory and current constraints.In this paper,the hyperparameters of the network are optimized in the CNN to decrease the requirement for manual search and enhance network performance using a new proposed model built on an optimization algorithm and Convolutional Neural Networks(CNN).

Deep Learning Enabled Microarray Gene Expression Classification for Data Science Applications

In bioinformatics applications,examination of microarray data has received significant interest to diagnose diseases.Microarray gene expression data can be defined by a massive searching space that poses a primary challenge in the appropriate selection of genes.Microarray data classification incorporates multiple disciplines such as bioinformatics,machine learning(ML),data science,and pattern classification.This paper designs an optimal deep neural network based microarray gene expression classification(ODNN-MGEC)model for bioinformatics applications.The proposed ODNN-MGEC technique performs data normalization process to normalize the data into a uniform scale.Besides,improved fruit fly optimization(IFFO)based feature selection technique is used to reduce the high dimensionality in the biomedical data.Moreover,deep neural network(DNN)model is applied for the classification of microarray gene expression data and the hyperparameter tuning of the DNN model is carried out using the Symbiotic Organisms Search(SOS)algorithm.The utilization of IFFO and SOS algorithms pave the way for accomplishing maximum gene expression classification outcomes.For examining the improved outcomes of the ODNN-MGEC technique,a wide ranging experimental analysis is made against benchmark datasets.The extensive comparison study with recent approaches demonstrates the enhanced outcomes of the ODNN-MGEC technique in terms of different measures.

A data structure and function classification based method to evaluate clustering models for gene expression data

Objective:To establish a systematic framework for selecting the best clustering algorithm and provide an evaluation method for clustering analyses of gene expression data. Methods: Based on data structure (internal information) and function classification (external information), the evaluation of gene expression data analyses were carried out by using 2 approaches. Firstly, to assess the predictive power of clusteringalgorithms, Entropy was introduced to measure the consistency between the clustering results from different algorithms and the known and validated functional classifications. Secondly, a modified method of figure of merit (adjust-FOM) was used as internal assessment method. In this method, one clustering algorithm was used to analyze all data but one experimental condition, the remaining condition was used to assess the predictive power of the resulting clusters. This method was applied on 3 gene expression data sets (2 from the Lyer's Serum Data Sets, and 1 from the Ferea's Saccharomyces Cerevisiae Data Set). Results: A method based on entropy and figure of merit (FOM) was proposed to explore the results of the 3 data sets obtained by 6 different algorithms, SOM and Fuzzy clustering methods were confirmed to possess the highest ability to cluster. Conclusion: A method based on entropy is firstly brought forward to evaluate clustering analyses.Different results are attained in evaluating same data set due to different function classification. According to the curves of adjust_FOM and Entropy_FOM, SOM and Fuzzy clustering methods show the highest ability to cluster on the 3 data sets.

Enhancing Cancer Classification through a Hybrid Bio-Inspired Evolutionary Algorithm for Biomarker Gene Selection

In this study,our aim is to address the problem of gene selection by proposing a hybrid bio-inspired evolutionary algorithm that combines Grey Wolf Optimization(GWO)with Harris Hawks Optimization(HHO)for feature selection.Themotivation for utilizingGWOandHHOstems fromtheir bio-inspired nature and their demonstrated success in optimization problems.We aimto leverage the strengths of these algorithms to enhance the effectiveness of feature selection in microarray-based cancer classification.We selected leave-one-out cross-validation(LOOCV)to evaluate the performance of both two widely used classifiers,k-nearest neighbors(KNN)and support vector machine(SVM),on high-dimensional cancer microarray data.The proposed method is extensively tested on six publicly available cancer microarray datasets,and a comprehensive comparison with recently published methods is conducted.Our hybrid algorithm demonstrates its effectiveness in improving classification performance,Surpassing alternative approaches in terms of precision.The outcomes confirm the capability of our method to substantially improve both the precision and efficiency of cancer classification,thereby advancing the development ofmore efficient treatment strategies.The proposed hybridmethod offers a promising solution to the gene selection problem in microarray-based cancer classification.It improves the accuracy and efficiency of cancer diagnosis and treatment,and its superior performance compared to other methods highlights its potential applicability in realworld cancer classification tasks.By harnessing the complementary search mechanisms of GWO and HHO,we leverage their bio-inspired behavior to identify informative genes relevant to cancer diagnosis and treatment.

Dietary manganese supplementation inhibits abdominal fat deposition possibly by regulating gene expression and enzyme activity involved in lipid metabolism in the abdominal fat of broilers

Excessive abdominal fat deposition seriously restricts the production efficiency of broilers.Several studies found that dietary supplemental manganese(Mn)could effectively reduce the abdominal fat deposition of broilers,but the underlying mechanisms remain unclear.The present study aimed to investigate the effect of dietary supplementation with the inorganic or organic Mn on abdominal fat deposition,and enzyme activity and gene expression involved in lipid metabolism in the abdominal fat of male or female broilers.A total of 4201-d-old AA broilers(half males and half females)were randomly allotted by body weight and gender to 1 of 6 treatments with 10 replicates cages of 7 chicks per cage in a completely randomized design involving a 3(dietary Mn addition)×2(gender)factorial arrangement.Male or female broilers were fed with the Mn-unsupplemented basal diets containing 17.52 mg Mn kg^(-1)(d 1-21)and 15.62 mg Mn kg^(-1)(d 22-42)by analysis or the basal diets supplemented with 110 mg Mn kg^(-1)(d 1-21)and 80 mg Mn kg^(-1)(d 22-42)as either the Mn sulfate or the Mn proteinate with moderate chelation strength(Mn-Prot M)for 42 d.The results showed that the interaction between dietary Mn addition and gender had no impact(P>0.05)on any of the measured parameters;abdominal fat percentage of broilers was decreased(P<0.003)by Mn addition;Mn addition increased(P<0.004)adipose triglyceride lipase(ATGL)activity,while Mn-Prot M decreased(P<0.002)the fatty acid synthase(FAS)activity in the abdominal fat of broilers compared to the control;Mn addition decreased(P<0.009)diacylglycerol acyltransferase 2(DGAT2)mRNA expression level and peroxisome proliferator-activated receptor γ(PPARγ)mRNA and protein expression levels,but up-regulated(P<0.05)the ATGL mRNA and protein expression levels in the abdominal fat of broilers.It was concluded that dietary supplementation with Mn inhibited the abdominal fat deposition of broilers possibly via decreasing the expression of PPARγand DGAT2 as well as increasing the expression and activity of ATGL in the abdominal fat of broilers,and Mn-Prot M was more effective in inhibiting the FAS acitivity.

Effects of pyraclostrobin on growth,oxidative stress,and gene expression in relation to stress and ATP-binding cassette transporters in Tetrahymena thermophila

Pyraclostrobin(PYR),a widely used fungicide,has negative effects on fish and algae,but its toxicity in protozoa remains unclear.In this study,the effects of PYR on the growth,oxidative stress,and gene expression related to stress and ATP-binding cassette(ABC)transporters in Tetrahymena thermophila were investigated.The result showed that the 96-h IC_(50)of PYR against T.thermophila was 17.2 mg/L.Moreover,PYR inhibited the growth of T.thermophila in concentration-or time-dependent manner.A morphological study revealed that the shape and size of T.thermophila changed,and damage of cell membrane surface was observed by scanning electron microscopy after 96 h of PYR exposure.The activities of superoxide dismutase(SOD)and catalase(CAT)increased throughout the experiment.In contrast,the glutathione(GSH)content was increased at 24 h and 48 h of exposure and decreased at 96 h.Moreover,a significant increase in malondialdehyde(MDA)level was observed in T.thermophila after96 h of exposure.Furthermore,PYR upregulated the HSP703,HSP705,GPx2,and ABAC15 gene expression in the 0.1–5-mg/L groups and downregulated the HSP704,HSP90,TGR,and ABCC52 mRNA levels at 96 h of exposure.These results suggest that PYR may exert adverse effects on T.thermophila by inducing oxidative stress and changing the gene expression related to ABC transporters and stress,which may enrich the understanding of the toxicity mechanism of PYR in aquatic organisms and provide reference data for aquatic ecological risk assessments.

Effects of antioxidant‑rich Lactiplantibacillus plantarum inoculated alfalfa silage on rumen fermentation, antioxidant and immunity status, and mammary gland gene expression in dairy goats

Background Milk synthesis in lactating animals demands high energy metabolism,which results in an increased production of reactive oxygen metabolites(ROM)causing an imbalance between oxidants and antioxidants thereby inducing oxidative stress(OS)on the animals.To mitigate OS and postpartum disorders in dairy goats and gain insight into the impact of dietary choices on redox status during lactation,a feeding trial was conducted using alfalfa silage inoculated with a high-antioxidant strain of Lactiplantibacillus plantarum.Methods Twenty-four Guanzhong dairy goats(38.1±1.20 kg)were randomly assigned to two dietary treatments:one containing silage inoculated with L.plantarum MTD/1(RSMTD-1),and the other containing silage inoculated with high antioxidant activity L.plantarum 24-7(ES24-7).Results ES24-7-inoculated silage exhibited better fermentation quality and antioxidant activity compared to RSMTD-1.The ES24-7 diet elevated the total antioxidant capacity(T-AOC),superoxide dismutase(SOD),glutathione peroxi-dase(GSH-Px),and catalase(CAT)activities in milk,serum,and feces of lactating goats(with the exception of T-AOC in milk).Additionally,the diet containing ES24-7 inoculated silage enhanced casein yield,milk free fatty acid(FFA)content,and vitamin A level in the goats’milk.Furthermore,an increase of immunoglobulin(Ig)A,IgG,IgM,inter-leukin(IL)-4,and IL-10 concentrations were observed,coupled with a reduction in IL-1β,IL-2,IL-6,interferon(IFN)-γ,and tumor necrosis factor(TNF)-αconcentrations in the serum of lactating goats fed ES24-7.Higher concentrations of total volatile fatty acid(VFA),acetate,and propionate were observed in the rumen fluid of dairy goats fed ES24-7 inoculated silage.Moreover,the diet containing ES24-7 inoculated silage significantly upregulated the expression of nuclear factor erythroid 2 like 2(NFE2L2),beta-carotene oxygenase 1(BCO1),SOD1,SOD2,SOD3,GPX2,CAT,glu-tathione-disulfide reductase(GSR),and heme oxygenase 1(HMOX1)genes in the mammary gland,while decreased the levels of NADPH oxidase 4(NOX4),TNF,and interferon gamma(IFNG).Conclusions These findings indicated that feeding L.plantarum 24-7 inoculated alfalfa silage not only improved rumen fermentation and milk quality in lactating dairy goats but also boosted their immunity and antioxidant status by modulating the expression of several genes related to antioxidant and inflammation in the mammary gland.

Decoding Retinoblastoma: Differential Gene Expression

Background: Retinoblastoma, the most common intraocular pediatric cancer, presents complexities in its genetic landscape that necessitate a deeper understanding for improved therapeutic interventions. This study leverages computational tools to dissect the differential gene expression profiles in retinoblastoma. Methods: Employing an in silico approach, we analyzed gene expression data from public repositories by applying rigorous statistical models, including limma and de seq 2, for identifying differentially expressed genes DEGs. Our findings were validated through cross-referencing with independent datasets and existing literature. We further employed functional annotation and pathway analysis to elucidate the biological significance of these DEGs. Results: Our computational analysis confirmed the dysregulation of key retinoblastoma-associated genes. In comparison to normal retinal tissue, RB1 exhibited a 2.5-fold increase in expression (adjusted p Conclusions: Our analysis reinforces the critical genetic alterations known in retinoblastoma and unveils new avenues for research into the disease’s molecular basis. The discovery of chemoresistance markers and immune-related genes opens potential pathways for personalized treatment strategies. The study’s outcomes emphasize the power of in silico analyses in unraveling complex cancer genomics.

Gene expression analysis of cytokines and MMPs in melatonin and rhBMP-2 enhanced bone remodeling

BACKGROUND In the medical and dental fields,there is a need for studies of new therapeutic approaches for the treatment of bone defects that cause extensive bone loss.Melatonin may be an important endogenous biological factor for bone remodeling,and growth factors may enhance the repair process.AIM To evaluate the gene expression of cytokines(IL-1β,IL-6,IL-10 and TNF-α),markers of osteoclastogenesis(RANK,RANKL and OPG)and MMPs(MMP-1,MMP-2,MMP-8 and MMP-13)from the treatment of melatonin associated with an osteogenic membrane and rhBMP-2 on the recovery of a bone injury.METHODS Sixty-four rats were used and divided into 9 experimental groups and were formed according to the treatment carried out in the region of the bone lesion,which varied between the combination of 1,10 and 100μmol/L of melatonin.Gene Expression analysis was performed using real time-PCR by reading the concentration of total RNA and reverse transcription.RESULTS There were differences between groups when compared with clot or scaffold control,and improvement with a higher concentration of melatonin or rhBMP-2.The combination melatonin(1μg)with 5μg of rhBMP-2,using the guided bone regeneration technique,demonstrated some effects,albeit mild,on bone repair of critical bone defects.CONCLUSION This indicates that the approach for administering these substances needs to be reassessed,with the goal of ensuring their direct application to the affected area.Therefore,future research must be carried out,seeking to produce materials with these ideal characteristics.

Prediction of Lung Cancer Stage Using Tumor Gene Expression Data

Lung cancer remains a significant global health challenge and identifying lung cancer at an early stage is essential for enhancing patient outcomes. The study focuses on developing and optimizing gene expression-based models for classifying cancer types using machine learning techniques. By applying Log2 normalization to gene expression data and conducting Wilcoxon rank sum tests, the researchers employed various classifiers and Incremental Feature Selection (IFS) strategies. The study culminated in two optimized models using the XGBoost classifier, comprising 10 and 74 genes respectively. The 10-gene model, due to its simplicity, is proposed for easier clinical implementation, whereas the 74-gene model exhibited superior performance in terms of Specificity, AUC (Area Under the Curve), and Precision. These models were evaluated based on their sensitivity, AUC, and specificity, aiming to achieve high sensitivity and AUC while maintaining reasonable specificity.

Effect of Chuanzhifang component (ZGC) on macrophage inflammatory injury based on whole gene expression profile

Objective: The effect of Chuanzhi Fang (ZGC) on the whole genome expression profile of RAW264.7 cells activated by lipopolysaccharide (LPS) was analyzed, and to explore the possible mechanism of action and core target of this formula on macrophage inflammatory injury at the overall level. Methods: A model of LPS-induced inflammation in RAW264.7 cells was constructed, and the effect of ZGC intervention on the genome-wide expression of inflammatory macrophages 3was examined by gene microarray technology, GO/KEGG enrichment analysis was performed for significantly differentially expressed genes among each group. Results: The results of genome-wide expression profiling microarray analysis showed that the ZGC intervention group upregulated the expression of 5 genes including C4bp and inhibited the expression of 22 genes including Mgat3, Psma6, and Siglecg relative to the LPS model group. KEGG signaling pathway analysis results showed that ZGC mainly acted through cytokine receptor interaction and the C-type lectin receptor signaling pathway. Conclusion: ZGC can interfere with the abnormal expression of 27 genes in inflammatory macrophages, and the related genes may exert corresponding anti-inflammatory effects by affecting cytokine receptor interactions, C-type lectin receptor signaling pathway, and TLR4/ NF-κB signaling pathway.

In Vivo Improvements in Facial Appearance and in Vitro Changes in Gene Expression Using a Topical Formulation Designed to Repair Environmentally Induced DNA Damage

Background: While sunscreen has been accepted as a mainline defence against photodamage from ultraviolet, visible light and near-infrared radiation, there appears to be a lack of research into photorepair. The concept of protecting the skin during the day and repairing cellular damage at night is intuitive, yet specific strategies revolving around combinations of proven reparative active ingredients remain unelucidated. Purpose: To investigate the efficacy of a solar repair Formulation following ultraviolet and environmental exposure in order to improve overall skin health and appearance through three hypotheses: The Formulation increases expression of DNA repair mechanisms markers;The Formulation enhances overall skin appearance through reducing signs of inflammation, elevating hydration, reinforcing skin firmness and amplifying radiance;In-Vivo efficacy test results are aligned with measured gene expression changes. Methods: The Formulation (#6NIC1.V1.1-1) was tested for: In-vitro LDH cytotoxicity activity, In-vitro qPCR gene expression with and without ultraviolet exposure on a reconstructed 3-dimensional skin model, and In-Vivo efficacy study on a panel of 22 participants objectively and subjectively. Results: Skin radiance, firmness, hydration, redness, and inflammation are significantly improved after In-Vivo skin exposure to the Formulation and environmental challenges such as ultraviolet radiation. These outcomes were confirmed by in-vitro genetic testing on a reconstructed human skin model. Conclusion: The studies allowed us to identify and group results in four main skin functions that were significantly enhanced following the application of the Formulation: firmness, hydration, radiance and soothing.

Verification of gene expression profiles for colorectal cancer using 12 internet public microarray datasets

AIM: To verify gene expression profiles for colorectal cancer using 12 internet public microarray datasets.

Selection of Reference Genes in Transcription Analysis of Gene Expression of the Mandarin Fish, Siniperca chuasti

At present, transcription analysis of gene expression commonly uses housekeeping genes as control for normalization. In this study, the expression levels of three housekeeping genes including GAPDH, β-actin, and 18S rRNA in six tissues and five developmental stages of the Mandarin fish Siniperca chuatsi were assayed with quantitative real-time PCR （qPCR）. Differences in expression levels were analyzed using geNorm program. The results demonstrate that β-actin is the most stable gene at developmental stages and GAPDH is the most stable in different tissues. While 18S rRNA expression during development is differentially regulated, which indicates it is suitable as an internal control for gene expression normalization at the developmental level. Overall, the data suggest that the two most stable housekeeping genes are enough to accurately calibrate gene expression in S. chuatsi. The significance of this study provided convincing references and methodology for housekeeping gene selection and normalization in gene expression analysis with regular PCR or qPCR.

Differential Gene Expression Between Wheat Hybrids and Their Parental Inbreds in Primary Roots

To provide an insight into the molecular basis of heterosis, differential display of mRNA was used to analyze the difference of gene expression between wheat (Triticum aestivum L.) heterotic hybrid A, nonheterotic hybrid B and their parental inbreds in the primary roots. By using 5′ end random primers in combination with three one-base-anchored primers, it was found that 22.5% and 22.9% of 877 total displayed cDNAs were differentially expressed between hybrid A, B and their parents, respectively. Both quantitative and qualitative differences in gene expression between hybrids and their parental inbreds were obvious, indicating that the patterns of gene expression in hybrids alter significantly as compared to their corresponding parents. On the other hand, by using MADS-box gene specific 5′ end primer for DDRT-PCR, we found that nearly all of the displayed cDNA fragments were polymorphic between hybrids and their parents, and major difference occurred in qualitative level, in which hybrid specific-expressed and silenced genes are the major two patterns, suggesting that MADS-box gene may be important for manifestation of differential gene expression and wheat heterosis. In comparison with our previous results by using seedling leaves, it is indicated that differential gene expression between hybrids and parents is dependent on the tissues tested, and more differentially expressed genes were observed in the primary roots than in the seedling leaves. Therefore, it is concluded that the expressions of both randomly displayed cDNAs and transcription factor genes, such as MADS-box, alter significantly between hybrids and their parents, which might be responsible for the observed heterosis.

Classification with binary gene expressions

Microarray gene expression measurements are reported, used and archived usually to high numerical precision. However, properties of mRNA molecules, such as their low stability and availability in small copy numbers, and the fact that measurements correspond to a population of cells, rather than a single cell, makes high precision meaningless. Recent work shows that reducing measurement precision leads to very little loss of information, right down to binary levels. In this paper we show how properties of binary spaces can be useful in making inferences from microarray data. In particular, we use the Tanimoto similarity metric for binary vectors, which has been used effectively in the Chemoinformatics literature for retrieving chemical compounds with certain functional properties. This measure, when incorporated in a kernel framework, helps recover any information lost by quantization. By implementing a spectral clustering framework, we further show that a second reason for high performance from the Tanimoto metric can be traced back to a hitherto unnoticed systematic variability in array data: Probe level uncertainties are systematically lower for arrays with large numbers of expressed genes. While we offer no molecular level explanation for this systematic variability, that it could be exploited in a suitable similarity metric is a useful observation in itself. We further show preliminary results that working with binary data considerably reduces variability in the results across choice of algorithms in the preprocessing stages of microarray analysis.

Influence of Matrix Attachment Regions from Maize on Transgene Expression Level in Tobacco

The effect of matrix attachment regions (MARs) on foreign gene expression in transgenic plants was studied, The beta-glucuronidase (GUS) gene (uidA) was flanked by the MARs isolated from the genome of maize to form plant expression vector. The vectors with and without MARs were transferred into tobacco ( Nicotiana tabacum L.) through Agrobacterium-mediated transformation procedure. GUS activity assays indicated that MARs could increase expression level of uidA gene. The mean GUS activity could be increased twofold as compared to that of transformants without MARs, and the highest GUS activity of transformant could reach tenfold. The correspondence between GUS activity and mRNA accumulation was positive and indicated that MARs could improve transcription of foreign gene.

Gene expression profile in H4IIE rat hepatoma cells exposed to an antifouling booster biocide Irgarol-1051 degradation product

To better understand the toxicity of an antifouling booster biocide Irgarol-1051 degradation product M2 3-4-tert-butylamino-6-methylthiol-s-triazin-2-ylamino pro-pionaldehyde this study utilized a DNA microarray technique to explore the genotoxicity of M2. The Affymetrix Inc. rat genome 230 2.0 GeneChip was employed to examine alterations in gene regulation in rat hepatoma cells exposed to 30 μmol/L of M2 for 96 h.The results showed that 38 genes were significantly p＆lt;0.002 5 altered by M2 at two-fold changes in all the four possible control/exposure comparisons. Accn5 was the only well described gene consistently being suppressed which likely altered the epithelial sodium channel ENaC .10 and 82 annotated genes were up-and down-regulated in at least one of the control/exposure comparisons respectively. The induced genes were mainly involved in the nucleus belonging to the cellular component. The largest categories of suppression concerned G-protein coupled receptor protein signaling pathways belonging to the biological process and integral to membranes belonging to the cellular component.

Gene Expression and Regulation of Blastocyst Formation

Blastocyst formation is a crucial stage of early embryo development.Cell junction proteins and cell adhesion associated proteins are involved in the establishment of cell junction,and subsequently induce cell compaction,blastocyst formation,differentiation of trophectoderm and maintenance of blastocyst expansion.Genes regulating development and differentiation participate in embryo development and differentiation of inner cell mass and trophectoderm,which controls the transition from the undifferentiation to differentiation state.Furthermore,cytokine and growth factor have influence on the proliferation of cells of inner cell mass.In a word,many proteins and factors are involved in the gene expression and regulation of blastocyst formation.

Analysis of Gene Expression of Seven Isoforms of ADP-glucose Pyrophosphorylase in Rice Endosperm under Different Temperature Conditions

[Objective] This study aimed to analyze the effects of temperature on the expression of AGPase isoform genes in rice endosperm during milk stage. [Method] Different temperature treatments （33 and 25 ℃ of daily mean temperature for high and normal temperature treatments, respectively） and the real-time fluorescence quantitative PCR （ FQPCR） were used to analyze the expression patterns of seven isoforms （AGPS1, AGPS2a, AGPS2b, AGPL1, AGPL2, AGPL3 and AGPL4） of ADPglucose pyrophosphorylase （AGPase） which was the key enzyme in starch synthesis and metabolism in rice endosperm of two rice varieties Teqing and Thai Fragrant Rice. [Result] The AGPase isoforms AGPS2b, AGPL2 and AGPL3 had much higher expression than the other four isoforms, thus they were thought to be the main expression patterns of AGPase in rice endosperm. The relative expressions of AGPL2 was the highest among all the isoforms. The relative expressions of AGPS2b, AGPL2 and AGPL3 were higher in the normal temperature treatment than in the high temperature treatment in both rice varieties. The relative expression of the three enzyme genes in milk stages in Teqing was higher than those in Thai Fragrant Rice under different temperature treatments. [Conclusion] This study provides a theoretical basis for further use of molecular biology techniques to cultivate stable high-quality rice varieties.