Machine Learning(ML)-based prediction and classification systems employ data and learning algorithms to forecast target values.However,improving predictive accuracy is a crucial step for informed decision-making.In th...Machine Learning(ML)-based prediction and classification systems employ data and learning algorithms to forecast target values.However,improving predictive accuracy is a crucial step for informed decision-making.In the healthcare domain,data are available in the form of genetic profiles and clinical characteristics to build prediction models for complex tasks like cancer detection or diagnosis.Among ML algorithms,Artificial Neural Networks(ANNs)are considered the most suitable framework for many classification tasks.The network weights and the activation functions are the two crucial elements in the learning process of an ANN.These weights affect the prediction ability and the convergence efficiency of the network.In traditional settings,ANNs assign random weights to the inputs.This research aims to develop a learning system for reliable cancer prediction by initializing more realistic weights computed using a supervised setting instead of random weights.The proposed learning system uses hybrid and traditional machine learning techniques such as Support Vector Machine(SVM),Linear Discriminant Analysis(LDA),Random Forest(RF),k-Nearest Neighbour(kNN),and ANN to achieve better accuracy in colon and breast cancer classification.This system computes the confusion matrix-based metrics for traditional and proposed frameworks.The proposed framework attains the highest accuracy of 89.24 percent using the colon cancer dataset and 72.20 percent using the breast cancer dataset,which outperforms the other models.The results show that the proposed learning system has higher predictive accuracies than conventional classifiers for each dataset,overcoming previous research limitations.Moreover,the proposed framework is of use to predict and classify cancer patients accurately.Consequently,this will facilitate the effective management of cancer patients.展开更多
OBJECTIVE To study the difference of gene expression in gastric cancer (T) and normal tissue of gastric mucosa (C), and to screen for associated novel genes in gastric cancers by oligonucleotide microarrays. METHODS U...OBJECTIVE To study the difference of gene expression in gastric cancer (T) and normal tissue of gastric mucosa (C), and to screen for associated novel genes in gastric cancers by oligonucleotide microarrays. METHODS U133A (Affymetrix, Santa Clara, CA) gene chip was used to detect the gene expression profile difference in T and C. Bioinformatics was used to analyze the detected results. RESULTS When gastric cancers were compared with normal gastric mucosa, a total of 270 genes were found with a difference of more than 9 times in expression levels. Of the 270 genes, 157 were up-regulated (Signal Log Ratio [SLR] ≥3), and 113 were down-regulated (SLR ≤-3). Using a classification of function, the highest number of gene expression differences related to enzymes and their regulatory genes (67, 24.8%), followed by signal-transduction genes (43,15.9%). The third were nucleic acid binding genes (17, 6.3%), fourth were transporter genes (15, 5.5%) and fifth were protein binding genes (12, 4.4%). In addition there were 50 genes of unknown function, accounting for 18.5%. The five above mentioned groups made up 56.9% of the total gene number. CONCLUSION The 5 gene groups (enzymes and their regulatory proteins, signal transduction proteins, nucleic acid binding proteins, transporter and protein binding) were abnormally expressed and are important genes for further study in gastric cancers.展开更多
窖蛋白(Caveolin)是一类构成细胞膜上胞膜窖主要结构的标志蛋白,由Caveolin基因家族编码而成。Caveolin-1基因是Caveolin基因家族的成员之一。该实验采用RT-PCR与RACE(rapid amplification of cDNA ends)技术成功地克隆了家鸽Caveolin-...窖蛋白(Caveolin)是一类构成细胞膜上胞膜窖主要结构的标志蛋白,由Caveolin基因家族编码而成。Caveolin-1基因是Caveolin基因家族的成员之一。该实验采用RT-PCR与RACE(rapid amplification of cDNA ends)技术成功地克隆了家鸽Caveolin-1基因的全长cDNA。该cDNA全长2605bp,包含537bp的完整编码区,编码178个氨基酸;分析发现家鸽Caveolin-1基因编码区与牛、家犬、鸡、褐家鼠等核苷酸同源性为80.1%～93.4%,氨基酸同源性高达85.4%～97.2%;半定量RT-PCR分析表明该基因在家鸽各种组织广泛表达,脂肪中表达量最高,各种肌肉中表达量次之,肝脏中表达量最低。此结果说明家鸽Caveolin-1基因可能与脂肪、肌肉中的某些代谢途径有关。展开更多
Based on a deterministic cell cycle model of fission yeast, the effects of the finite cell size on the cell cycle regulation in wee1- cdc25△ double mutant type are numerically studied by using of the chemical Langevi...Based on a deterministic cell cycle model of fission yeast, the effects of the finite cell size on the cell cycle regulation in wee1- cdc25△ double mutant type are numerically studied by using of the chemical Langevin equations. It is found that at a certain region of cell size, our numerical results from the chemical Langevin equations are in good qualitative agreement with the experimental observations. The two resettings to the G2 phase from early stages of mitosis can be induced under the moderate cell size. The quantized cycle times can be observed during such a cell size region. Therefore, a coarse estimation of cell size is obtained from the mesoscopic stochastic cell cycle model.展开更多
文摘Machine Learning(ML)-based prediction and classification systems employ data and learning algorithms to forecast target values.However,improving predictive accuracy is a crucial step for informed decision-making.In the healthcare domain,data are available in the form of genetic profiles and clinical characteristics to build prediction models for complex tasks like cancer detection or diagnosis.Among ML algorithms,Artificial Neural Networks(ANNs)are considered the most suitable framework for many classification tasks.The network weights and the activation functions are the two crucial elements in the learning process of an ANN.These weights affect the prediction ability and the convergence efficiency of the network.In traditional settings,ANNs assign random weights to the inputs.This research aims to develop a learning system for reliable cancer prediction by initializing more realistic weights computed using a supervised setting instead of random weights.The proposed learning system uses hybrid and traditional machine learning techniques such as Support Vector Machine(SVM),Linear Discriminant Analysis(LDA),Random Forest(RF),k-Nearest Neighbour(kNN),and ANN to achieve better accuracy in colon and breast cancer classification.This system computes the confusion matrix-based metrics for traditional and proposed frameworks.The proposed framework attains the highest accuracy of 89.24 percent using the colon cancer dataset and 72.20 percent using the breast cancer dataset,which outperforms the other models.The results show that the proposed learning system has higher predictive accuracies than conventional classifiers for each dataset,overcoming previous research limitations.Moreover,the proposed framework is of use to predict and classify cancer patients accurately.Consequently,this will facilitate the effective management of cancer patients.
文摘OBJECTIVE To study the difference of gene expression in gastric cancer (T) and normal tissue of gastric mucosa (C), and to screen for associated novel genes in gastric cancers by oligonucleotide microarrays. METHODS U133A (Affymetrix, Santa Clara, CA) gene chip was used to detect the gene expression profile difference in T and C. Bioinformatics was used to analyze the detected results. RESULTS When gastric cancers were compared with normal gastric mucosa, a total of 270 genes were found with a difference of more than 9 times in expression levels. Of the 270 genes, 157 were up-regulated (Signal Log Ratio [SLR] ≥3), and 113 were down-regulated (SLR ≤-3). Using a classification of function, the highest number of gene expression differences related to enzymes and their regulatory genes (67, 24.8%), followed by signal-transduction genes (43,15.9%). The third were nucleic acid binding genes (17, 6.3%), fourth were transporter genes (15, 5.5%) and fifth were protein binding genes (12, 4.4%). In addition there were 50 genes of unknown function, accounting for 18.5%. The five above mentioned groups made up 56.9% of the total gene number. CONCLUSION The 5 gene groups (enzymes and their regulatory proteins, signal transduction proteins, nucleic acid binding proteins, transporter and protein binding) were abnormally expressed and are important genes for further study in gastric cancers.
文摘窖蛋白(Caveolin)是一类构成细胞膜上胞膜窖主要结构的标志蛋白,由Caveolin基因家族编码而成。Caveolin-1基因是Caveolin基因家族的成员之一。该实验采用RT-PCR与RACE(rapid amplification of cDNA ends)技术成功地克隆了家鸽Caveolin-1基因的全长cDNA。该cDNA全长2605bp,包含537bp的完整编码区,编码178个氨基酸;分析发现家鸽Caveolin-1基因编码区与牛、家犬、鸡、褐家鼠等核苷酸同源性为80.1%～93.4%,氨基酸同源性高达85.4%～97.2%;半定量RT-PCR分析表明该基因在家鸽各种组织广泛表达,脂肪中表达量最高,各种肌肉中表达量次之,肝脏中表达量最低。此结果说明家鸽Caveolin-1基因可能与脂肪、肌肉中的某些代谢途径有关。
基金Supported by the National Natural Science Foundation of China under Grant No 10575041.
文摘Based on a deterministic cell cycle model of fission yeast, the effects of the finite cell size on the cell cycle regulation in wee1- cdc25△ double mutant type are numerically studied by using of the chemical Langevin equations. It is found that at a certain region of cell size, our numerical results from the chemical Langevin equations are in good qualitative agreement with the experimental observations. The two resettings to the G2 phase from early stages of mitosis can be induced under the moderate cell size. The quantized cycle times can be observed during such a cell size region. Therefore, a coarse estimation of cell size is obtained from the mesoscopic stochastic cell cycle model.
