Background and Aims:The relationship between quanti-tative magnetic resonance imaging(MRI)imaging features and gene-expression signatures associated with the recur-rence of hepatocellular carcinoma(HCC)is not well stu...Background and Aims:The relationship between quanti-tative magnetic resonance imaging(MRI)imaging features and gene-expression signatures associated with the recur-rence of hepatocellular carcinoma(HCC)is not well studied.Methods:In this study,we generated multivariable regres-sion models to explore the correlation between the preoper-ative MRI features and Golgi membrane protein 1(GOLM1),SET domain containing 7(SETD7),and Rho family GTPase 1(RND1)gene expression levels in a cohort study including 92 early-stage HCC patients.A total of 307 imaging features of tumor texture and shape were computed from T2-weighted MRI.The key MRI features were identified by performing a multi-step feature selection procedure including the cor-relation analysis and the application of RELIEFF algorithm.Afterward,regression models were generated using kernel-based support vector machines with 5-fold cross-validation.Results:The features computed from higher specificity MRI better described GOLM1 and RND1 gene-expression levels,while imaging features computed from lower specificity MRI data were more descriptive for the SETD7 gene.The GOLM1 regression model generated with three features demon-strated a moderate positive correlation(p<0.001),and the RND1 model developed with five variables was positively as-sociated(p<0.001)with gene expression levels.Moreover,RND1 regression model integrating four features was mod-erately correlated with expressed RND1 levels(p<0.001).Conclusions:The results demonstrated that MRI radiomics features could help quantify GOLM1,SETD7,and RND1 ex-pression levels noninvasively and predict the recurrence risk for early-stage HCC patients.展开更多
We present a computational study of tissue transcriptomic data of 14 cancer types to address： what may drive cancer cell division？ Our analyses point to that persistent disruption of the intraceUular pH by Fenton re...We present a computational study of tissue transcriptomic data of 14 cancer types to address： what may drive cancer cell division？ Our analyses point to that persistent disruption of the intraceUular pH by Fenton reactions may be at the root of cancer development. Specifically, we have statistically demonstrated that Fenton reactions take place in cancer cytosoi and mitochondria across all the 14 cancer types, based on cancer tissue gene-expression data integrated via the Michaelis-Menten equation. In addition, we have shown that （i） Fenton reactions in cytosol of the disease cells will continuously increase their pH, to which the cells respond by generating net protons to keep the pH stable through a combination of synthesizing glycolytic ATPs and consuming them by nucleotide syntheses, which may drive cell division to rid of the continuously synthesized nucleotides; and （ii） Fenton reactions in mitochondria give rise to novel ways for ATP synthesis with electrons ultimately coming from H2O2, largely originated from immune cells. A model is developed to link these to cancer development, where some mutations may be selected to facilitate cell division at rates dictated by Fenton reactions.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
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
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
基金This study was supported by the National Key Research and Development Program of China(No.2016YFC0107101 and No.2016YFC0107109).
文摘Background and Aims:The relationship between quanti-tative magnetic resonance imaging(MRI)imaging features and gene-expression signatures associated with the recur-rence of hepatocellular carcinoma(HCC)is not well studied.Methods:In this study,we generated multivariable regres-sion models to explore the correlation between the preoper-ative MRI features and Golgi membrane protein 1(GOLM1),SET domain containing 7(SETD7),and Rho family GTPase 1(RND1)gene expression levels in a cohort study including 92 early-stage HCC patients.A total of 307 imaging features of tumor texture and shape were computed from T2-weighted MRI.The key MRI features were identified by performing a multi-step feature selection procedure including the cor-relation analysis and the application of RELIEFF algorithm.Afterward,regression models were generated using kernel-based support vector machines with 5-fold cross-validation.Results:The features computed from higher specificity MRI better described GOLM1 and RND1 gene-expression levels,while imaging features computed from lower specificity MRI data were more descriptive for the SETD7 gene.The GOLM1 regression model generated with three features demon-strated a moderate positive correlation(p<0.001),and the RND1 model developed with five variables was positively as-sociated(p<0.001)with gene expression levels.Moreover,RND1 regression model integrating four features was mod-erately correlated with expressed RND1 levels(p<0.001).Conclusions:The results demonstrated that MRI radiomics features could help quantify GOLM1,SETD7,and RND1 ex-pression levels noninvasively and predict the recurrence risk for early-stage HCC patients.
基金This work was supported by grants from Georgia Research Alliance, the National Natural Science Foundation of China （61572227）, Projects of international Cooperation and Exchanges of the National Natural Science Foundation of China （81320108025）, and Jilin University.
文摘We present a computational study of tissue transcriptomic data of 14 cancer types to address： what may drive cancer cell division？ Our analyses point to that persistent disruption of the intraceUular pH by Fenton reactions may be at the root of cancer development. Specifically, we have statistically demonstrated that Fenton reactions take place in cancer cytosoi and mitochondria across all the 14 cancer types, based on cancer tissue gene-expression data integrated via the Michaelis-Menten equation. In addition, we have shown that （i） Fenton reactions in cytosol of the disease cells will continuously increase their pH, to which the cells respond by generating net protons to keep the pH stable through a combination of synthesizing glycolytic ATPs and consuming them by nucleotide syntheses, which may drive cell division to rid of the continuously synthesized nucleotides; and （ii） Fenton reactions in mitochondria give rise to novel ways for ATP synthesis with electrons ultimately coming from H2O2, largely originated from immune cells. A model is developed to link these to cancer development, where some mutations may be selected to facilitate cell division at rates dictated by Fenton reactions.
基金supported by grant from the scientif ic fund of the Ministry of Personnel for returned overseas expert (2006)Natural Science Foundation Project of CQ CSTC (to Mingjian GE)(CSTC, No.2008BB5210)
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.
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.
