Background:Mild cognitive impairment (MCI) is a common non-motor symptom of early Parkinson's disease (PD),but the neural mechanisms underlying it remain poorly understood.The aim of the present study was to inves...Background:Mild cognitive impairment (MCI) is a common non-motor symptom of early Parkinson's disease (PD),but the neural mechanisms underlying it remain poorly understood.The aim of the present study was to investigate the characteristics of cognition-related brain activities in the PD patients with MCI.Methods:The brain fMRIs and cognition tests were acquired in 39 PD patients and 22 healthy controls (HC) from September 2013 to January 2015.The patients were divided into two groups:PD-MCI (n--18) and PD with normal cognition (PDNC,n =19).we used resting state fMRI and a regional homogeneity (ReHo) method to explore patterns of intrinsic brain activity in patients with PD-MCI as compared with PDNC subjects and HC.Results:Compared with the PDNC group,the PD-MCI group exhibited significantly increased ReHo in parts of the prefrontal cortex regions (e.g.right superior frontal gyrus,right middle frontal gyrus and orbitofrontal cortex).Compared to the HC group,a decrease of ReHo value in left thalamus was found in PD-MCI.However,this reduction was not found in the left thalamus of PDNC group,but in the above prefrontal regions (p ＜ 0.05,with Bonferroni correction).Conclusions:These results demonstrate that the ReHo of prefrontal cortex in resting state is changed in PD patients with MCI.The presence of MCI in PD may be attributed to abnormal regional activity in prefrontal cortex regions.展开更多
DNA methylation analysis has been applied to determine the primary site of cancer;however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To ...DNA methylation analysis has been applied to determine the primary site of cancer;however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To build an accurate and robust cancer type prediction tool with a minimum number of DNA methylation sites, we internally benchmarked different DNA methylation site selection and ranking procedures, as well as different classification models. We used The Cancer Genome Atlas dataset (26 cancer types with 8296 samples) to train and test models and used an independent dataset (17 cancer types with 2738 samples) for model validation. A deep neural network model using a combined feature selection procedure (named MethyDeep) can predict 26 cancer types using 30 methylation sites with superior performance compared with the known methods for both primary and metastatic cancers in independent validation datasets. In conclusion, MethyDeep is an accurate and robust cancer type predictor with the minimum number of DNA methylation sites;it could help the cost-effective clarification of cancer of unknown primary patients and the liquid biopsy-based early screening of cancers.展开更多
基金The study was generously supported by the Fujian Province Natural Science Foundation，also sponsored by key clinical specialty discipline construction program of Fujian,PRC
文摘Background:Mild cognitive impairment (MCI) is a common non-motor symptom of early Parkinson's disease (PD),but the neural mechanisms underlying it remain poorly understood.The aim of the present study was to investigate the characteristics of cognition-related brain activities in the PD patients with MCI.Methods:The brain fMRIs and cognition tests were acquired in 39 PD patients and 22 healthy controls (HC) from September 2013 to January 2015.The patients were divided into two groups:PD-MCI (n--18) and PD with normal cognition (PDNC,n =19).we used resting state fMRI and a regional homogeneity (ReHo) method to explore patterns of intrinsic brain activity in patients with PD-MCI as compared with PDNC subjects and HC.Results:Compared with the PDNC group,the PD-MCI group exhibited significantly increased ReHo in parts of the prefrontal cortex regions (e.g.right superior frontal gyrus,right middle frontal gyrus and orbitofrontal cortex).Compared to the HC group,a decrease of ReHo value in left thalamus was found in PD-MCI.However,this reduction was not found in the left thalamus of PDNC group,but in the above prefrontal regions (p ＜ 0.05,with Bonferroni correction).Conclusions:These results demonstrate that the ReHo of prefrontal cortex in resting state is changed in PD patients with MCI.The presence of MCI in PD may be attributed to abnormal regional activity in prefrontal cortex regions.
基金supported by Shanghai Science and Technology Commission(21ZR1442400)the National Natural Science Foundation of China(31771373)startup funding from ShanghaiTech University.
文摘DNA methylation analysis has been applied to determine the primary site of cancer;however, robust and accurate prediction of cancer types with a minimum number of sites is still a significant scientific challenge. To build an accurate and robust cancer type prediction tool with a minimum number of DNA methylation sites, we internally benchmarked different DNA methylation site selection and ranking procedures, as well as different classification models. We used The Cancer Genome Atlas dataset (26 cancer types with 8296 samples) to train and test models and used an independent dataset (17 cancer types with 2738 samples) for model validation. A deep neural network model using a combined feature selection procedure (named MethyDeep) can predict 26 cancer types using 30 methylation sites with superior performance compared with the known methods for both primary and metastatic cancers in independent validation datasets. In conclusion, MethyDeep is an accurate and robust cancer type predictor with the minimum number of DNA methylation sites;it could help the cost-effective clarification of cancer of unknown primary patients and the liquid biopsy-based early screening of cancers.
