ABSTRACT
Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer's disease. The Alzheimer's disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer's disease based on high dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.
Subject(s)
Alzheimer Disease/complications , Cognition Disorders/diagnosis , Cognition Disorders/etiology , Alzheimer Disease/genetics , Apolipoproteins E/genetics , Biomarkers , Cognition Disorders/genetics , Computational Biology , Databases, Bibliographic/statistics & numerical data , Humans , Predictive Value of TestsABSTRACT
ZnO/Graphene (G)/Graphene Oxide (GO)/Multi-walled Carbon Nanotube (MCNT) composite aerogels with a three-dimensional porous structure were prepared by the sol-gel method under average temperature and alkaline conditions, combined with freeze-drying process and heat treatment process. The photocatalytic degradation of Rhodamine B (RhB) was mainly studied. The scanning electron microscope (SEM) test results showed that the morphology uniformity of the ZnO/G/GO/MCNT composite aerogel was significantly enhanced, which effectively solving the agglomeration problem of MCNT and ZnO. The photocatalytic degradation test results of RhB show that due to the synergistic effect of physical adsorption and photocatalytic degradation, the total degradation efficiency of RhB by ZnO/G/GO/MCNT could reach 86.8%, which is 3.3 times higher than that of ZnO. In addition, the synergistic effect of ZnO and G effectively hinders the recombination of photo-generated electron-hole pairs and enhances photocatalytic activity. The ZnO/G/GO/MCNT composite aerogel can be applied in the visible light catalytic degradation of water pollution.
ABSTRACT
Identifying drug-target interactions is crucial for the success of drug discovery. Approaches based on machine learning for this problem can be divided into two types: feature-based and similarity-based methods. By utilizing the "Learning to rank" framework, we propose a new method, DrugE-Rank, to combine these two different types of methods for improving the prediction performance of new candidate drugs and targets. DrugE-Rank is available at http://datamining-iip.fudan.edu.cn/service/DrugE-Rank/ .