Recommender systems have been well studied and applied both in the academia and industry recently. However, traditional recommender systems assume that all the users and items are independent and identically distributed. This assumption ignores the correlation of explicit attributes of both users and items. Aiming at modeling recommender systems more realistically and interpretably, we propose a novel and efficient hybrid matrix factorization method which combines implicit and explicit attributes, and can be used to solve the problem of cold start and recommender interpretation. Based on the MovieLens datasets, the experimental analysis shows our method is promising and efficient.
Erythropoietin (EPO), known for its role in erythroid differentiation, has been suggested to have a direct protective role against a variety of neurotoxic insults. In the present study, we investigated the expression of EPO receptor (EPOR) and the number of EPORpositive cells in three encephalic regions (ventral mesencephalon, striatum, cortex) following lesion induced by 1-methyl-4-phenyl- 1,2,3,6-tetrahydropyridine (MPTP). C57BL/6 mice underwent intraperitoneal injection of MPTP at 24 h intervals for 5 days, and their brains were examined 1, 2, 4, 7, 14 or 21 days after the last injection. Western blot and immunohistochemistry analysis revealed that EPOR was dramatically up-regulated in the ventral mesencephalon, 4 days after MPTP insult until the day 21. In contrast, there was a baseline level of EPOR in the striatum and cortex. At subsequent time points after MPTP injury, the levels of EPOR in the two regions were not statistically different compared with those in normal animals. These results suggest that the regional specific up-regulation of EPOR at an early stage after MPTP stimulus may represent a pro-survival mechanism against neurotoxin injury in Parkinsonian model., Y. Wu ... [et al.]., and Obsahuje bibliografii a bibliografické odkazy