| 1 | Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride显示文摘It is well-known that the atomic-scale and nano-scale configuration of dopants can play a crucial role in determining the electronic properties of materials.However,predicting such effects is challenging due to the large range of atomic configurations that are possible.Here,we present a case study of how deep learning algorithms can enable bandgap prediction in hybridized boron–nitrogen graphene with arbitrary supercell configurations.A material descriptor that enables correlation of structure and bandgap was developed for convolutional neural networks.Bandgaps calculated by ab initio calculations,and corresponding structures,were used as training datasets.The trained networks were then used to predict bandgaps of systems with various configurations.For 4×4 and 5×5 supercells they accurately predict bandgaps,with a R^(2) of >90% and root-mean-square error of~0.1 eV.The transfer learning was performed by leveraging data generated from small supercells to improve the prediction accuracy for 6×6 supercells.This work will pave a route to future investigation of configurationally hybridized graphene and other 2D materials.Moreover,given the ubiquitous existence of configurations in materials,this work may stimulate interest in applying deep learning algorithms for the configurational design of materials across different length scales. | Yuan Dong Chuhan Wu Chi Zhang Yingda Liu Jianlin Cheng Jian Lin | 2019 | npj Computational Materials2019，，1： | 5 |
| 4 | Effects of Yishenjiangzhuo granules on immunity and bone metabolism in patients with stage 3-4 chronic kidney disease显示文摘OBJECTIVE:To determine the effects of Yishenjiangzhuo granules(YJG)on bone metabolism and to explore the changes in levels of bone Gla protein(BGP),tartrate-resistant acid phosphatase(TRAP),as well as their relationships with levels of B cells,regulatory T cells(Treg)and interleukin(IL)-17 in patients with stage 3-4 chronic kidney disease(CKD)before and after treatment.METHODS:Fifty-three stage 3-4 CKD patients were divided randomly into two groups:YJG treatment and control.Peripheral blood was taken from two groups of CKD patients and 21 healthy subjects in the normal group.The parameters determined were the levels of CD4+,CD19+,CD19+CD69+,CD19+AV,Treg(CD4+CD25+CD127lo),BGP,TRAP,IL-17,calcium,phosphate,blood urea nitrogen,serum creatinine(SCr),hemoglobin(Hb)in peripheral blood,and urinary creatinine.Calcium-phosphate products and endogenous creatinine clearance rate(CCr)were calculated according to standard protocols.RESULTS:In YJG and control groups,SCr levels were lowered(P<0.01)after treatment,whereas CCr(P<0.05)as well as Hb and albumin levels(P<0.01)were increased.The changes in levels of CCr and SCr in the YJG group were more significant.After treatment,CD19+CD69+and Treg levels in the two groups varied(P<0.01)compared with those of the normal group;the level of CD19+increased but the levels of CD4+and CD19+AV decreased(P<0.01)in both groups.Compared with the control group,the changes of CD19+and CD19+AV in the YJG group were more apparent(P<0.05).Compared with the normal group,levels of IL-17 in both groups increased significantly(P<0.01),and the difference in the control group was more significant(P<0.05).After treatment,the TRAP level increased(P<0.05),but the difference in BGP level(P>0.05)was not significant.CONCLUSION:In stage 3-4 CKD patients,B cells and IL-17 participated in the induction of osteoclast activation.YJG could also elevate the level of B cells and decrease their apoptosis,but showed no significant effects on active B cells,IL-17 or osteoclast activity. | Jing Zheng Yingda Lin Lu Huang Caifeng Chen Xuemin Zheng Xinhong Wu Ciyun Liu | 2013 | Journal of Traditional Chinese Medicine2013，33，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员