|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Materials discovery and design using machine learning显示文摘The screening of novel materials with good performance and the modelling of quantitative structureactivity relationships(QSARs),among other issues,are hot topics in the field of materials science.Traditional experiments and computational modelling often consume tremendous time and resources and are limited by their experimental conditions and theoretical foundations.Thus,it is imperative to develop a new method of accelerating the discovery and design process for novel materials.Recently,materials discovery and design using machine learning have been receiving increasing attention and have achieved great improvements in both time efficiency and prediction accuracy.In this review,we first outline the typical mode of and basic procedures for applying machine learning in materials science,and we classify and compare the main algorithms.Then,the current research status is reviewed with regard to applications of machine learning in material property prediction,in new materials discovery and for other purposes.Finally,we discuss problems related to machine learning in materials science,propose possible solutions,and forecast potential directions of future research.By directly combining computational studies with experiments,we hope to provide insight into the parameters that affect the properties of materials,thereby enabling more efficient and target-oriented research on materials discovery and design. | Yue Liu Tianlu Zhao Wangwei Ju Siqi Shi | 2017 | Journal of Materiomics2017，3，3： | 61 |
| 2 | Predicting the onset temperature(Tg) of GexSe1-x glass transition: a feature selection based two-stage support vector regression method显示文摘Despite the usage of both experimental and topological methods, realizing a rapid and accurate measurement of the onset temperature(Tg ) of GexSe1-xglass transition remains an open challenge. In this paper, a predictive model for the Tg in GexSe1-xglass system is presented by a machine learning method named feature selection based two-stage support vector regression(FSTS-SVR). Firstly, Pearson correlation coefficient(PCC) is used to select features highly correlated with Tg from the candidate features of GexSe1-x glass system. Secondly, in order to simulate the two-stage characteristic of Tg which is caused by structural variation with a turning point at x = 0.33 via the structural analysis, SVR is utilized to build predictive models for two stages separately and then the two achieved models are synthesized using a minimum error based model for Tg prediction. Compared with the topological and other methods based on SVR, the FSTS-SVR gives the highest predictive accuracy with the root mean square error(RMSE) and mean absolute percentage error(MAPE) of 10.64 K and 2.38%, respectively. This method is also expected to be more efficient for the prediction of Tg of other glass systems with the multi-stage characteristic. | Yue Liu Junming Wu Guang Yang Tianlu Zhao Siqi Shi | 2019 | Science Bulletin2019，64，16： | 12 |
| 3 | Genome Mining and Biosynthesis Study of a Type B Linaridin Reveals a Highly Versatileα-N-Methyltransferase显示文摘Linaridins are a small but growing family of natural products belonging to the ribosomally synthesized and post-translationally modified peptide(RiPP)superfamily.In this study,a genome mining approach led to the identification of a novel linaridin,mononaridin(MON),from Streptomyces monomycini.In-frame deletion genetic knockout studies showed that,in addition to many genes essential for MON biosynthesis,monM encodes an S-adenosyl methionine(SAM)-dependentα-N-methyltransferase that is responsible for installing two methyl groups in the MON N-terminus.Besides SAM,MonM also accepts ethyl-SAM and allyl-SAM,in which the methyl of SAM is replaced by an ethyl and an allyl,respectively.We showed that ethyl-SAM and allyl-SAM have distinct reactivities in MonM catalysis,and this observation was further investigated in detail by density functional theory(DFT)calculations.Remarkably,MonM acts efficiently on nisin,a prototypic lantibiotic that is structurally very different from the native substrate,and the ability of MonM to transfer an allyl group to the nisin N-terminus allowed production of a fluorescently labeled nisin,which can be further used in microscopic cell analysis.Our studies provide new insights into linaridin biosynthesis and demonstrate the potential of linaridin methyltransferases in bioengineering applications. | Fangting Wang Wanqing Wei Junfeng Zhao Tianlu Mo Xin Wang Xuedong Huang Suze Ma Shu Wang Zixin Deng Wei Ding Yong Liang Qi Zhang | 2021 | CCS Chemistry2021，3，3： | 1 |
| 4 | STUDY OF SEMISUBMERSIBLE ANTI-TYPHOON OFFSHORE PRODUCTION,STORAGE AND MOORING PLATFORM显示文摘Most of reservoirs explorated offshore China are of medium and small size considered as marginal fields. Economic analysis of fields development shows that the conventional floating production system is still too expensive to be taken for the small sized reservoirs. It is necessary to develop a new concept of early production system. SOECO has developed a new production platform which is called formally Semisubmersible Anti-Typhoon Production Storage and Mooring - SAPSM. Both the theoretic study and model test have proved that the new platform is a suitable early production system for developing oil reserves offshore China and has the ability to survive in typhoon. | Lian, Gan Zhao, Weimin Tuo, Tianlu Zeng, Jinzhao Li, Lin | 1990 | China Ocean Engineering1990，5，2： | 0 |
| 5 | Ultrathin two-dimensional medium-entropy oxide as a highly efficient and stable electrocatalyst for oxygen evolution reaction显示文摘Medium-entropy oxides(MEOs)with broad compositional tunability and entropy-driven structural stability,are receiving booming attention as a promising candidate for oxygen evolution reaction(OER)electrocatalysts.Meanwhile,ultrathin two-dimensional(2D)nanostructure offers extremely large specific surface area and is therefore considered to be an ideal catalyst structure.However,it remains a grant challenge to synthesize ultrathin 2D MEOs due to distinct nucleation and growth kinetics of constituent multimetallic elements in 2D anisotropic systems.In this work,an ultrathin 2D MEO(MnFeCoNi)O was successfully synthesized by a facile and low-temperature ionic layer epitaxy method.Benefiting from multi-metal synergistic effects within ultrathin 2D nanostructure,this 2D MEO(MnFeCoNi)O revealed excellent OER electrocatalytic performance with a quite low overpotential of 117 mV at 10 mA·cm^(-2) and an impressive stability for 120 h continuous operation with only 6.9%decay.Especially,the extremely high mass activity(5584.3 A·g^(-1))was three orders of magnitude higher than benchmark RuO_(2)(3.4 A·g^(-1))at the same overpotential of 117 mV.This work opens up a new avenue for developing highly efficient and stable electrocatalysts by creating 2D nanostructured MEOs. | Guangyuan Yan Tianlu Wang Biwei Zhao Wenjing Gao Tong Wu Liming Ou | 2024 | Nano Research2024，17，4： | 0 |
| 6 | A STIR nucleic acid drug delivery system for stirring phenotypic switch of microglia in Parkinson’s disease treatments显示文摘Neuroinflammation is one of the three important pathological features in neurodegenerative diseases including Parkinson’s disease(PD).The regulation of neuroinflammation can reduce the severity of neurological damage to alleviate diseases.Numerous studies have shown that the phenotype switch of microglia is tightly associated with the nuclear factorκB(NF-κB)-mediated inflammatory pathway.Therefore,the small interfering RNA(siRNA)therapy for downregulating the expression of NF-κB,provides a promising therapeutic strategy for Parkinson’s disease treatments.Considering the brain delivery challenges of siRNA,a sequential targeting inflammation regulation(STIR)delivery system based on poly(amino acid)s is developed to improve the therapeutic effects of Parkinson’s disease treatments.The STIR system sequentially targets the blood–brain barrier and the microglia to enhance the effective concentration of siRNA in the targeted microglia.The results demonstrate that the STIR nanoparticles can transform microglial phenotypes and regulate brain inflammation,thus achieving neuronal recovery and abnormal aggregation ofα-synuclein protein(α-syn)reduction in the treatment of Parkinson’s disease.Herein,this STIR delivery system provides a promising therapeutic platform in PD treatments and has great potential for other neurodegenerative diseases’therapies. | Yanyue Wu Wenli Wang Xinyu Qiu Zhiguo Lu Weihong Ji Jie Shen Huan Peng Ruichen Zhao Jingwen Wang Tianlu Zhang Jun Yang Xin Zhang | 2023 | Nano Research2023，16，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员