http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Robust estimation and variable selection in censored partially linear additive models
Huilan Liu,Hu Yang,Xiaochao Xia 한국통계학회 2017 Journal of the Korean Statistical Society Vol.46 No.1
In this paper, we consider a new estimation in censored partially linear additive models in which the nonparametric components are approximated by polynomial spline. For identifying the significant variables in the linear part, a regularization procedure based on adaptive lasso is proposed for estimation and variable selection simultaneously. Under some regular conditions, the asymptotic normality and oracle property of the parametric components are established, and the convergence rates of the nonparametric components are obtained. Simulation studies and a real data analysis are presented to illustrate the behavior of the proposed estimators.
Xiaokang Yu,Jinsheng Liang,Jiarui Xu,Xingsong Li,Shan Xing,Huilan Liu,Wan-Li Liu,Dongdong Liu,Jianhua Xu,Lizhen Huang,Hongli Du 한국유방암학회 2018 Journal of breast cancer Vol.21 No.4
Purpose: Breast cancer is the most commonly occurring cancer among women worldwide, and therefore, improved approaches for its early detection are urgently needed. As microRNAs (miRNAs) are increasingly recognized as critical regulators in tumorigenesis and possess excellent stability in plasma, this study focused on using miRNAs to develop a method for identifying noninvasive biomarkers. Methods: To discover critical candidates, differential expression analysis was performed on tissue-originated miRNA profiles of 409 early breast cancer patients and 87 healthy controls from The Cancer Genome Atlas database. We selected candidates from the differentially expressed miRNAs and then evaluated every possible molecular signature formed by the candidates. The best signature was validated in independent serum samples from 113 early breast cancer patients and 47 healthy controls using reverse transcription quantitative real-time polymerase chain reaction. Results: The miRNA candidates in our method were revealed to be associated with breast cancer according to previous studies and showed potential as useful biomarkers. When validated in independent serum samples, the area under curve of the final miRNA signature (miR-21-3p, miR-21-5p, and miR-99a-5p) was 0.895. Diagnostic sensitivity and specificity were 97.9% and 73.5%, respectively. Conclusion: The present study established a novel and effective method to identify biomarkers for early breast cancer. And the method, is also suitable for other cancer types. Furthermore, a combination of three miRNAs was identified as a prospective biomarker for breast cancer early detection.
Tan, Yongwen,Zang, Xining,Gu, Jiajun,Liu, Dingxin,Zhu, Shenmin,Su, Huilan,Feng, Chuanliang,Liu, Qinglei,Lau, Woon Ming,Moon, Won-Jin,Zhang, Di American Chemical Society 2011 Langmuir Vol.27 No.19
<P>Through a simple room-temperature photoreduction process, this letter conformally replicates 3D submicrometer structures of wing scales from two butterfly species into Ag to generate practical surface-enhanced Raman scattering (SERS) substrates. The Ag replicas of butterfly scales with higher structural periodicity are able to detect rhodamine 6G at a low concentration down to 10(-9) M, which is three orders of magnitude lower than the detectable concentration limit of using quasi-periodic Ag butterfly structures. This result presents a way to select suitable scale morphologies from 174,500 species of Lepidopterans to replicate, as consumable SERS substrates with low cost and high reproducibility.</P>