Semi-non parametric smooth isotonic regression

We propose a new method for smooth isotonic regression analysis. Unlike most existing methods for isotonic regression, the proposed method is akin to parametric regression without order restriction. To account for smoothness and isotonicity simultaneously, we exploit the flexible class of semi-non parametric densities to model isotonic regression functions. Under this framework, the full range of inference techniques for parametric regression models become applicable for model estimation and model validation in isotonic regression.     

A note on statistical method for genotype calling of high-throughput single-nucleotide polymorphism arrays

We study the genotype calling algorithms for the high-throughput single-nucleotide polymorphism (SNP) arrays. Building upon the novel SNP-robust multi-chip average preprocessing approach and the state-of-the-art corrected robust linear model with Mahalanobis distance (CRLMM) approach for genotype calling, we propose a simple modification to better model and combine the information across multiple SNPs with empirical Bayes modeling, which could often significantly improve the genotype calling of CRLMM. Through applications to the HapMap Trio data set and a non-HapMap test set of high quality SNP chips, we illustrate the competitive performance of the proposed method.     

2型糖尿病相关单核苷酸多态性c/t位点相似性分析

2型糖尿病（非胰岛素依赖型糖尿病）具有明显的家族遗传特点,但它的基因起源很大程度上并未得到深入了解。几种遗传因素共同影响提高了患2型糖尿病及相关代谢性疾病的风险性。通过对与2型糖尿病相关联的单核苷酸多态性位点（SNPs）做相似性分析来揭示2型糖尿病的基本机制,并作为标记来定位和识别与这一疾病相关的基因。     

An Approximation Algorithm for Alignment of Multiple Sequences using Motif Discovery

Given a set of N sequence, the Multiple Sequence Alignment problem is to align these N sequences, possibly with gaps, that brings out the best commonality of the N sequences. The quality of the alignment is usually measured by penalizing the mis-matches and gaps, and rewarding the matches with appropriate weight functions. However for larger values of N, additional constraints are required to give meaningful alignments. We identify a user-controlled parameter, an alignment number K (2 K N): this additional requirement constrains the alignment to have at least K sequences agree on a character, whenever possible, in the alignment. We identify a natural optimization problem for this approach called the K-MSA problem. We show that the problem is MAX SNP hard. We give a natural extension of this problem that incorporates biological relevance by using motifs (common patterns in the sequences) and give an approximation algorithm for this problem in terms of the motifs in the data. MUSCA is an implementation of this approach and our experimental results indicate that this approach is efficient, particularly on large numbers of long sequences, and gives good alignments when tested on biological data such as DNA and protein sequences.     

Genetic variants in 5p13.2 and 7q21.1 are associated with treatment for benign prostatic hyperplasia with the α-adrenergic receptor antagonist

Background: The etiology of benign prostatic hyperplasia (BPH) has not been well established. The preferred medical treatment for many men with symptomatic benign prostatic hyperplasia is either an α-adrenergic receptor antagonist (α-blocker), or a 5α-reductase inhibitor. Single nucleotide polymorphism (SNP) is a powerful tool for successful implementation of individualized treatment.

Methods: Eighteen SNPs associated with drug efficacy in a Chinese population were genotyped in 790 BPH cases (330 aggressive and 460 non-aggressive BPH cases) and 1008 controls. All BPH patients were treated with α-adrenergic blockers for at least 9 months. We tested the associations between tagging single nucleotide polymorphism and BPH risk/aggressiveness, clinical characteristics at baseline, including the International Prostate Symptom Score (IPSS) and total prostate volume, and changes in clinical characteristics after treatment.

Results: There were nine SNPs associated with BPH risk, clinical progression and therapeutic effect. (1) There were nine tSNPs been chosen in CYP3A4, CYP3A5 and RANBP3L genes. (2) The SNP, rs16902947 in RANBP3L at 5p13.2 (p?=?.01), was significantly associated with BPH. (3) We found two SNPs, rs16902947 in RANBP3L at 5p13.2 (p?=?.0388) and rs4646437 in CYP3A4 at 7q21.1 (p?=?.0325), associated with drug effect. (4) Allele “G” for rs16902947 was found to be risk alleles for BPH risk (OR=?2.357, 95%CI 1.01–1.48). The “A” allele of rs4646437 was associated with lower IPSS at baseline (β=??0.4232, p=?.03255).

Conclusions: rs16902947, rs16902947 and rs4646437 single nucleotide polymorphisms are significantly associated with the clinical characteristics of benign prostatic hyperplasia and the efficacy of benign prostatic hyperplasia treatment.     

短期利率模型在上交所债券市场上的实证分析

以中国上海证券交易所从债券价格导出的0.5年期利率的周度数据为分析对象,使用SNP法,估计出短期利率的条件密度函数,发现其条件分布具有明显的异方差性和非正态性.然后利用EMM法实证分析了常用的连续时间的单因子和两因子短期利率模型.单因子短期利率模型包括Vasicek模型,CIR模型,CKLS模型等,两因子利率模型包括Gallant,Tanchen给出的随机波动率模型和Balduzzi等人的随机均值回复模型.实证结果表明所有的单因子短期利率模型都不能很好地描述中国上海证券交易所债券市场上的短期利率变化,CKLS模型是它们中表现最好的单因子利率模型.随机均值回复模型也不能描述短期利率的变化,只有随机波动率模型可以描述上海证券交易所的短期利率的变化.     

"SNP是"类判断句的发展——兼论语言接触在其发展过程中的影响

＂SNP是＂类判断句是近代汉语特有的判断句式,其产生以后,主要用于佛经或与之相关的佛教文献中,本土文献虽然也使用这一格式,但数量始终有限。随着佛教势力的衰弱和佛教文献中语言的僵化,该句式也慢慢走向消亡。元明时期句末的＂便是＂已经虚化,其功能分析为语气词更合适。     

Statistical inference through AFT model for biotechnical systems

The objective of this paper is to model the phenomenon of degradation-to-failure for assemblies used for lumbar arthrodesis, starting from the analysis of their structure/geometry, the load applied and the kind of failure when several occur. An AFT model is proposed to model the joint effects of the applied load and the structural dimensions of the brand (namely length and diameter of the screw, presence of a connector or not) on the failure time due to a screw failure. The estimations of S–N curves and maximum permissible load (named critical load) values are provided as functions of the structural dimensions of the product. This allows comparisons of devices in terms of key factors determining product behavior and ageing under loading stress.     

白藜芦醇和硝普钠对月季切花的保鲜效应

为筛选出高效、低毒、无污染的月季切花保鲜剂,试验探讨了白藜芦醇和外源NO供体硝普钠对月季切花保鲜的影响。结果表明：含有50μmol·L^-1白藜芦醇和100μmol·L^-1硝普钠的保鲜剂均能有效调节切花水分平衡,改善切花体内的水分状况,减轻细胞质膜透性,降低膜脂过氧化水平,从而延缓切花衰老进程,延长瓶插寿命。对白藜芦醇和硝普钠保鲜效应的机理进行了初步探讨。     

CD14基因多态性与强直性脊柱炎的关联性研究

目的：探讨CD14基因rs2569190位点的单核苷酸多态性与强直性脊柱炎易感性的关系.方法采用PCR-RFLP方法对240例AS患者进行CD14基因多态性检测,并与140名健康对照者进行对比.结果 rs2569190位点基因型频率两组间差异具有统计学意义(χ2=6.778,υ=2,P<0.05);强直性脊柱炎组携带突变体A基因的频率高于对照组,差异具有统计学意义(χ2=3.876,υ=1,P<0.05).结论 CD14基因rs2569190位点单核苷酸多态性与强直性脊柱炎易感性存在关联,携带CD14突变体A基因者患AS风险较大.