Bayesian logistic regression in detection of gene-steroid interaction for cancer at PDLIM5 locus
Bayesian logistic regression in detection of gene-steroid interaction for cancer at PDLIM5 locus
复制标题
DOI：
10.1007/s12041-016-0642-1
复制
发表时间：
2016-06-01
影响因子：
1.5
通讯作者：
Xie, Changchun
中科院分区：
文献类型：
--
作者：
Wang, Ke-Sheng;Owusu, Daniel;Xie, Changchun
PDZ和LIM结构域5（PDLIM 5）基因可能在癌症、双相情感障碍、抑郁症、酒精依赖和精神分裂症中发挥作用;然而，关于类固醇和PDLIM 5基因在癌症中的相互作用知之甚少。该研究检测了Marshfield样本中PDLIM 5基因内的47个单核苷酸多态性（SNP），其中包括716名癌症患者（任何确诊的癌症，不包括轻微皮肤癌）和2848名非癌症对照。采用PLINK软件中的多元Logistic回归模型分析各SNP与癌症的相关性。SAS统计软件中PROC GENMOD中的贝叶斯逻辑回归，版本9.4用于检测影响癌症的基因-类固醇相互作用。使用PLINK的单标记分析鉴定出12个与癌症相关的SNP（P < 0.05）;特别是SNP rs6532496显示出与癌症最强的关联（P = 6.84 x 10（-3））;而次佳信号是rs 951613（P = 7.46 x 10（-3））。PROC GENMOD中的经典逻辑回归表明，rs6532496和rs 951613均显示出强烈的基因-类固醇相互作用效应（rs6532496的OR = 2.18，95%CI = 1.31-3.63，P = 2.9 x 10（-3）; rs951613的OR = 2.07，95%CI = 1.24 - 3.45，P = 5.43 x 10（-3））。贝叶斯logistic回归分析结果显示，rs6532496和rs 951613的交互作用更强（OR = 2.26，95%CI = 1.2 - 3.38和OR = 2.14，95%CI = 1.14 - 3.2）。与癌症相关的12个SNPs均显示出显著的基因-类固醇交互作用（P < 0.05），而13个SNPs显示出基因-类固醇交互作用，但对癌症无主效应。SNP rs 4634230揭示了最强的基因-类固醇相互作用效应（基于经典逻辑回归的OR = 2.49，95%CI = 1.5 - 4.13，P = 4.0 × 10（-4）;基于贝叶斯逻辑回归的OR = 2.59，95%CI = 1.4 - 3.97;分别地）。这项研究提供了PDLIM 5基因内常见遗传变异的证据，以及PLDIM 5基因多态性和类固醇使用影响癌症之间的相互作用。
The PDZ and LIM domain 5 (PDLIM5) gene may play a role in cancer, bipolar disorder, major depression, alcohol dependence and schizophrenia; however, little is known about the interaction effect of steroid and PDLIM5 gene on cancer. This study examined 47 single-nucleotide polymorphisms (SNPs) within the PDLIM5 gene in the Marshfield sample with 716 cancer patients (any diagnosed cancer, excluding minor skin cancer) and 2848 noncancer controls. Multiple logistic regression model in PLINK software was used to examine the association of each SNP with cancer. Bayesian logistic regression in PROC GENMOD in SAS statistical software, ver. 9.4 was used to detect gene-steroid interactions influencing cancer. Single marker analysis using PLINK identified 12 SNPs associated with cancer (P < 0.05); especially, SNP rs6532496 revealed the strongest association with cancer (P = 6.84 x 10(-3)); while the next best signal was rs951613 (P = 7.46 x 10(-3)). Classic logistic regression in PROC GENMOD showed that both rs6532496 and rs951613 revealed strong gene-steroid interaction effects (OR = 2.18, 95% CI = 1.31-3.63 with P = 2.9 x 10(-3) for rs6532496 and OR = 2.07, 95% CI = 1.24 -3.45 with P = 5.43 x 10(-3) for rs951613, respectively). Results from Bayesian logistic regression showed stronger interaction effects (OR = 2.26, 95% CI = 1.2 -3.38 for rs6532496 and OR = 2.14, 95% CI = 1.14 -3.2 for rs951613, respectively). All the 12 SNPs associated with cancer revealed significant gene-steroid interaction effects (P < 0.05); whereas 13 SNPs showed gene-steroid interaction effects without main effect on cancer. SNP rs4634230 revealed the strongest gene-steroid interaction effect (OR = 2.49, 95% CI = 1.5 -4.13 with P = 4.0 x 10(-4) based on the classic logistic regression and OR = 2.59, 95% CI = 1.4 -3.97 from Bayesian logistic regression; respectively). This study provides evidence of common genetic variants within the PDLIM5 gene and interactions between PLDIM5 gene polymorphisms and steroid use influencing cancer.