The heparan sulfate 6-O-sulfotransferase 3 (HS6ST3) gene is involved in heparan sulphate and heparin metabolism, and has been reported to be associated with diabetic retinopathy in type 2 diabetes. We hypothesized that HS6ST3 gene polymorphisms might play an important role in obesity and related phenotypes (such as triglycerides). We examined genetic associations of 117 single-nucleotide polymorphisms (SNPs) within the HS6ST3 gene with obesity and triglycerides using two Caucasian samples: the Marshfield sample (1442 obesity cases and 2122 controls), and the Health aging and body composition (Health ABC) sample (305 cases and 1336 controls). Logistic regression analysis of obesity as a binary trait and linear regression analysis of triglycerides as a continuous trait, adjusted for age and sex, were performed using PLINK. Single marker analysis showed that six SNPs in the Marshfield sample and one SNP in the Health ABC sample were associated with obesity $(P \lt 0.05)$. SNP rs535812 revealed a stronger association with obesity in meta-analysis of these two samples $(P = 0.0105)$. The T–A haplotype from rs878950 and rs9525149 revealed significant association with obesity in the Marshfield sample $(P = 0.012)$. Moreover, nine SNPs showed associations with triglycerides in the Marshfield sample $(P \lt 0.05)$ and the best signal was rs1927796 $(P = 0.00858)$. In addition, rs7331762 showed a strong gene × gender interaction $(P = 0.00956)$ for obesity while rs1927796 showed a strong gene × gender interaction $(P = 0.000625)$ for triglycerides in the Marshfield sample. These findings contribute new insights into the pathogenesis of obesity and triglycerides and demonstrate the importance of gender differences in the aetiology.

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 $(P=6.84×10^{−3})$; while the next best signal was rs951613 $(P=7.46×10^{−3})$. 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 $P= 2.9×10^{−3}$ for rs6532496 and OR = 2.07, 95% CI =1.24 −3.45 with $P=5.43×10^{−3}$ 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 $P=4.0×10^{−4}$ 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.