Risk prediction models for oral clefts allowing for phenotypic heterogeneity

Genetic Variants in Mammalian STE20-like Protein Kinase 2 were associated with risk of NSCL/P

AIM

Mammalian STE20-like protein kinase 2 (MST2) plays an important role in apoptosis and the development of many disorders. Here, we aim to explore if genetic variants in MST2 are associated with the risk of non-syndromic cleft lip with or without palate (NSCL/P).

MATERIALS AND METHODS

The association study was performed in a two-stage study of 1,069 cases and 1,724 controls to evaluate the association between genetic variants in the MST2 and NSCL/P risk. The potential function of the candidate single nucleotide polymorphism (SNP) was predicted using HaploReg, RegulomeDB, and public craniofacial histone chromatin immunoprecipitation sequencing (ChIP-seq) data. Haploview was used to perform the haplotype of risk alleles. The expression quantitative trait loci (eQTL) effect was assessed using the Genotype-Tissue Expression (GTEx) project. Gene expression in mouse embryo tissue was performed using data downloaded from GSE67985. The potential role of candidate gene in the development of NSCL/P was assessed by correlation and enrichment analysis.

RESULTS

Among SNPs in MST2, rs2922070 C allele (P_meta = 2.93E-04) and rs6988087 T allele (P_meta = 1.57E-03) were linked with significantly increased risk of NSCL/P. Rs2922070, rs6988087 and their high linkage disequilibrium (LD) SNPs constituted a risk haplotype of NSCL/P. Individuals carrying 3-4 risk alleles had an elevated risk of NSCL/P compared to those who carried less risk alleles (P = 2.00E-04). The eQTL analysis revealed a significant association between these two variants and MST2 in muscle tissue of the body. The MST2 expressed during mouse craniofacial development and over-expressed in the human orbicularis oris muscle (OOM) of NSCL/P patients compared to controls. MST2 was involved in the development of NSCL/P by regulating the mRNA surveillance pathway, the MAPK signaling pathway, the neurotrophin signaling pathway, the FoxO signaling pathway and the VEGF signaling pathway.

CONCLUSION

MST2 was associated with the development of NSCL/P.

Predicting congenital heart defects: A comparison of three data mining methods

Congenital heart defects (CHD) is one of the most common birth defects in China. Many studies have examined risk factors for CHD, but their predictive abilities have not been evaluated. In particular, few studies have attempted to predict risks of CHD from, necessarily unbalanced, population-based cross-sectional data. Therefore, we developed and validated machine learning models for predicting, before and during pregnancy, women’s risks of bearing children with CHD. We compared the results of these models in a large-scale, comprehensive population-based retrospective cross-sectional epidemiological survey of birth defects in six counties in Shanxi Province, China, covering 2006 to 2008. This contained 78 cases of CHD among 33831 live births. We constructed nine synthetic variables to use in the models: maternal age, annual per capita income, family history, maternal history of illness, nutrition and folic acid deficiency, maternal illness in pregnancy, medication use in pregnancy, environmental risk factors in pregnancy, and unhealthy maternal lifestyle in pregnancy. The machine learning algorithms Weighted Support Vector Machine (WSVM) and Weighted Random Forest (WRF) were trained on, and a logistic regression (Logit) was fitted to, two-thirds of the data. Their predictive abilities were then tested in the remaining data. True positive rate (TPR), true negative rate (TNR), accuracy (ACC), area under the curves (AUC), G-means, and Weighted accuracy (WTacc) were used to compare the classification performance of the models. Median values, from repeating the data partitioning 1000 times, were used in all comparisons. The TPR and TNR of the three classifiers were above 0.65 and 0.93, respectively, better than any reported in the literature. TPR, wtACC, AUC and G were highest for WSVM, showing that it performed best. All three models are precise enough to identify groups at high risk of CHD. They should all be considered for future investigations of other birth defects and diseases.