Machine learning in prediction of genetic risk of nonsyndromic oral clefts in the Brazilian population.

OBJECTIVES: Genetic variants in multiple genes and loci have been associated with the risk of nonsyndromic cleft lip with or without cleft palate (NSCL ± P). However, the estimation of risk remains challenge, because most of these variants are population-specific rendering the identification of the underlying genetic risk difficult. Herein we examined the use of machine learning network in previously reported single nucleotide polymorphisms (SNPs) to predict risk of NSCL ± P in the Brazilian population. MATERIALS AND METHODS: Random forest and neural network methods were applied in 72 SNPs in a case-control sample composed by 722 NSCL ± P and 866 controls for discrimination of NSCL ± P risk. SNP-SNP interactions and functional annotation biological processes associated with the identified NSCL ± P risk genes were verified. RESULTS: Supervised random forest decision trees revealed high scores of importance for the SNPs rs11717284 and rs1875735 in FGF12, rs41268753 in GRHL3, rs2236225 in MTHFD1, rs2274976 in MTHFR, rs2235371 and rs642961 in IRF6, rs17085106 in RHPN2, rs28372960 in TCOF1, rs7078160 in VAX1, rs10762573 and rs2131960 in VCL, and rs227731 in 17q22, with an accuracy of 99% and an error rate of approximately 3% to predict the risk of NSCL ± P. Those same 13 SNPs were considered the most important for the neural network to effectively predict NSCL ± P risk, with an overall accuracy of 94%. Multivariate regression model revealed significant interactions among all SNPs, with an exception of those in FGF12 and MTHFD1. The most significantly biological processes for selected genes were those involved in tissue and epithelium development; neural tube closure; and metabolism of methionine, folate, and homocysteine. CONCLUSIONS: Our results provide novel clues for genetic mechanism studies of NSCL ± P and point out for a machine learning model composed by 13 SNPs that is capable of predicting NSCL ± P risk. CLINICAL RELEVANCE: Although validation is necessary, this genetic panel can be useful in the near future to assist in NSCL ± P genetic counseling.

Interactions between superoxide dismutase and paraoxonase polymorphic variants in nonsyndromic cleft lip with or without cleft palate in the Brazilian population.

During development, oxidative stress is hypothesized to mediate embryotoxicity, which may be intensified by exposition to environmental factors and by genetic variations in the enzymes involved in protecting cells from these damaging effects, including superoxide dismutase (SOD) and paraoxonase (PON). The aim of this study was to evaluate the influence of single-nucleotide polymorphisms (SNP) in genes associated with the neutralization of oxidative stress (SOD and PON family members) in the risk of nonsyndromic oral cleft in the Brazilian population. Initially, we tested for association between 28 SNP in SOD1, SOD2, SOD3, PON1, PON2, and PON3 among 325 nonsyndromic cleft lip with or without cleft palate (NSCL±P) case-parent trios. Multiple logistic regression analyses were used to explore gene, GxG and GxE, involving factors that induce oxidative stress accumulation during pregnancy. Signals still significant after both Bonferroni correction and in permutation test were subsequently confirmed in an ancestry-structured case-control analysis with 722 NSCL±P and 866 controls from the same population. In the trio sample, transmission disequilibrium test (TDT) (allele and haplotype) and GxE analysis showed no significant associations, but multiple pairwise GxG interactions involving 10 SNP in PON1, PON2, and PON3 were detected and further examined in the case-control sample. The PON1 rs2237583 and PON2 rs17166879 yielded significant evidence of SNP-SNP interactions after adjustment for multiple tests (both Bonferroni correction and 10,000 permutation test). The C allele and the CT genotype of PON1 rs2237583 were associated with significant protective effects against NSCL±P, while rs3917490 showed a significant association only in the sample composed of patients displaying high African ancestry. Our results reveal associations between rs2237583 and rs3917490 in PON1 and GxG interactions containing rs2237583 and rs17166879 with the susceptibility of NSCL±P in the Brazilian population. Furthermore, this study underlines the recent tendency of taking into account potential GxG interactions to clarify the underlying mechanisms associated with the etiology of this common malformation. Environ. Mol. Mutagen. 60: 185-196, 2019. © 2018 Wiley Periodicals, Inc.