Prediction of Early Childhood Caries Based on Single Nucleotide Polymorphisms Using Neural Networks.
Ontology highlight
ABSTRACT: Background
Several genes and single nucleotide polymorphisms (SNPs) have been associated with early childhood caries. However, they are highly age- and population-dependent and the majority of existing caries prediction models are based on environmental and behavioral factors only and are scarce in infants.Methods
We examined 6 novel and previously analyzed 22 SNPs in the cohort of 95 Polish children (48 caries, 47 caries-free) aged 2-3 years. All polymorphisms were genotyped from DNA extracted from oral epithelium samples. We used Fisher's exact test, receiver operator characteristic (ROC) curve and uni-/multi-variable logistic regression to test the association of SNPs with the disease, followed by the neural network (NN) analysis.Results
The logistic regression (LogReg) model showed 90% sensitivity and 96% specificity, overall accuracy of 93% (p < 0.0001), and the area under the curve (AUC) was 0.970 (95% CI: 0.912-0.994; p < 0.0001). We found 90.9-98.4% and 73.6-87.2% prediction accuracy in the test and validation predictions, respectively. The strongest predictors were: AMELX_rs17878486 and TUFT1_rs2337360 (in both LogReg and NN), MMP16_rs1042937 (in NN) and ENAM_rs12640848 (in LogReg).Conclusions
Neural network prediction model might be a substantial tool for screening/early preventive treatment of patients at high risk of caries development in the early childhood. The knowledge of potential risk status could allow early targeted training in oral hygiene and modifications of eating habits.
SUBMITTER: Zaorska K
PROVIDER: S-EPMC8064067 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background:DNA prediction of eye color represent one application of the externally visible characteristics (EVC), which attained growing interest in the field of DNA forensic phenotyping. This is mainly due to its ability to narrow the pool of suspects without the need to compare any retrieved DNA material from the crime scene to a reference DNA. Several methods and multiplex genetic panel were proposed with variable prediction accuracy between different populations. However, such panel was not previously tested in the Saudi population, nor any populations of the Middle East and North Africa origin. Method:A panel of eleven single nucleotide polymorphisms (SNPs) was tested for their association with three eye colors (brown, hazel, and intermediate) in 80 volunteer Saudi individuals. SNPs and haplotype association test with eye colors were performed to identify the top significant SNPs with the three eye colors. Also, multinomial logistic regression was used to construct the prediction model using a training set of 60 subjects, and a validation set of 20 subjects. The goodness of fit parameter of the model to correctly predicts each eye color as compared to the other was performed. Results:Eye color was significantly associated with rs12913832, rs7170852, and rs916977 that are located within HERC2. SNP rs12913832 was the top significant SNP (p-value?=?1.78E-15) that accounted for the association in this region, as the other SNPs were not significant after adjusting for rs12913832. A prediction model containing five SNPs showed high prediction accuracy with Area Under the receiver operating characteristic Curves (AUC) equals to 0.95 and 0.83 for brown and intermediate eye colors, respectively. However, the model's performance was very low for predicting the hazel eye color with AUC equals 0.75. Discussion:Despite the small sample size of our study, we reported very significant SNP associations with eye color. Our model to predict eye colors based on DNA material showed high accuracy for brown and intermediate eye colors. The eye color prediction-model underperformed for the hazel eye colors, suggesting that larger sample size, as well as more comprehensive set of SNPs, could improve the model-prediction accuracy.
| S-EPMC6864217 | biostudies-literature
Project description:Background: Alterations of oral microbiota are the main cause of the progression of caries. The goal of this study was to characterize the oral microbiota in childhood caries based on single-molecule real-time sequencing. Methods: A total of 21 preschoolers, aged 3-5 years old with severe early childhood caries, and 20 age-matched, caries-free children as controls were recruited. Saliva samples were collected, followed by DNA extraction, Pacbio sequencing, and phylogenetic analyses of the oral microbial communities. Results: Eight hundred and seventy six species derived from 13 known bacterial phyla and 110 genera were detected from 41 children using Pacbio sequencing. At the species level, 38 species, including Veillonella spp., Streptococcus spp., Prevotella spp., and Lactobacillus spp., showed higher abundance in the caries group compared to the caries-free group (p < 0.05). The core microbiota at the genus and species levels was more stable in the caries-free micro-ecological niche. At follow-up, oral examinations 6 months after sample collection, development of new dental caries was observed in 5 children (the transitional group) among the 21 caries free children. Compared with the caries-free children, in the transitional and caries groups, 6 species, which were more abundant in the caries-free group, exhibited a relatively low abundance in both the caries group and the transitional group (p < 0.05). We conclude that Abiotrophia spp., Neisseria spp., and Veillonella spp., might be associated with healthy oral microbial ecosystem. Prevotella spp., Lactobacillus spp., Dialister spp., and Filifactor spp. may be related to the pathogenesis and progression of dental caries.
| S-EPMC5694851 | biostudies-literature
Project description:In this study, we developed machine learning-based prediction models for early childhood caries and compared their performances with the traditional regression model. We analyzed the data of 4195 children aged 1-5 years from the Korea National Health and Nutrition Examination Survey data (2007-2018). Moreover, we developed prediction models using the XGBoost (version 1.3.1), random forest, and LightGBM (version 3.1.1) algorithms in addition to logistic regression. Two different methods were applied for variable selection, including a regression-based backward elimination and a random forest-based permutation importance classifier. We compared the area under the receiver operating characteristic (AUROC) values and misclassification rates of the different models and observed that all four prediction models had AUROC values ranging between 0.774 and 0.785. Furthermore, no significant difference was observed between the AUROC values of the four models. Based on the results, we can confirm that both traditional logistic regression and ML-based models can show favorable performance and can be used to predict early childhood caries, identify ECC high-risk groups, and implement active preventive treatments. However, further research is essential to improving the performance of the prediction model using recent methods, such as deep learning.
| S-EPMC8393254 | biostudies-literature
Project description:Human microbiomes are predicted to assemble in a reproducible and ordered manner yet there is limited knowledge on the development of the complex bacterial communities that constitute the oral microbiome. The oral microbiome plays major roles in many oral diseases including early childhood caries (ECC), which afflicts up to 70% of children in some countries. Saliva contains oral bacteria that are indicative of the whole oral microbiome and may have the ability to reflect the dysbiosis in supragingival plaque communities that initiates the clinical manifestations of ECC. The aim of this study was to determine the assembly of the oral microbiome during the first four years of life and compare it with the clinical development of ECC. The oral microbiomes of 134 children enrolled in a birth cohort study were determined at six ages between two months and four years-of-age and their mother's oral microbiome was determined at a single time point. We identified and quantified 356 operational taxonomic units (OTUs) of bacteria in saliva by sequencing the V4 region of the bacterial 16S RNA genes. Bacterial alpha diversity increased from a mean of 31 OTUs in the saliva of infants at 1.9 months-of-age to 84 OTUs at 39 months-of-age. The oral microbiome showed a distinct shift in composition as the children matured. The microbiome data were compared with the clinical development of ECC in the cohort at 39, 48, and 60 months-of-age as determined by ICDAS-II assessment. Streptococcus mutans was the most discriminatory oral bacterial species between health and current disease, with an increased abundance in disease. Overall our study demonstrates an ordered temporal development of the oral microbiome, describes a limited core oral microbiome and indicates that saliva testing of infants may help predict ECC risk.
| S-EPMC6930300 | biostudies-literature
Project description:BackgroundDental caries is one of the most prevalent chronic diseases worldwide among children. The rs35874116 single nucleotide polymorphism (SNP) in the sweet receptor gene TAS1R2 has been associated with dental caries at a high risk in permanent teeth among school children and adults. To date, little is known about the association of this SNP with sweet intake and caries risk in the primary school children.MethodsTotal of 236 children were included, namely 118 subjects in the non-caries (NC) group and severe early childhood caries (S-ECC) group, respectively. Oral mucosa cells were collected from all the selected children, and the full length of exon 3 in TAS1R2 was sequenced to analyse rs35874116 polymorphism. A questionnaire was used to collect information about socio-demographic information, frequency of sweet intake and oral hygiene habits. Multiple logistic regression models were applied to assess the relationship of rs35874116 polymorphism with frequency of sweet intake and S-ECC among the five-year-old children.ResultsChildren with the TT genotype of rs35874116 had a higher frequency of sweet intake than CT/CC carriers (51.3% vs. 32.7%; x2 = 5.436, p = 0.020), and S-ECC individuals were more likely to be TT genotype carriers than NC individuals (53.5% vs. 46.5%; x2 = 4.353, p = 0.037). Multiple logistic regression analyses showed that the TT genotype of rs35874116 was not only significantly related to the frequency of sweet intake (OR = 2.25, 95% CI = 1.14-4.44) but also significantly associated with S-ECC (OR = 2.11, 95% CI = 1.01 ~ 4.42).ConclusionsThe rs35874116 polymorphism might increase sweet intake and the risk of S-ECC among five-year-old children in Nanning, China.
| S-EPMC9636656 | biostudies-literature
Project description:Comparative analysis of Severe Early Childhood Caries microbiome
| PRJNA454811 | ENA
Project description:The objective of this study was to prove the association between dental caries and single nucleotide polymorphisms (SNPs) in the ENAM gene.The research was carried out in 96 children (48 with caries and 48 counterparts free of this disease), aged 20-42 months, with 11-20 erupted teeth. All children were from four day nurseries located in Poznan. The study included the dental examination to select individuals to the research and oral swab collection for molecular evaluation. Seven selected SNPs markers of the ENAM gene were genotyped, five using TaqMan probe assay (rs2609428, rs7671281, rs36064169, rs3796704, and rs12640848) and two by Sanger sequencing (rs144929717 and rs139228330).Statistically significant higher prevalence of the alternative G allele and the alternative GG homozygote in the control group in comparison with the caries group in SNP rs12640848 was observed, respectively, p = 0.0062 and 0.0010. Although the prevalence of the AG heterozygote was higher for the caries subjects in comparison with controls (OR = 2.9), and the result was statistically significant (p = 0.0010), the overall prevalence of the G allele for this SNP was significantly higher in control group (OR = 2.3; p = 0.0062).The study revealed the strong association between rs12640848 marker of ENAM gene and caries susceptibility in primary teeth in children from Poznan.The presence of SNPs in the ENAM gene may be important as suspected predictive factor of dental caries occurrence in children.
| S-EPMC4799241 | biostudies-literature
Project description:BackgroundDNA recognition by proteins is one of the most important processes in living systems. Therefore, understanding the recognition process in general, and identifying mutual recognition sites in proteins and DNA in particular, carries great significance. The sequence and structural dependence of DNA-binding sites in proteins has led to the development of successful machine learning methods for their prediction. However, all existing machine learning methods predict DNA-binding sites, irrespective of their target sequence and hence, none of them is helpful in identifying specific protein-DNA contacts. In this work, we formulate the problem of predicting specific DNA-binding sites in terms of contacts between the residue environments of proteins and the identity of a mononucleotide or a dinucleotide step in DNA. The aim of this work is to take a protein sequence or structural features as inputs and predict for each amino acid residue if it binds to DNA at locations identified by one of the four possible mononucleotides or one of the 10 unique dinucleotide steps. Contact predictions are made at various levels of resolution viz. in terms of side chain, backbone and major or minor groove atoms of DNA.ResultsSignificant differences in residue preferences for specific contacts are observed, which combined with other features, lead to promising levels of prediction. In general, PSSM-based predictions, supported by secondary structure and solvent accessibility, achieve a good predictability of approximately 70-80%, measured by the area under the curve (AUC) of ROC graphs. The major and minor groove contact predictions stood out in terms of their poor predictability from sequences or PSSM, which was very strongly (>20 percentage points) compensated by the addition of secondary structure and solvent accessibility information, revealing a predominant role of local protein structure in the major/minor groove DNA-recognition. Following a detailed analysis of results, a web server to predict mononucleotide and dinucleotide-step contacts using PSSM was developed and made available at http://sdcpred.netasa.org/ or http://tardis.nibio.go.jp/netasa/sdcpred/.ConclusionMost residue-nucleotide contacts can be predicted with high accuracy using only sequence and evolutionary information. Major and minor groove contacts, however, depend profoundly on the local structure. Overall, this study takes us a step closer to the ultimate goal of predicting mutual recognition sites in protein and DNA sequences.
| S-EPMC2693520 | biostudies-literature
Project description:Single nucleotide polymorphisms (SNPs) can have significant effects on phenotypic characteristics in cattle. MicroRNAs (miRNAs) are small, non-coding RNAs that act as post-transcriptional regulators by binding them to target mRNAs. In the present study, we scanned ~56 million SNPs against 1,064 bovine miRNA sequences and analyzed, in silico, their possible effects on target binding prediction, primary miRNA formation, association with QTL regions and the evolutionary conservation for each SNP locus. Following target prediction, we show that 71.6% of miRNA predicted targets were altered as a consequence of SNPs located within the seed region of the mature miRNAs. Next, we identified variations in the Minimum Free Energy (MFE), which represents the capacity to alter molecule stability and, consequently, miRNA maturation. A total of 48.6% of the sequences analyzed showed values within those previously reported as sufficient to alter miRNA maturation. We have also found 131 SNPs in 46 miRNAs, with altered target prediction, occurring in QTL regions. Lastly, analysis of evolutionary conservation scores for each SNP locus suggested that they have a conserved biological function through the evolutionary process. Our results suggest that SNPs in microRNAs have the potential to affect bovine phenotypes and could be of great value for genetic improvement studies, as well as production.
| S-EPMC8059806 | biostudies-literature
Project description:Dental caries is a multifactorial infectious disease. In this study, we investigated whether single nucleotide polymorphisms (SNPs) in vitamin D receptor (VDR) gene were associated with susceptibility to permanent tooth caries in Chinese adolescents.A total of 200 dental caries patients and 200 healthy controls aged 12 years were genotyped for VDR gene polymorphisms using the PCR-restriction fragment length polymorphism (PCR-RFLP) assay. All of them were examined for their oral and dental status with the WHO criteria, and clinical information such as the Decayed Missing Filled Teeth Index (DMFT) was evaluated. Genomic DNA was extracted from the buccal epithelial cells. The four polymorphic SNPs (Bsm I, Taq I, Apa I, and Fok I) in VDR were assessed for both genotypic and phenotypic susceptibilities.Among the four examined VDR gene polymorphisms, the increased frequency of the CT and CC genotype of the Fok I VDR gene polymorphism was associated with dental caries in 12-year-old adolescent, compared with the controls (X2 = 17.813, p ? 0.001). Moreover, Fok I polymorphic allele C frequency was significantly increased in the dental caries cases, compared to the controls (X2 = 14.144, p ? 0.001, OR = 1.730, 95% CI = 1.299-2.303). However, the other three VDR gene polymorphisms (Bsm I, Taq I, and Apa I) showed no statistically significant differences in the caries groups compared with the controls.VDR-Fok I gene polymorphisms may be associated with susceptibility to permanent tooth caries in Chinese adolescent.
| S-EPMC5702413 | biostudies-literature