Genome-wide association studies in the osteoporosis field: Impressive technological achievements, but an uncertain future in the clinical setting

Andrews, Neil A

doi:10.1138/20100472

Cited by 5 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Haplotype Reference Consortium (HRC) reference panel, a most comprehensive imputation reference panel, as well as Positional Burrows-Wheeler Transform (PBWT) imputing algorithm, were used for the genotype imputation in order to ensure high imputation quality. In the large-scale GWAS meta-analysis a total of 63 SNPs was reported to be associated with BMD [19]. Because rs344081 was associated with BMD only in man [19], only 62 SNPs were included in the imputation and analysis.…”

Section: Methodsmentioning

confidence: 99%

“…In the large-scale GWAS meta-analysis a total of 63 SNPs was reported to be associated with BMD [19]. Because rs344081 was associated with BMD only in man [19], only 62 SNPs were included in the imputation and analysis. Imputation quality was excellent, with mean R 2 = 0.99.…”

Section: Methodsmentioning

confidence: 99%

“…None of the 62 SNPs was removed after pruning. Both unweighted and weighted GRS were then calculated with algorithms described by Estrada and colleagues [19]. Briefly, the unweighted multi-locus genetic risk score (UW-GRS) was generated by summing the number of risk-conferring alleles that each individual had (0, 1, or 2) across all loci.…”

Section: Methodsmentioning

confidence: 99%

“…Hence, in addition to the established factors, uncovering the underlying genetic risk inherent in certain populations will help identify susceptible groups and hasten the implementation of preventive treatments [17]. With a mounting number of genome-wide association studies (GWAS) implemented, dozens of Single Nucleotide Polymorphisms (SNPs) have been found to be associated with BMD [18, 19]. However, what remains unclear is how these variants cause decreased BMD and osteoporosis.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Genetic profiling of decreased bone mineral density in an independent sample of Caucasian women

Xiao

Roohani

2018

Osteoporos Int

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Genetic profiling of decreased bone mineral density in an independent sample of Caucasian women

Xiao

Roohani

2018

Osteoporos Int

View full text Add to dashboard Cite

show abstract

“…None of the 1,103 SNPs was removed after the pruning. The weighted GRS was then calculated with algorithms described previously 16 . Briefly, for each participant in MrOS, overall weighted GRS was calculated by summing the number of risk alleles at each locus multiplied by their effect size, which are regression coefficients related to BMD, from the referenced literature 6 .…”

Section: Genetic Risk Scorementioning

confidence: 99%

Machine Learning Approaches for the Prediction Bone Mineral Density by using genomic and phenotypic data of 5,130 older Men

Nasoz

Jung

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The study aimed to utilize machine learning (ML) approaches and genomic data to develop the prediction model for bone mineral density (BMD), and to identify the best modeling approach for BMD prediction. Method: The genomic and phenotypic data of Osteoporotic Fractures in Men Study (n=5,130), was analyzed. Genetic risk score (GRS) was calculated from 1,103 associated SNPs for each participant after a comprehensive genotype imputation. Data were normalized and divided into a training set (80%) and a validation set (20%) for analysis. Random forest, gradient boosting, neural network, and linear regression were used to develop prediction models for BMD separately. The 10-fold cross-validation was used for hyperparameter optimization. Mean square error and mean absolute error were used to assess model performance. Results: When using GRS and phenotypic covariates as the predictors, the performance of all ML models and linear regression in BMD prediction is similar. However, when replacing GRS with the 1,103 individual SNPs in the model, ML models performed significantly better than linear regression, and the gradient boosting model performed the best. Conclusion: Our study suggested that ML models, especially gradient boosting, can improve BMD prediction in genomic data.

show abstract

Machine Learning Approaches for Fracture Risk Assessment: A Comparative Analysis of Genomic and Phenotypic Data in 5130 Older Men

Nasoz

Jung

et al. 2020

Calcif Tissue Int

View full text Add to dashboard Cite

The study aims were to develop fracture prediction models by using machine learning approaches and genomic data, as well as to identify the best modeling approach for fracture prediction. The genomic data of Osteoporotic Fractures in Men, cohort Study (n = 5,130), was analyzed. After a comprehensive genotype imputation, genetic risk score (GRS) was calculated from 1,103 associated Single-Nucleotide Polymorphisms for each participant. Data were normalized and split into a training set (80%) and a validation set (20%) for analysis. Random forest, gradient boosting, Terms of use and reuse: academic research for non-commercial purposes, see here for full terms. https://www.springer.com/aamterms-v1

show abstract

Genome-wide association studies in the osteoporosis field: Impressive technological achievements, but an uncertain future in the clinical setting

Cited by 5 publications

References 0 publications

Genetic profiling of decreased bone mineral density in an independent sample of Caucasian women

Genetic profiling of decreased bone mineral density in an independent sample of Caucasian women

Machine Learning Approaches for the Prediction Bone Mineral Density by using genomic and phenotypic data of 5,130 older Men

Machine Learning Approaches for Fracture Risk Assessment: A Comparative Analysis of Genomic and Phenotypic Data in 5130 Older Men

Contact Info

Product

Resources

About