Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes
The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2016-12-01
|
| Series: | Genomics & Informatics |
| Subjects: | |
| Online Access: | http://genominfo.org/upload/pdf/gni-14-138.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572133103894528 |
|---|---|
| author | Sungkyoung Choi Sunghwan Bae Taesung Park |
| author_facet | Sungkyoung Choi Sunghwan Bae Taesung Park |
| author_sort | Sungkyoung Choi |
| collection | DOAJ |
| description | The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the “large p and small n” problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes. |
| format | Article |
| id | doaj-art-5d080074b3cb472ea8e164b3faab0087 |
| institution | Kabale University |
| issn | 1598-866X 2234-0742 |
| language | English |
| publishDate | 2016-12-01 |
| publisher | BioMed Central |
| record_format | Article |
| series | Genomics & Informatics |
| spelling | doaj-art-5d080074b3cb472ea8e164b3faab00872025-02-02T11:35:27ZengBioMed CentralGenomics & Informatics1598-866X2234-07422016-12-0114413814810.5808/GI.2016.14.4.138169Risk Prediction Using Genome-Wide Association Studies on Type 2 DiabetesSungkyoung Choi0Sunghwan Bae1Taesung Park2Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea.Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea.Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul 08826, Korea.The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the “large p and small n” problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.http://genominfo.org/upload/pdf/gni-14-138.pdfclinical prediction rulegenome-wide association studypenalized regression modelstype 2 diabetes |
| spellingShingle | Sungkyoung Choi Sunghwan Bae Taesung Park Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes Genomics & Informatics clinical prediction rule genome-wide association study penalized regression models type 2 diabetes |
| title | Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes |
| title_full | Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes |
| title_fullStr | Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes |
| title_full_unstemmed | Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes |
| title_short | Risk Prediction Using Genome-Wide Association Studies on Type 2 Diabetes |
| title_sort | risk prediction using genome wide association studies on type 2 diabetes |
| topic | clinical prediction rule genome-wide association study penalized regression models type 2 diabetes |
| url | http://genominfo.org/upload/pdf/gni-14-138.pdf |
| work_keys_str_mv | AT sungkyoungchoi riskpredictionusinggenomewideassociationstudiesontype2diabetes AT sunghwanbae riskpredictionusinggenomewideassociationstudiesontype2diabetes AT taesungpark riskpredictionusinggenomewideassociationstudiesontype2diabetes |