Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS
Summary: Trusted execution environments (TEEs), such as Intel SGX, enable secure, privacy-preserving computations but may have computational resource constraints. To address this, methods like SkSES use sketching for genome-wide association studies (GWAS) across distributed datasets while maintainin...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004225002718 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849773325941735424 |
|---|---|
| author | Junyan Xu Kaiyuan Zhu Jieling Cai Can Kockan Natnatee Dokmai Hyunghoon Cho David P. Woodruff S. Cenk Sahinalp |
| author_facet | Junyan Xu Kaiyuan Zhu Jieling Cai Can Kockan Natnatee Dokmai Hyunghoon Cho David P. Woodruff S. Cenk Sahinalp |
| author_sort | Junyan Xu |
| collection | DOAJ |
| description | Summary: Trusted execution environments (TEEs), such as Intel SGX, enable secure, privacy-preserving computations but may have computational resource constraints. To address this, methods like SkSES use sketching for genome-wide association studies (GWAS) across distributed datasets while maintaining privacy. Here, we present a learning-augmented version of SkSES for more accurate identification of significant SNPs. Our method first conducts GWAS on a public training dataset to locally identify significant SNPs. These SNPs are assigned dedicated memory to enable more precise selection of significant SNPs over the entire dataset while optimizing memory usage. Our method maintains the stringent privacy guarantees of SkSES, ensuring sensitive genotype data remains undisclosed to other institutions or cloud providers. Experimental results on benchmark datasets show the learning-augmented version achieves up to 40% higher accuracy compared to the original SkSES under identical memory constraints. This advancement improves the scalability and effectiveness of collaborative GWAS studies in TEEs. |
| format | Article |
| id | doaj-art-0bbc87a2f45d44f4a3b64ab452a64cd9 |
| institution | DOAJ |
| issn | 2589-0042 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj-art-0bbc87a2f45d44f4a3b64ab452a64cd92025-08-20T03:02:06ZengElsevieriScience2589-00422025-03-0128311201110.1016/j.isci.2025.112011Learning-augmented sketching offers improved performance for privacy preserving and secure GWASJunyan Xu0Kaiyuan Zhu1Jieling Cai2Can Kockan3Natnatee Dokmai4Hyunghoon Cho5David P. Woodruff6S. Cenk Sahinalp7Cancer Data Science Laboratory, National Cancer Institute, National Institutes of Health, Bethesda, MD, USADepartment of Computer Science and Engineering, UC San Diego, La Jolla, CA, USADepartment of Computer Science, Tufts University, Medford, MA, USABroad Institute of MIT and Harvard, Cambridge, MA, USADepartment of Biomedical Informatics and Data Science, Yale University, New Haven, CT, USADepartment of Biomedical Informatics and Data Science, Yale University, New Haven, CT, USADepartment of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USACancer Data Science Laboratory, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA; Corresponding authorSummary: Trusted execution environments (TEEs), such as Intel SGX, enable secure, privacy-preserving computations but may have computational resource constraints. To address this, methods like SkSES use sketching for genome-wide association studies (GWAS) across distributed datasets while maintaining privacy. Here, we present a learning-augmented version of SkSES for more accurate identification of significant SNPs. Our method first conducts GWAS on a public training dataset to locally identify significant SNPs. These SNPs are assigned dedicated memory to enable more precise selection of significant SNPs over the entire dataset while optimizing memory usage. Our method maintains the stringent privacy guarantees of SkSES, ensuring sensitive genotype data remains undisclosed to other institutions or cloud providers. Experimental results on benchmark datasets show the learning-augmented version achieves up to 40% higher accuracy compared to the original SkSES under identical memory constraints. This advancement improves the scalability and effectiveness of collaborative GWAS studies in TEEs.http://www.sciencedirect.com/science/article/pii/S2589004225002718GeneticsHealth technology |
| spellingShingle | Junyan Xu Kaiyuan Zhu Jieling Cai Can Kockan Natnatee Dokmai Hyunghoon Cho David P. Woodruff S. Cenk Sahinalp Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS iScience Genetics Health technology |
| title | Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS |
| title_full | Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS |
| title_fullStr | Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS |
| title_full_unstemmed | Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS |
| title_short | Learning-augmented sketching offers improved performance for privacy preserving and secure GWAS |
| title_sort | learning augmented sketching offers improved performance for privacy preserving and secure gwas |
| topic | Genetics Health technology |
| url | http://www.sciencedirect.com/science/article/pii/S2589004225002718 |
| work_keys_str_mv | AT junyanxu learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT kaiyuanzhu learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT jielingcai learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT cankockan learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT natnateedokmai learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT hyunghooncho learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT davidpwoodruff learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas AT scenksahinalp learningaugmentedsketchingoffersimprovedperformanceforprivacypreservingandsecuregwas |