Skip to main navigation Skip to search Skip to main content

Low-dimensional genotype embeddings for predictive models

  • Furman University
  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We develop methods for constructing low-dimensional vector representations (embeddings) of large-scale genotyping data, capable of reducing genotypes of hundreds of thousands of SNPs to 100-dimensional embeddings that retain substantial predictive power for inferring medical phenotypes. We demonstrate that embedding-based models yield an average F-score of 0.605 on a test of ten phenoypes (including BMI prediction, genetic relatedness, and depression) versus 0.339 for baseline models. Genotype embeddings also hold promise for creating sharing data while preserving subject anonymity: we show that they retain substantial predictive power even after anonymization by adding Gaussian noise to each dimension.

Original languageEnglish
Title of host publicationProceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450393867
DOIs
StatePublished - Aug 7 2022
Event13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022 - Chicago, United States
Duration: Aug 7 2022Aug 8 2022

Publication series

NameProceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022

Conference

Conference13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022
Country/TerritoryUnited States
CityChicago
Period08/7/2208/8/22

Keywords

  • Embeddings
  • Genotype
  • Privacy-preserving

Fingerprint

Dive into the research topics of 'Low-dimensional genotype embeddings for predictive models'. Together they form a unique fingerprint.

Cite this