@inproceedings{338707c26ad043c98a634f013b771b58,
title = "Low-dimensional genotype embeddings for predictive models",
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.",
keywords = "Embeddings, Genotype, Privacy-preserving",
author = "Sultan, \{Syed Fahad\} and Xingzhi Guo and Steven Skiena",
note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022 ; Conference date: 07-08-2022 Through 08-08-2022",
year = "2022",
month = aug,
day = "7",
doi = "10.1145/3535508.3545507",
language = "English",
series = "Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022",
publisher = "Association for Computing Machinery, Inc",
booktitle = "Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB 2022",
}