Article

EmbedGEM: A framework to evaluate the utility of embeddings for genetic discovery

2023-11-25

Abstract excerpt

Machine learning (ML)-derived embeddings are a compressed representation of high content data modalities. Embeddings can capture detailed information about disease states and have been qualitatively shown to be useful in genetic discovery. Despite their promise, embeddings have a major limitation: it is unclear if genetic variants associated with embeddings are relevant to the disease or trait of interest. In this...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 9124ea67-b03a-5aff-bd25-5818e5b01f40
DOI: 10.1101/2023.11.24.568344

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

EmbedGEM: A framework to evaluate the utility of embeddings for genetic discoveryDOI 10.1101/2023.11.24.568344Read

Improving polygenic risk prediction performance through integrating electronic health records by phenotype embeddingSemantic proximity Read

Improving polygenic risk prediction performance by integrating electronic health records through phenotype embedding.Semantic proximity Read

Vector2Variant: Discovery of Genetic Associations from ML Derived Representations without Phenotype EngineeringSemantic proximity Read

Representation learning-based genome-wide association mapping discovers genes underlying complex traits.Semantic proximity Read

EA-PheWAS: Integrating Phenotype Embeddings with PheWAS for Enhanced Gene-Phenotype DiscoverySemantic proximity Read

Unsupervised representation learning on high-dimensional clinical data improves genomic discovery and prediction.Semantic proximity Read

Genetic decoding reveals druggable biology implicitly learned by a medical-history foundation modelSemantic proximity Read

GENPHIRE: Enhancing Disease Risk Prediction Using Large Language ModelSemantic proximity Read

Prioritizing genomic variants through neuro-symbolic, knowledge-enhanced learningSemantic proximity Read

Estimating heritability and genetic correlations from large health datasets in the absence of genetic data.Semantic proximity Read

PERADIGM: Phenotype Embedding Similarity-based Rare Disease Gene MappingSemantic proximity Read

Unsupervised representation learning improves genomic discovery and risk prediction for respiratory and circulatory functions and diseasesSemantic proximity Read