Discover Community Create You

Loading publication...

Noodle always counts identifier-free feature events for service operation. With your permission, Google Analytics can also estimate audience and engagement. Search text, publication identifiers, cookies, IP addresses and browser fingerprints are never included in Noodle's first-party event counters.

Privacy details

Article

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

Nature genetics - 1 Aug 2024

Yun Taedong, Cosentino Justin, Behsaz Babak, McCaw Zachary R, Hill Davin, Luben Robert, Lai Dongbing, Bates John, Yang Howard, Schwantes-An Tae-Hwi, Zhou Yuchen, Khawaja Anthony P, Carroll Andrew, Hobbs Brian D, Cho Michael H, McLean Cory Y, Hormozdiari Farhad

Abstract excerpt

Although high-dimensional clinical data (HDCD) are increasingly available in biobank-scale datasets, their use for genetic discovery remains challenging. Here we introduce an unsupervised deep learning model, Representation Learning for Genetic Discovery on Low-Dimensional Embeddings (REGLE), for discovering associations between genetic variants and HDCD. REGLE leverages variational autoencoders to compute...

Read the complete abstract on PubMed

Topics

Share this publication in a Topic to start or enrich a Post.

Share to Deep Learning
Share to Genetic Predisposition to Disease

Methodology Data sources Editorial policy Privacy Delete account & data About Contact Helena Bioinformatics

Share to Genome-Wide Association Study

Share to Genomics

Share to Multifactorial Inheritance

Share to Polymorphism, Single Nucleotide

Share to Unsupervised Machine Learning

Source

Open in PubMed Open full text

Identifiers

PMID: 38977853
DOI: 10.1038/s41588-024-01831-6
PMCID: PMC11319202

Provenance

PubMed metadata and Literature Corpus relationships. Corpus snapshot updated 7 Sept 2026. Manifest publication-graph-cohort-2026-09-08.1.

Source receipt: pubmed, retrieved 7 Sept 2026.

Related research

Semantic proximity does not establish scientific evidence. Graph snapshot: 2026-09-29.

Research trail→

Click a neighbor to travelStep 1 · 12 closest

Unsupervised representation learning on high-dimensional clinical data improves genomic discovery and prediction.PMID 38977853Read ↗

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

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

Unifying the genetic landscape of common and rare diseases via latent neighborhoodsSemantic proximity Read ↗

EmbedGEM: A framework to evaluate the utility of embeddings for genetic discoverySemantic proximity Read ↗

DROP-DEEP: Dimensionality Reduction for Polygenic Risk Score Using Deep Learning ApproachSemantic proximity Read ↗

Deep representation learning for clustering longitudinal survival data from electronic health recordsSemantic proximity Read ↗

JOINT CLINICAL AND MOLECULAR SUBTYPING OF COPD WITH VARIATIONAL AUTOENCODERSSemantic proximity Read ↗

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

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

Representation Learning of Human Diseases for Indication Expansion and Investment DecisionsSemantic proximity Read ↗

Variational Autoencoder-based Model Improves Polygenic Prediction in Blood Cell TraitsSemantic proximity Read ↗

CLEP: A Hybrid Data- and Knowledge-Driven Framework for Generating Patient RepresentationsSemantic proximity Read ↗

⌁Select a neighboring publication to make it the new centre.