Article

Genetic decoding reveals druggable biology implicitly learned by a medical-history foundation model

2026-07-29

Abstract excerpt

<h4>ABSTRACT</h4> Foundation models trained on electronic healthcare records (EHRs) have gained traction with the aim to transform personalised medicine. However, their interpretability is bound to redescribing the records the models were trained on, missing implicitly learned concepts and biases. Here, we show that human genetics provides an orthogonal layer to surface implicitly learned biological concepts and...

Topics

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

Identifiers and source

Literature Corpus work: e76fc5b6-f654-51d4-a3e3-43721cc72df4
DOI: 10.64898/2026.07.28.26359117

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Genetic decoding reveals druggable biology implicitly learned by a medical-history foundation modelDOI 10.64898/2026.07.28.26359117Read

Interpretable variant effect prediction from genomic foundation model representationsSemantic proximity Read

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

Mining hidden knowledge: Embedding models of cause-effect relationships curated from the biomedical literatureSemantic proximity Read

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

Multimodal Data Integration Improves Disease Risk Prediction in the UK Biobank.Semantic proximity Read

A deep learning transformer model predicts high rates of undiagnosed rare disease in large electronic health systemsSemantic proximity Read

Gene-centered representation of coding and regulatory variation enables outcome predictionSemantic proximity Read

OmicFormer: a statistical priors–informed transformer for accurate and generalizable omics prediction of diseases and complex traitsSemantic proximity Read

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

Learning the shared structure of human health across diseases, modalities, and timeSemantic proximity Read

Causal Transformer for Learning Embeddings from Structured Medical History Records and Multi-Source Data Integration for Complex Disease Risk Prediction.Semantic proximity Read

Integrating Genomics into Multimodal EHR Foundation ModelsSemantic proximity Read