Article

VariantFormer: A hierarchical transformer integrating DNA sequences with genetic variations and regulatory landscapes for personalized gene expression prediction

2025-11-02

Abstract excerpt

1 Accurately predicting gene expression from DNA sequence remains a central challenge in human genetics. Current sequence-based models overlook natural genetic variation across individuals, while population-based models are restricted to variants observed within specific cohorts. Here, we present VariantFormer, a 1.2-billion-parameter transformer that predicts gene-level RNA abundance directly from personalized di...

Topics

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

Identifiers and source

Literature Corpus work: d7eaada9-cde2-51a8-a821-0b8da55f1da8
DOI: 10.1101/2025.10.31.685862

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

VariantFormer: A hierarchical transformer integrating DNA sequences with genetic variations and regulatory landscapes for personalized gene expression predictionDOI 10.1101/2025.10.31.685862Read

The EN-TEx resource of multi-tissue personal epigenomes & variant-impact models.Semantic proximity Read

AlphaGenome: advancing regulatory variant effect prediction with a unified DNA sequence modelSemantic proximity Read

Advancing regulatory variant effect prediction with AlphaGenome.Semantic proximity Read

An Enhanced Variant-Aware Deep Learning Model for Individual Gene Expression PredictionSemantic proximity Read

Predicting the regulatory impacts of noncoding variants on gene expression through epigenomic integration across tissues and single-cell landscapes.Semantic proximity Read

Single-cell gene expression prediction from DNA sequence at large contextsSemantic proximity Read

A sequence-based global map of regulatory activity for deciphering human geneticsSemantic proximity Read

Genetic background shapes AI-predicted variant effectsSemantic proximity Read

gRely: Relyability for genome trained sequence-to-expression modelsSemantic proximity Read

Enhancing personalized gene expression prediction from DNA sequences using genomic foundation models.Semantic proximity Read

BioToken and BioFM – Biologically-Informed Tokenization Enables Accurate and Efficient Genomic Foundation ModelsSemantic proximity Read

Transcriptomic signatures across human tissues identify functional rare genetic variation.Semantic proximity Read