Article

Interpretable variant effect prediction from genomic foundation model representations

2026-04-11

Abstract excerpt

Scientific foundation models learn high-dimensional representations from diverse data modalities, yet what they encode and how to extract that knowledge remain open questions. Here we show that probing the internal representations of Evo 2, a 7-billion-parameter genomic foundation model, enables accurate and interpretable genetic variant effect prediction. We introduce a covariance-based probe that captures second...

Topics

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

Identifiers and source

Literature Corpus work: 970edee1-5e62-511c-abf5-7fbf138fa2cf
DOI: 10.64898/2026.04.10.717844

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Interpretable variant effect prediction from genomic foundation model representationsDOI 10.64898/2026.04.10.717844Read

Semantic embedding of variant effect annotations enables rapid and accurate pathogenicity prediction with VUS.Life.Semantic proximity Read

MAGI: Mechanistic Consequences of Genetic Variants via Genomic Foundation ModelsSemantic proximity Read

VUS. Life: Leveraging Vector Embeddings for Rapid and Accurate Pathogenicity Prediction of Genetic VariantsSemantic proximity Read

Predicting Genetic Variant Pathogenicity Using Vector EmbeddingsSemantic proximity Read

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

The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human GenomicsSemantic proximity Read

The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human GenomicsSemantic proximity Read

DITTO: An explainable machine-learning model for transcript- specific variant pathogenicity predictionSemantic proximity Read

Disease variant prediction with deep generative models of evolutionary data.Semantic proximity Read

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

Large-scale clinical interpretation of genetic variants using evolutionary data and deep learningSemantic proximity Read

Benchmarking DNA Foundation Models for Genomic and Genetic TasksSemantic proximity Read