Article

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

2025-05-24

Abstract excerpt

Generative models trained on natural sequences are increasingly used to predict the effects of genetic variation, enabling progress in therapeutic design, disease risk prediction, and synthetic biology. In the zero-shot setting, variant impact is estimated by comparing the likelihoods of sequences, under the assumption that likelihood serves as a proxy for fitness. However, this assumption often breaks down in pra...

Topics

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

Identifiers and source

Literature Corpus work: 7c46c80e-4420-53a7-b4ff-ab8b3767156f
DOI: 10.1101/2025.05.20.655154

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language ModelsDOI 10.1101/2025.05.20.655154Read

Structure-informed protein language models are robust predictors for variant effects.Semantic proximity Read

Evolutionary profiles for protein fitness prediction.Semantic proximity Read

Understanding language model scaling for protein fitness prediction.Semantic proximity Read

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

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

Contrastive Fitness Learning: Reprogramming Protein Language Models for Low- <i>N</i> Learning of Protein Fitness LandscapeSemantic proximity Read

Deep generative models of LDLR protein structure to predict variant pathogenicity.Semantic proximity Read

Benchmarking DNA Foundation Models for zero-shot variant effect prediction: the role of context, training, and architectureSemantic proximity Read

Improving Variant Effect Prediction by Steering Sparse Mechanistic Features in Protein Language ModelsSemantic proximity Read

Expert-guided protein Language Models enable accurate and blazingly fast fitness predictionSemantic proximity Read

Benchmarking DNA Foundation Models for zero-shot variant effect prediction: the role of context, training, and architectureSemantic proximity Read

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