Article

Fine-tuning protein language models on human spatial constraint improves variant effect prediction by reducing wild-type sequence bias

2025-10-16

Abstract excerpt

Protein language models (PLMs) achieve state-of-the-art performance in predicting effects of missense variants, yet they do not explicitly consider variation within the human population. Here, we introduce Hu man S patial C onstraint (HuSC), a framework for quantifying intraspecies constraint on missense variants that integrates population-scale human genetic variation with 3D protein structures. We then fine-t...

Topics

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

Identifiers and source

Literature Corpus work: 63870c83-4cfb-57fb-90b9-f834207a134c
DOI: 10.1101/2025.10.15.682722

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Fine-tuning protein language models on human spatial constraint improves variant effect prediction by reducing wild-type sequence biasDOI 10.1101/2025.10.15.682722Read

The 3D mutational constraint on amino acid sites in the human proteome.Semantic proximity Read

Coupling codon and protein constraints decouples drivers of variant pathogenicitySemantic proximity Read

Genome-wide prediction of disease variants with a deep protein language modelSemantic proximity Read

The 3D spatial constraint on 6.1 million amino acid sites in the human proteomeSemantic proximity Read

Genetic constraint at single amino acid resolution improves missense variant prioritisation and gene discoverySemantic proximity Read

A probabilistic graphical model for estimating selection coefficient of nonsynonymous variants from human population sequence dataSemantic proximity Read

The landscape of tolerated genetic variation in humans and primatesSemantic proximity Read

Genetic background shapes AI-predicted variant effectsSemantic proximity Read

Learning sequence to predict gain- or loss-of-function variantsSemantic proximity Read

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

GPN-MSA: an alignment-based DNA language model for genome-wide variant effect predictionSemantic proximity Read

Uncovering differential tolerance to deletions versus substitutions with a protein language modelSemantic proximity Read