Fitness translocation: improving variant effect prediction with biologically-grounded data augmentation.

Abstract excerpt

MOTIVATION: Data scarcity limits the characterization of protein fitness landscapes and the development of accurate variant effect prediction models. To address this challenge, we introduce fitness translocation, a data augmentation strategy that generates synthetic variants for a target protein by leveraging variant fitness data previously measured in homologous proteins. Using embeddings from protein language...

Topics

Share this publication in a Topic to start or enrich a Post.

• Share to Computational Biology
• Share to Genetic Variation