Learning sequence to predict gain- or loss-of-function variants
Abstract
ClearVariant is a deep learning framework designed to predict the functional impact of human genetic variants, with a particular focus on identifying the direction of mutational effects — such as gain-of-function (GOF) and loss-of-function (LOF) mutations. Built on protein language models (PLMs) fine-tuned with human variant data, ClearVariant analyzes full-length mutant and reference protein sequences to achieve state-of-the-art performance on benchmark datasets including ClinVar, HGMD and ProteinGym.
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 5 January 2026
- Language
- EN
- Document type
- Dataset