Work

Leveraging protein language models and a scoring function for indel characterization and transfer learning

Year: 2025

Type: article

Abstract: Protein language models (PLMs) are increasingly used to assess the impact of genetic variants, achieving high accuracy and often outperforming traditional pathogenicity predictors. They enable zero-shot inference, making predictions without task-specific fine-tuning, though studying in-frame insertions and deletions (indels) remains challenging due to altered protein lengths and limited annotated datasets. Here, we present IndeLLM, a scoring approach for indel pathogenicity that accounts for sequence length differences. Our zero-shot method relies solely on sequence information, requires minimal computing resources, and achieves performance comparable to existing predictors. Building on this, we developed a Siamese network via transfer learning that outperformed all tested indel predictors (Matthews correlation coefficient = 0.77). To enhance accessibility, we provide a plug-and-play Google Colab notebook for using IndeLLM and visualizing the impact of indels on protein sequence and structure. The tool is freely available on GitHub and Google Colab.

Source: Patterns

DOI: 10.1016/j.patter.2025.101425

Authors: Oriol Gracia Carmona, Vilde Leipart, Gro V. Amdam, Christine Orengo, Franca Fraternali