Parameter-efficient fine-tuning enables scalable transfer of regulatory sequence models to novel contexts.

ABSTRACT:

Background

DNA sequence deep learning models can accurately predict epigenetic and transcriptional profiles, enabling analysis of gene regulation and genetic variant effects. While large-scale models like Enformer and Borzoi are trained on abundant data, they cannot cover all cell states and assays, necessitating training new model to analyze gene regulation in novel contexts. However, training models from scratch for new datasets is computationally expensive.

Results

In this study, we systematically develop and evaluate a transfer learning framework based on parameter-efficient fine-tuning for supervised regulatory sequence models. Using the state-of-the-art model Borzoi, our framework enables accurate model transfer while significantly reducing runtime and memory requireme

SUBMITTER: Yuan H 

PROVIDER: S-EPMC12930932 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature