BioinformaticsbioRxivPreprint
Preference-Based Fine-Tuning of Genomic Sequence Models for Personal Expression Prediction with Data Augmentation
Moonwon Choi, Bokeum Cho, Seunggeun Lee
The paper improves gene expression prediction from DNA sequences by fine-tuning genomic models with synthetic data and preference-based objectives, outperforming existing methods on the GEUVADIS dataset.
DOI 10.1101/2025.11.09.687505