Evaluating the representational power of pre-trained DNA language models for regulatory genomics.

ABSTRACT:

Background

The emergence of genomic language models (gLMs) offers an unsupervised approach to learning a wide diversity of cis-regulatory patterns in the non-coding genome without requiring labels of functional activity generated by wet-lab experiments. Previous evaluations have shown that pre-trained gLMs can be leveraged to improve predictive performance across a broad range of regulatory genomics tasks, albeit using relatively simple benchmark datasets and baseline models. Since the gLMs in these studies were tested upon fine-tuning their weights for each downstream task, determining whether gLM representations embody a foundational understanding of cis-regulatory biology remains an open question.

Results

Here, we evaluate the representational power of pre-trained gLMs to

SUBMITTER: Tang Z 

PROVIDER: S-EPMC12261763 | biostudies-literature | 2025 Jul

REPOSITORIES: biostudies-literature