{"doi":"10.1101/2024.02.29.582810","title":"Evaluating the representational power of pre-trained DNA language models for regulatory genomics","abstract":"ABSTRACT 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. Here we evaluate the representational power of pre-trained gLMs to predict and interpret cell-type-specific functional genomics data that span DNA and RNA regulation. Our findings suggest that probing the representations of pre-trained gLMs do not offer substantial advantages over conventional machine learning approaches that use one-hot encoded sequences. This work highlights a major gap with current gLMs, raising potential issues in conventional pre-training strategies for the non-coding genome.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2024,"id":483960,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":26,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9459,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1326110,"name":"Nirali Somia","orcid":null,"position":1,"is_corresponding":false},{"id":1299737,"name":"Yiyang Yu","orcid":"0009-0001-2925-1909","position":2,"is_corresponding":false},{"id":298873,"name":"Peter K. Koo","orcid":"0000-0001-8722-0038","position":3,"is_corresponding":false},{"id":820021,"name":"Ziqi Tang","orcid":"0000-0001-7585-915X","position":0,"is_corresponding":true}],"reference_count":97,"raw_metadata":null,"created_at":"2026-07-19T02:07:38.055693Z","pmid":"38464101","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}