{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dart-eval-a-comprehensive-dna-language-model","title":"DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA","arxiv_id":"2412.05430","date":"2024-12-06","proceeding":null,"authors":["Aman Patel","Arpita Singhal","Austin Wang","Anusri Pampari","Maya Kasowski","Anshul Kundaje"],"abstract":"Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn generalizable representations of diverse DNA elements, potentially enabling various genomic prediction, interpretation and design tasks. Despite their potential, existing benchmarks do not adequately assess the capabilities of DNALMs on key downstream applications involving an important class of non-coding DNA elements critical for regulating gene activity. In this study, we introduce DART-Eval, a suite of representative benchmarks specifically focused on regulatory DNA to evaluate model performance across zero-shot, probed, and fine-tuned scenarios against contemporary ab initio models as baselines. Our benchmarks target biologically meaningful downstream tasks such as functional sequence feature discovery, predicting cell-type specific regulatory activity, and counterfactual prediction of the impacts of genetic variants. We find that current DNALMs exhibit inconsistent performance and do not offer compelling gains over alternative baseline models for most tasks, while requiring significantly more computational resources. We discuss potentially promising modeling, data curation, and evaluation strategies for the next generation of DNALMs. Our code is available at https://github.com/kundajelab/DART-Eval.","url_abs":"https://arxiv.org/abs/2412.05430v1","url_pdf":"https://arxiv.org/pdf/2412.05430v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dart-eval-a-comprehensive-dna-language-model","repo_url":"https://github.com/kundajelab/dart-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-model-evaluation","task_name":"Language Model Evaluation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.05430","atlas_url":"https://app.syntology.ai/?focus=2412.05430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05430"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/kundajelab/DART-Eval","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kundajelab/dart-eval","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":15},"by_repo_kind":{"official":{"samples":16,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":16,"samples":[{"code_sha256_prefix":"853d8aee53d39296","entry":"make_region_df","repo":"kundajelab/DART-Eval","repo_kind":"official","path":"src/dnalm_bench/task_1_paired_control/dataset_generators/encode_ccre.py","file_url":"https://github.com/kundajelab/DART-Eval/blob/HEAD/src/dnalm_bench/task_1_paired_control/dataset_generators/encode_ccre.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"853d8aee53d39296"}},{"code_sha256_prefix":"44434c209290ce5b","entry":"dinucleotide_shuffle","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/utils.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44434c209290ce5b"}},{"code_sha256_prefix":"f8b8d077d64721d3","entry":"evaluate_finetuned_classifier","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_1_paired_control/finetune.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_1_paired_control/finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8b8d077d64721d3"}},{"code_sha256_prefix":"b59c3fbf640d6503","entry":"generate_latex_table_per_cell_type","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_1_paired_control/generate_latex.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_1_paired_control/generate_latex.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b59c3fbf640d6503"}},{"code_sha256_prefix":"8d44605ff38fcc40","entry":"get_accuracies","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d44605ff38fcc40"}},{"code_sha256_prefix":"3f5f87a9d18060a3","entry":"get_confidence_interval","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_1_paired_control/generate_latex.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_1_paired_control/generate_latex.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f5f87a9d18060a3"}},{"code_sha256_prefix":"ba9e7c54f2991e6a","entry":"get_distances","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba9e7c54f2991e6a"}},{"code_sha256_prefix":"129082c04db6596b","entry":"get_likelihoods","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"129082c04db6596b"}},{"code_sha256_prefix":"8dcd29ed5e28d719","entry":"get_pvals","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_likelihoods.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8dcd29ed5e28d719"}},{"code_sha256_prefix":"b05bd25300b743b3","entry":"load_embeddings","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b05bd25300b743b3"}},{"code_sha256_prefix":"ebb6d12a7eaca88b","entry":"load_embeddings_and_labels","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/embedding_clustering.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/embedding_clustering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ebb6d12a7eaca88b"}},{"code_sha256_prefix":"11d6f70d2317495f","entry":"load_embeddings_and_labels_subset","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/embedding_clustering.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/embedding_clustering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"11d6f70d2317495f"}},{"code_sha256_prefix":"a32416b3ff7b6896","entry":"one_hot_encode","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/utils.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a32416b3ff7b6896"}},{"code_sha256_prefix":"75f2134f65415576","entry":"onehot_to_chars","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/utils.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75f2134f65415576"}},{"code_sha256_prefix":"ae9202aca7e7c370","entry":"relate_embeddings_to_motifs","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_2_5_single/experiments/task_2_transcription_factor_binding/footprint_eval_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ae9202aca7e7c370"}},{"code_sha256_prefix":"51187133335595b3","entry":"underline_max_values","repo":"kundajelab/dart-eval","repo_kind":"official","path":"src/dnalm_bench/task_1_paired_control/generate_latex.py","file_url":"https://github.com/kundajelab/dart-eval/blob/HEAD/src/dnalm_bench/task_1_paired_control/generate_latex.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51187133335595b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}