{"doi":"10.1093/nar/gkt1249","title":"Systematic discovery and characterization of regulatory motifs in ENCODE TF binding experiments","abstract":"Recent advances in technology have led to a dramatic increase in the number of available transcription factor ChIP-seq and ChIP-chip data sets. Understanding the motif content of these data sets is an important step in understanding the underlying mechanisms of regulation. Here we provide a systematic motif analysis for 427 human ChIP-seq data sets using motifs curated from the literature and also discovered de novo using five established motif discovery tools. We use a systematic pipeline for calculating motif enrichment in each data set, providing a principled way for choosing between motif variants found in the literature and for flagging potentially problematic data sets. Our analysis confirms the known specificity of 41 of the 56 analyzed factor groups and reveals motifs of potential cofactors. We also use cell type-specific binding to find factors active in specific conditions. The resource we provide is accessible both for browsing a small number of factors and for performing large-scale systematic analyses. We provide motif matrices, instances and enrichments in each of the ENCODE data sets. The motifs discovered here have been used in parallel studies to validate the specificity of antibodies, understand cooperativity between data sets and measure the variation of motif binding across individuals and species.","journal":"Nucleic Acids Research","year":2013,"id":1404,"datarank":8.917117275240916,"base_score":6.26530121273771,"endowment":6.26530121273771,"self_citation_contribution":0.9397951819106567,"citation_network_contribution":7.977322093330259,"self_endowment_contribution":0.9397951819106567,"citer_contribution":7.977322093330259,"corpus_percentile":98.29813568500039,"corpus_rank":221,"citation_count":525,"citer_count":100,"citers_with_citation_signal":100,"citers_with_endowment":100,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.5714,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2013-12-12","fair_score":71.6667,"fair_percentile":84.76821192052981,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":14693,"name":"Sharon L. R. Kardia","orcid":"0000-0002-9853-3379","position":1,"is_corresponding":false},{"id":21276,"name":"Yanxiao Zhang","orcid":"0000-0001-9618-637X","position":0,"is_corresponding":true}],"reference_count":110,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":"24335146","pmcid":"PMC3950668","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":"gold","license":"cc-by-nc","views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":100.0,"fair_a":70.0,"fair_i":50.0,"fair_r":66.6667,"fair_zscore":1.262,"fair_rationale":{"fair_score":71.67,"has_llm":false,"dimensions":{"F":{"name":"Findable","score":100.0,"criteria":[{"key":"f_has_doi","label":"Has a persistent DOI","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"DOI present","rationale":null},{"key":"f_repository_presence","label":"Indexed in repositories / literature DBs","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"datacite=25, pmcid=True, pmid=True","rationale":null},{"key":"f_persistent_ids","label":"Resolvable scholarly identifiers (OpenAlex)","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"OpenAlex id present","rationale":null}]},"A":{"name":"Accessible","score":70.0,"criteria":[{"key":"a_open_access","label":"Open Access / files deposited","kind":"deterministic","weight":1.5,"fraction":0.5,"signal":"files/OA location present but not flagged OA","rationale":null},{"key":"a_retrievable","label":"Free full text retrievable","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"13 OA location(s)","rationale":null}]},"I":{"name":"Interoperable","score":50.0,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"linked_datasets=25, datacite=25","rationale":null},{"key":"i_standard_ids","label":"References data via standard accessions","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"accessions=0, trials=0","rationale":null}]},"R":{"name":"Reusable","score":66.67,"criteria":[{"key":"r_license","label":"Clear, open reuse license","kind":"deterministic","weight":1.5,"fraction":1.0,"signal":"open license (cc-by-nc)","rationale":null},{"key":"r_downloads","label":"Demonstrated reuse (downloads)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"downloads=0","rationale":null},{"key":"r_version","label":"Versioned / maintained","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no version chain","rationale":null},{"key":"r_dataset","label":"Classified as a data resource","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"is_dataset","rationale":null}]}},"suggestions":["Reference data using standard accessions (e.g. GEO, PDB, ClinicalTrials.gov).","Maintain explicit versioning for the dataset.","Make the paper/data Open Access or deposit the files in an open repository."],"model":null,"agent_version":"fair_agent_v3","fulltext_source":"epmc_xml"},"fair_model":null,"fair_agent_version":"fair_agent_v3","fair_fulltext_source":"epmc_xml","fair_has_llm":false,"fair_computed_at":"2026-06-26T20:54:42.958904Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}