{"doi":"10.1101/gr.278373.123","title":"GeneMark-ETP significantly improves the accuracy of automatic annotation of large eukaryotic genomes","abstract":"Large-scale genomic initiatives, such as the Earth BioGenome Project, require efficient methods for eukaryotic genome annotation. Here we present an automatic gene finder, GeneMark-ETP, integrating genomic-, transcriptomic-, and protein-derived evidence that has been developed with a focus on large plant and animal genomes. GeneMark-ETP first identifies genomic loci where extrinsic data are sufficient for making gene predictions with \"high confidence.\" The genes situated in the genomic space between the high-confidence genes are predicted in the next stage. The set of high-confidence genes serves as an initial training set for the statistical model. Further on, the model parameters are iteratively updated in the rounds of gene prediction and parameter re-estimation. Upon reaching convergence, GeneMark-ETP makes the final predictions and delivers the whole complement of predicted genes. GeneMark-ETP outperforms gene finders using a single type of extrinsic evidence. Comparisons with gene finders MAKER2 and TSEBRA, those that use both transcript- and protein-derived extrinsic evidence, show that GeneMark-ETP delivers state-of-the-art gene-prediction accuracy, with the margin of outperforming existing approaches increasing in its application to larger and more complex eukaryotic genomes.","journal":"Genome Research","year":2024,"id":483859,"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":142,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9474,"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":17119,"name":"Alexandre Lomsadze","orcid":null,"position":1,"is_corresponding":false},{"id":17120,"name":"Mark Borodovsky","orcid":"0000-0002-1401-4046","position":2,"is_corresponding":false},{"id":110466,"name":"Tomáš Brůna","orcid":"0000-0001-9811-5532","position":0,"is_corresponding":true}],"reference_count":44,"raw_metadata":null,"created_at":"2026-07-19T02:07:33.718973Z","pmid":"38866548","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":[]}