@article{Brůna01052024,
author = {Brůna, Tomáš and Lomsadze, Alexandre and Borodovsky, Mark}, 
title = {GeneMark-ETP significantly improves the accuracy of automatic annotation of large eukaryotic genomes},
volume = {34}, 
number = {5}, 
pages = {757-768}, 
year = {2024}, 
doi = {10.1101/gr.278373.123}, 
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.}, 
URL = {http://genome.cshlp.org/content/34/5/757.abstract}, 
eprint = {http://genome.cshlp.org/content/34/5/757.full.pdf+html}, 
journal = {Genome Research} 
}