GeneMark-EP+: eukaryotic gene prediction with self-training in the space of genes and proteins

• Published in: NAR genomics and bioinformatics Vol. 2; no. 2; p. lqaa026
• Main Authors: Brůna, Tomáš, Lomsadze, Alexandre, Borodovsky, Mark
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.06.2020
• Subjects: Accuracy; Gene mapping; Genes; Genomes; Methart; Peptide mapping; Predictions
• ISSN: 2631-9268; 2631-9268
• DOI: 10.1093/nargab/lqaa026

We have made several steps toward creating a fast and accurate algorithm for gene prediction in eukaryotic genomes. First, we introduced an automated method for efficient ab initio gene finding, GeneMark-ES, with parameters trained in iterative unsupervised mode. Next, in GeneMark-ET we proposed a method of integration of unsupervised training with information on intron positions revealed by mapping short RNA reads. Now we describe GeneMark-EP, a tool that utilizes another source of external information, a protein database, readily available prior to the start of a sequencing project. A new specialized pipeline, ProtHint, initiates massive protein mapping to genome and extracts hints to splice sites and translation start and stop sites of potential genes. GeneMark-EP uses the hints to improve estimation of model parameters as well as to adjust coordinates of predicted genes if they disagree with the most reliable hints (the -EP+ mode). Tests of GeneMark-EP and -EP+ demonstrated improvements in gene prediction accuracy in comparison with GeneMark-ES, while the GeneMark-EP+ showed higher accuracy than GeneMark-ET. We have observed that the most pronounced improvements in gene prediction accuracy happened in large eukaryotic genomes.