GeneMark-EP+: eukaryotic gene prediction with self-training in the space of genes and proteins
By Tomás Bruna, Alexandre Lomsadze, Mark Borodovsky. NAR Genomics and Bioinformatics, 2020
478 citations recorded by the source corpus.
Abstract 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.
Subfields: Molecular Biology
View Paper: https://www.semanticscholar.org/paper/e8cad437179ca30f2c6c9426b2c1d57a1513823f
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Molecular Biology
- Mark Borodovsky
- Alexandre Lomsadze
- Tomás Bruna
- Katharina Jasmin Hoff
- Mario Stanke
- L. Gabriel
- Heng Li
- Mark Yandell
Citations in the corpus
- BRAKER3: Fully automated genome annotation using RNA-seq and protein evidence with GeneMark-ETP, AUGUSTUS and TSEBRA (2023, unknown): “Earlier developed BRAKER1 (Hoff et al., 2016) and BRAKER2 (Br˚una et al., 2021) combined Gene-30 Mark and AUGUSTUS to utilize, respectively, a single source of extrinsic evidence, either RNA-seq short reads or homologous proteins.”
- Protein-to-genome alignment with miniprot (2022, background): “, 2021) integrates Spaln2 (Iwata and Gotoh, 2012) and depends on ProtHint (Brůna et al., 2020) which also optionally invokes Spaln2.”
- BRAKER2: automatic eukaryotic genome annotation with GeneMark-EP+ and AUGUSTUS supported by a protein database (2020, methodology): “gtf | perl -ne ’ @t = split(/\t/); $seen{$t[8]} += ($t[4] - $t[3] + 1); if(eof()){ $sum = 0; $c = 0; foreach my $key ( keys %seen ){ $c=$c+1; $sum += $seen{$key}; } print ($sum.”
- TSEBRA: transcript selector for BRAKER (2021, methodology): “BRAKER2 [18] exploits spliced 29 alignments of homologous proteins as a source of extrinsic evidence for genome annotation with 30 GeneMark-EP+ [19] and AUGUSTUS.”