Gene prediction in novel fungal genomes using an ab initio algorithm with unsupervised training.

By Vardges Ter-Hovhannisyan, Alexandre Lomsadze, Y. Chernoff, Mark Borodovsky. Genome Research, 2008

894 citations recorded by the source corpus.

We describe a new ab initio algorithm, GeneMark-ES version 2, that identifies protein-coding genes in fungal genomes. The algorithm does not require a predetermined training set to estimate parameters of the underlying hidden Markov model (HMM). Instead, the anonymous genomic sequence in question is used as an input for iterative unsupervised training. The algorithm extends our previously developed method tested on genomes of Arabidopsis thaliana, Caenorhabditis elegans, and Drosophila melanogaster. To better reflect features of fungal gene organization, we enhanced the intron submodel to accommodate sequences with and without branch point sites. This design enables the algorithm to work equally well for species with the kinds of variations in splicing mechanisms seen in the fungal phyla Ascomycota, Basidiomycota, and Zygomycota. Upon self-training, the intron submodel switches on in several steps to reach its full complexity. We demonstrate that the algorithm accuracy, both at the exon and the whole gene level, is favorably compared to the accuracy of gene finders that employ supervised training. Application of the new method to known fungal genomes indicates substantial improvement over existing annotations. By eliminating the effort necessary to build comprehensive training sets, the new algorithm can streamline and accelerate the process of annotation in a large number of fungal genome sequencing projects.

Subfields: Genetics, Molecular Biology, Plant Science

View Paper: https://www.semanticscholar.org/paper/325c3d37434ccec5c6eefcc2dfffaad188c65ac7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

In Molecular Biology

In Plant Science

Citations in the corpus

Genome Sequencing and Comparative Transcriptomics of the Model Entomopathogenic Fungi Metarhizium anisopliae and M. acridum (2011, methodology): “An ab initio predictor, GeneMark [112] was additionally used for ORF prediction with both Metarhizium genomes.”
MycoCosm portal: gearing up for 1000 fungal genomes (2013, background): “The ab initio Fgenesh (9) and GeneMark (10) are speciﬁcally trained for the given genome.”
Integration of mapped RNA-Seq reads into automatic training of eukaryotic gene finding algorithm (2014, background): “Also, parameters of the branch point site model, especially important for fungal genomes, are not defined until one of the later iterations (6).”
WormBase 2016: expanding to enable helminth genomic research (2015, methodology): “For the remaining genomes, we used MAKER2 (11) to generate high-quality annotations by integrating evidence from multiple sources: ab initio gene predictions from AUGUSTUS (12), GeneMarkES (13) and SNAP (14); projected annotations from C. elegans and the taxonomically nearest previously-annotated he”
Genome of an arbuscular mycorrhizal fungus provides insight into the oldest plant symbiosis (2013, methodology): “Like obligate biotrophic pathogens (20) and ectomycorrhizal symbionts (21, 24), R.”
GeneMark-EP+: eukaryotic gene prediction with self-training in the space of genes and proteins (2020, neutral): “For N. crassa , use of protein evidence never led to noticeable improvement over GeneMark-ES whose high accuracy for fungal genomes was demonstrated earlier as well (21).”
A beginner's guide to eukaryotic genome annotation (2012, methodology): “An alternative is to use GeneMark-ES 68,69 : a self-training, but sometimes less-accurate, algorithm 69,70 .”