Gene identification in novel eukaryotic genomes by self-training algorithm

By Alexandre Lomsadze, Vardges Ter-Hovhannisyan, Y. Chernoff, Mark Borodovsky. Nucleic Acids Research, 2005

947 citations recorded by the source corpus.

Finding new protein-coding genes is one of the most important goals of eukaryotic genome sequencing projects. However, genomic organization of novel eukaryotic genomes is diverse and ab initio gene finding tools tuned up for previously studied species are rarely suitable for efficacious gene hunting in DNA sequences of a new genome. Gene identification methods based on cDNA and expressed sequence tag (EST) mapping to genomic DNA or those using alignments to closely related genomes rely either on existence of abundant cDNA and EST data and/or availability on reference genomes. Conventional statistical ab initio methods require large training sets of validated genes for estimating gene model parameters. In practice, neither one of these types of data may be available in sufficient amount until rather late stages of the novel genome sequencing. Nevertheless, we have shown that gene finding in eukaryotic genomes could be carried out in parallel with statistical models estimation directly from yet anonymous genomic DNA. The suggested method of parallelization of gene prediction with the model parameters estimation follows the path of the iterative Viterbi training. Rounds of genomic sequence labeling into coding and non-coding regions are followed by the rounds of model parameters estimation. Several dynamically changing restrictions on the possible range of model parameters are added to filter out fluctuations in the initial steps of the algorithm that could redirect the iteration process away from the biologically relevant point in parameter space. Tests on well-studied eukaryotic genomes have shown that the new method performs comparably or better than conventional methods where the supervised model training precedes the gene prediction step. Several novel genomes have been analyzed and biologically interesting findings are discussed. Thus, a self-training algorithm that had been assumed feasible only for prokaryotic genomes has now been developed for ab initio eukaryotic gene identification.

Subfields: Molecular Biology

View Paper: https://www.semanticscholar.org/paper/f5faebc098e4bb94d96e529079f5cc773ac25520

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

Citations in the corpus

Nucleotide diversity and linkage disequilibrium in Populus nigra cinnamyl alcohol dehydrogenase (CAD4) gene (2011, methodology): “com), and confirmed using the gene prediction program GeneMark (Lomsadze et al. 2005), available at http://exon.”
GeneMark-EP+: eukaryotic gene prediction with self-training in the space of genes and proteins (2020, positive): “Prior to the final iteration, we update estimates of the HMM transition probabilities that affect frequencies of genes with given number of introns.”
Gene prediction in novel fungal genomes using an ab initio algorithm with unsupervised training. (2008, methodology): “pombe genome, 12 Mb, is close to the minimum size (10 Mb) required for unsupervised training (Lomsadze et al. 2005).”
The genome of woodland strawberry (Fragaria vesca) (2010, neutral): “Parameters of the ab initio gene finder GeneMark-E”
TSEBRA: transcript selector for BRAKER (2021, methodology): “BRAKER1 uses GeneMark-ET [10–12] together with AUGUSTUS [13–17] and relies on RNA-seq data to support gene finder training and accurate prediction of gene structures.”
Genome Annotation in Plants and Fungi: EuGene as a Model Platform (2008, neutral): “ES [47].”
MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects (2011, positive): “Ab initio gene predictions were produced by the programs SNAP[23] version 2010-07-28, Augustus[24] 2.5.5, and GeneMark-ES[25] 2.3a, using the D. melanogaster , C. elegans , and A. thaliana parameter files pre-packaged with each algorithm (GeneMark parameter files are packaged with the GeneMark.hmm d”
Using native and syntenically mapped cDNA alignments to improve de novo gene finding (2008, background): “Related genomes that have been sequenced, annotated, and aligned to the target genome provide evidence of existence and structure of genes.”
BRAKER3: Fully automated genome annotation using RNA-seq and protein evidence with GeneMark-ETP, AUGUSTUS and TSEBRA (2023, neutral): “Traditional ab initio gene prediction methods rely on computational predictions by statistical models using genome sequence data alone, for example AUGUSTUS (Stanke et al., 2006) and GeneMark-ES (Lomsadze et al., 2005).”
Integration of mapped RNA-Seq reads into automatic training of eukaryotic gene finding algorithm (2014, methodology): “The general training logic of GeneMark-ET is similar to that of GeneMark-ES (5).”