@article{mGene,
	author    = {Gabriele Schweikert and Georg Zeller and Alexander Zien and
		Jonas Behr and Cheng Soon Ong and Petra Philips and Anja Bohlen and Nina
			Kr\"uger and S\"oren Sonnenburg and Gunnar R\"atsch},
	journal   = {Genome Research},
	volume = {19},
	number = {11},
	pages = {2133-2143},
	title     = {{mGene}: {A} Novel Discriminative Gene Finding System},
	year      = {2009},
	abstract  = {We present a highly accurate gene prediction system for
	eukaryotic genomes, called mGene. It combines in an unprecedented manner the
	flexibility of generalized hidden Markov models with the predictive power of
	modern machine learning meth- ods, such as Support Vector Machines (SVMs). Its
	excellent performance was proved in an objective competition based on the
	genome of the nematode Caenorhabditis elegans (Coghlan et al., 2008).
	Considering the average of sensitivity and specificity the developmental
	version of mGene exhibited the best prediction performance on nucleotide, exon,
	and transcript level for ab initio and multiple-genome gene pre- diction tasks.
	The fully developed version shows superior performance in ten out of twelve
	evaluation criteria compared to the other participating gene finders, including
	Fgenesh++ (Salamov and Solovyev, 2000) and Augustus (Stanke et al., 2006).  An
	in-depth analysis of mGene's genome-wide predictions revealed that $\approx$ 2, 200
	predicted genes were not contained in the current genome annotation. Testing a
	subset of 57 of these genes by RT-PCR and sequencing, we confirmed expression
	for 24 (42\%) of them. mGene missed 300 annotated genes, out of which 205 were
	unconfirmed. RT-PCR testing of 24 of these genes resulted in a success rate of
	merely 8\%. These findings suggest that even the gene catalog of a well-studied
	organism such as C. elegans can be substantially improved by mGene's
	predictions.  We also provide gene predictions for the four nematodes C.
	briggsae, C. brenneri, C. japonica and C. remanei (Stein et al., 2003;
	Sternberg et al., 2003). Comparing the resulting proteomes among these
	organisms and to the known protein universe, we identified many
	species-specific gene inventions. In a quality assessment of several available
	annotations for these genomes, we find that mGene's predictions are most
	accurate.  Availability: mGene is available as source code under Gnu Public
	License from the project website http://mgene.org and as a Galaxy-based
	webserver at http://mgene.org/web. Moreover, the gene predictions have been
	included in the Worm- base annotation available at http://wormbase.org and
	the project website.},
    url       = {http://www.mgene.org},
	pdf = {http://genome.cshlp.org/content/19/11/2133.full.pdf+html}

}