AUGUSTUS: ab initio prediction of alternative transcripts

Abstract

AUGUSTUS is a software tool for gene prediction in eukaryotes based on a Generalized Hidden Markov Model, a probabilistic model of a sequence and its gene structure. Like most existing gene finders, the first version of AUGUSTUS returned one transcript per predicted gene and ignored the phenomenon of alternative splicing. Herein, we present a WWW server for an extended version of AUGUSTUS that is able to predict multiple splice variants. To our knowledge, this is the first ab initio gene finder that can predict multiple transcripts. In addition, we offer a motif searching facility, where user-defined regular expressions can be searched against putative proteins encoded by the predicted genes. The AUGUSTUS web interface and the downloadable open-source stand-alone program are freely available from http://augustus.gobics.de.

Figure 1

The human gene ATP5G1 and the AUGUSTUS ab initio prediction for this region. The first transcript (g1.t1) is also the one predicted by standard AUGUSTUS using the Viterbi algorithm only. It misses the second exon of the gene. The second transcript (g1.t2) contains that exon and is correct. The height of a box (black: exon, light gray: intron) reflects the posterior probability of that exon or intron: The higher the posterior probability, the higher the box.

Figure 2

Region of a human gene on the forward strand for which AUGUSTUS predicted six transcripts (gene SON, chromosome 21, 33 837 000–33 872 000, ncbi build 35). The long intron of transcript g1.t3 containing position 20 000 has low posterior probability. Thus, the model is unsure whether this is actually one gene, two or three genes. In fact, for this gene there exists EST evidence both for the short transcript g1.t1 and for longer transcripts with exons mostly agreeing with those predicted above.