augustus

AUGUSTUS is a software for gene prediction in eukaryotic genomic sequences that is based on a generalized hidden Markov model (HMM), a probabilistic model of a sequence and its gene structure. After learning gene structures from a reference annotation, AUGUSTUS uses the HMM to recognize genes in a new sequence and annotates it with the regions of identified genes. External hints, e.g. from RNA sequencing, EST or protein alignments etc. can be used to guide and improve the gene finding process. The result is the set of most likely gene structures that comply with all given user constraints, if such gene structures exist. AUGUSTUS already includes prebuilt HMMs for many species, as well as scripts to train custom models using annotated genomes.