This paper describes a new system, GLIMMER, for finding genes in micro
bial genomes. In a series of tests on Haemophilus influenzae, Helicoba
cter pylori and other complete microbial genomes, this system has prov
en to be very accurate at locating virtually ail the genes in these se
quences, outperforming previous methods. A conservative estimate based
on experiments on H.pylori and H.influenzae is that the system finds
>97% of all genes, GLIMMER uses Interpolated Markov models (IMMs) as a
framework for capturing dependencies between nearby nucleotides in a
DNA sequence. An IMM-based method makes predictions based on a variabl
e context; i.e., a variable-length oligomer in a DNA sequence, The con
text used by GLIMMER changes depending on the local composition of the
sequence, As a result, GLIMMER is more flexible and more powerful tha
n fixed-order Markov methods, which have previously been the primary c
ontent-based technique for finding genes in microbial DNA.