How to Interpret an Anonymous Bacterial Genome: Machine Learning Approach to Gene Identification

Table 10.

New Atypical Gene Predictions for the 10 Genomes Made by the GeneMark.hmm program

Species name Total No. of GeneMark.hmm new predictions characterized as atypical [corroborated by gapped BLASP search ( P < 1e − 5)]
A. fulgidus 111 25
B. subtilis 86 14
E. coli 135 22
H.influenzae 44 24
H. pylori 16 5
M. genitalium 37 25
M. jannaschii 80 26
M. pneumoniae 20 14
M. thermoautotrophicum 39 4
Synechocystis 115 17
  • The GeneMark.hmm program (Lukashin and Borodovsky 1998) shows typical and atypical models in parallel.

  • Numbers of new predictions, as compared with the GenBank records, are shown along with the numbers of cases when the gene prediction was corroborated by similarity search by gapped BLASTP (Altschul et. al. 1997).

This Article

  1. Genome Res. 8: 1154-1171

Preprint Server