Prediction of lipoprotein signal peptides in Gram-positive bacteria with a Hidden Markov Model

J Proteome Res. 2008 Dec;7(12):5082-93. doi: 10.1021/pr800162c.


We present a Hidden Markov Model method for the prediction of lipoprotein signal peptides of Gram-positive bacteria, trained on a set of 67 experimentally verified lipoproteins. The method outperforms LipoP and the methods based on regular expression patterns, in various data sets containing experimentally characterized lipoproteins, secretory proteins, proteins with an N-terminal TM segment and cytoplasmic proteins. The method is also very sensitive and specific in the detection of secretory signal peptides and in terms of overall accuracy outperforms even SignalP, which is the top-scoring method for the prediction of signal peptides. PRED-LIPO is freely available at, and we anticipate that it will be a valuable tool for the experimentalists studying secreted proteins and lipoproteins from Gram-positive bacteria.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Amino Acid Sequence
  • Bacterial Proteins / chemistry*
  • Computational Biology / methods*
  • Cytoplasm / metabolism
  • Databases, Protein
  • Gram-Positive Bacteria / metabolism*
  • Lipoproteins / chemistry*
  • Markov Chains
  • Molecular Sequence Data
  • Protein Sorting Signals
  • Protein Structure, Tertiary
  • Reproducibility of Results
  • Software


  • Bacterial Proteins
  • Lipoproteins
  • Protein Sorting Signals