MITOPRED: a genome-scale method for prediction of nucleus-encoded mitochondrial proteins

Bioinformatics. 2004 Jul 22;20(11):1785-94. doi: 10.1093/bioinformatics/bth171. Epub 2004 Mar 22.


Motivation: Currently available methods for the prediction of subcellular location of mitochondrial proteins rely largely on the presence of mitochondrial targeting signals in the protein sequences. However, a large fraction of mitochondrial proteins lack such signals, making those tools ineffective for genome-scale prediction of mitochondria-targeted proteins. Here, we propose a method for genome-scale prediction of nucleus-encoded mitochondrial proteins. The new method, MITOPRED, is based on the Pfam domain occurrence patterns and the amino acid compositional differences between mitochondrial and non-mitochondrial proteins.

Results: MITOPRED could predict mitochondrial proteins with 100% specificity at a 44% sensitivity rate and with 67% specificity at 99% sensitivity. Additionally, it was sufficiently robust to predict mitochondrial proteins across different eukaryotic species with similar accuracy. Based on Matthews correlation coefficient measure, the prediction performance of MITOPRED is clearly superior (0.73) to those of the two popular methods TargetP (0.51) and PSORT (0.53). Using this method, we predicted the nucleus-encoded mitochondrial proteins from six complete genomes (three invertebrate, two vertebrate and one plant species) and estimated the total number in each genome. In human, our method estimated the existence of 1362 mitochondrial proteins corresponding to 4.8% of the total proteome.

Availability: MITOPRED program is freely accessible at Source code is available on request from the authors.

Supplementary information: Training data sets are also available at

Publication types

  • Comparative Study
  • Evaluation Study
  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Algorithms*
  • Animals
  • Cell Nucleus / chemistry
  • Cell Nucleus / metabolism*
  • Gene Expression Profiling / methods*
  • Genome
  • Humans
  • Mitochondrial Proteins / chemistry
  • Mitochondrial Proteins / metabolism*
  • Proteome / chemistry
  • Proteome / metabolism
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Sequence Alignment / methods*
  • Sequence Analysis, Protein / methods*
  • Software*
  • Tissue Distribution


  • Mitochondrial Proteins
  • Proteome