We have developed a neural network based method (ChloroP) for identifying
chloroplast transit peptides and their cleavage sites. The ChloroP
predictor is available as a web-server at
http://www.cbs.dtu.dk/services/ChloroP/, where both single sequences and
local files in fasta format can be submitted.
Using cross-validation, 88% of the sequences in our homology reduced
training set were correctly classified by the ChloroP predictor as transit
peptides or non-transit peptides. This performance level is well above
that of the so far only publicly available chloroplast localization
predictor, which is part of the PSORT protein prediction system. Cleavage
sites are predicted using a scoring matrix derived by an automatic
motif-finding algorithm. Approximately 60% of the known cleavage sites in
our sequence collection were predicted to within +- 2 residues from the
cleavage sites given in SWISS-PROT. The ChloroP method should be useful
for the identification of putative transit peptides in genome-wide
sequence data.
If you use ChloroP in your research, please cite:
Olof Emanuelsson (1), Henrik Nielsen (1) (2), and Gunnar von Heijne (1)
"ChloroP, a neural network-based method for predicting chloroplast transit
peptides and their cleavage sites", submitted.
(1) Department of Biochemistry, Stockholm University, Stockholm, Sweden
(2) Center for Biological Sequence Analysis, The Technical University of
Denmark, Lyngby, Denmark
E-mail:
Olof Emanuelsson: olof at cbs.dtu.dk
Henrik Nielsen: hnielsen at cbs.dtu.dk
Gunnar von Heijne: gunnar at biokemi.su.se
