Limits...
PredGPI: a GPI-anchor predictor.

Pierleoni A, Martelli PL, Casadio R - BMC Bioinformatics (2008)

Bottom Line: Several eukaryotic proteins associated to the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor, which is linked to the C-terminal residue after a proteolytic cleavage occurring at the so called omega-site.PredGPI outperforms all the other previously described methods and is able to correctly replicate the results of previously published high-throughput experiments.PredGPI reaches a lower rate of false positive predictions with respect to other available methods and it is therefore a costless, rapid and accurate method for screening whole proteomes.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biocomputing Group, Department of Biology, University of Bologna, Via Irnerio 42, 40126 Bologna, Italy. andrea@biocomp.unibo.it

ABSTRACT

Background: Several eukaryotic proteins associated to the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor, which is linked to the C-terminal residue after a proteolytic cleavage occurring at the so called omega-site. Computational methods were developed to discriminate proteins that undergo this post-translational modification starting from their aminoacidic sequences. However more accurate methods are needed for a reliable annotation of whole proteomes.

Results: Here we present PredGPI, a prediction method that, by coupling a Hidden Markov Model (HMM) and a Support Vector Machine (SVM), is able to efficiently predict both the presence of the GPI-anchor and the position of the omega-site. PredGPI is trained on a non-redundant dataset of experimentally characterized GPI-anchored proteins whose annotation was carefully checked in the literature.

Conclusion: PredGPI outperforms all the other previously described methods and is able to correctly replicate the results of previously published high-throughput experiments. PredGPI reaches a lower rate of false positive predictions with respect to other available methods and it is therefore a costless, rapid and accurate method for screening whole proteomes.

Show MeSH
The ROC curve of PredGPI. The ROC curve of PredGPI is shown as a continuous line. The dashed line is referred to a random guess. Two points are shown over the ROC curve: the circle indicates a false positive rate of 0.15%, while the triangle indicates a false positive rate of 0.5%. The curve was computed using the 145 positive examples and the 10,630 negative examples in GPI-Set and Non-GPI-Set, respectively. See text for details in the Methods section.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2571997&req=5

Figure 2: The ROC curve of PredGPI. The ROC curve of PredGPI is shown as a continuous line. The dashed line is referred to a random guess. Two points are shown over the ROC curve: the circle indicates a false positive rate of 0.15%, while the triangle indicates a false positive rate of 0.5%. The curve was computed using the 145 positive examples and the 10,630 negative examples in GPI-Set and Non-GPI-Set, respectively. See text for details in the Methods section.

Mentions: The performances of the discrimination of the GPI-anchored proteins were computed with a complete jack-knife procedure, and are described by the ROC curve depicted in Figure 2: the Coverage is plotted versus the rate of false positives when varying the discrimination threshold, which is the distance from the separating hyperplane. It is evident that the performance of the method is very different from that of a random guess, which would give origin to a linear plot on the main diagonal line.


PredGPI: a GPI-anchor predictor.

Pierleoni A, Martelli PL, Casadio R - BMC Bioinformatics (2008)

The ROC curve of PredGPI. The ROC curve of PredGPI is shown as a continuous line. The dashed line is referred to a random guess. Two points are shown over the ROC curve: the circle indicates a false positive rate of 0.15%, while the triangle indicates a false positive rate of 0.5%. The curve was computed using the 145 positive examples and the 10,630 negative examples in GPI-Set and Non-GPI-Set, respectively. See text for details in the Methods section.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2571997&req=5

Figure 2: The ROC curve of PredGPI. The ROC curve of PredGPI is shown as a continuous line. The dashed line is referred to a random guess. Two points are shown over the ROC curve: the circle indicates a false positive rate of 0.15%, while the triangle indicates a false positive rate of 0.5%. The curve was computed using the 145 positive examples and the 10,630 negative examples in GPI-Set and Non-GPI-Set, respectively. See text for details in the Methods section.
Mentions: The performances of the discrimination of the GPI-anchored proteins were computed with a complete jack-knife procedure, and are described by the ROC curve depicted in Figure 2: the Coverage is plotted versus the rate of false positives when varying the discrimination threshold, which is the distance from the separating hyperplane. It is evident that the performance of the method is very different from that of a random guess, which would give origin to a linear plot on the main diagonal line.

Bottom Line: Several eukaryotic proteins associated to the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor, which is linked to the C-terminal residue after a proteolytic cleavage occurring at the so called omega-site.PredGPI outperforms all the other previously described methods and is able to correctly replicate the results of previously published high-throughput experiments.PredGPI reaches a lower rate of false positive predictions with respect to other available methods and it is therefore a costless, rapid and accurate method for screening whole proteomes.

View Article: PubMed Central - HTML - PubMed

Affiliation: Biocomputing Group, Department of Biology, University of Bologna, Via Irnerio 42, 40126 Bologna, Italy. andrea@biocomp.unibo.it

ABSTRACT

Background: Several eukaryotic proteins associated to the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor, which is linked to the C-terminal residue after a proteolytic cleavage occurring at the so called omega-site. Computational methods were developed to discriminate proteins that undergo this post-translational modification starting from their aminoacidic sequences. However more accurate methods are needed for a reliable annotation of whole proteomes.

Results: Here we present PredGPI, a prediction method that, by coupling a Hidden Markov Model (HMM) and a Support Vector Machine (SVM), is able to efficiently predict both the presence of the GPI-anchor and the position of the omega-site. PredGPI is trained on a non-redundant dataset of experimentally characterized GPI-anchored proteins whose annotation was carefully checked in the literature.

Conclusion: PredGPI outperforms all the other previously described methods and is able to correctly replicate the results of previously published high-throughput experiments. PredGPI reaches a lower rate of false positive predictions with respect to other available methods and it is therefore a costless, rapid and accurate method for screening whole proteomes.

Show MeSH