PredGPI: a GPI-anchor predictor

TLDR

Several eukaryotic proteins on the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor linked to the C‑terminal residue after proteolytic cleavage at the ω‑site, and more accurate methods are needed for reliable proteome annotation. The study introduces PredGPI, a computational tool that predicts GPI‑anchor presence and ω‑site location from protein sequences. PredGPI combines a Hidden Markov Model and a Support Vector Machine trained on a curated, non‑redundant set of experimentally verified GPI‑anchored proteins. PredGPI outperforms existing methods, achieves lower false‑positive rates, and offers a cost‑effective, rapid, and accurate approach for whole‑proteome screening.

Abstract

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 ω-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 ω-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.