ab_phd_htm

Prediction of helical transmembrane segments at 95% accuracy

Rost, Burkhard; Casadio, Rita; Fariselli, Piero & Sander, Chris

1995, Protein Science, 4, 521-533.

Abstract

We describe a neural network system that predicts the locations of helical transmembrane segments in integral membrane proteins. The prediction method significantly improves on a previous system by using evolutionary information as input to the network system. The following input data is derived from multiple alignments for each position in a window of 13 adjacent residues: amino acid frequency, conservation weights, number of insertions and deletions, and position of the window with respect to N- and C-terminal ends of the protein. As additional input the amino acid composition and length of the protein are used.

A rigorous cross-validation test on 69 proteins with experimentally determined locations of the transmembrane segments yields an overall two-state per-residue accuracy of 95%. About 94% of all segments are predicted correctly. When applied to known globular proteins as a negative control, the network system incorrectly classifies fewer than 4% of the globular proteins as helical transmembrane proteins.