ab_phd_asi95

Progress of 1D protein structure prediction at last

Rost, Burkhard & Sander, Chris

Proteins, 1995, 23, 295-300.

Abstract

Accuracy of predicting secondary structure and accessibility has been improved significantly by using information contained in multiple sequence alignments as input to neural network systems (PHD). For the Asilomar meeting, predictions for 13 proteins were generated automatically by the publicly available prediction method PHD. The results confirm the published estimation for the performance of PHD. The fairly accurate predictions make the tool become useful as a starting point for modelling.