Multiple linear regression for protein secondary structure prediction

In the present work, a novel method was proposed for prediction of secondar y structure. Over a database of 396 proteins (CB396) with a three-state-def ining secondary structure, this method with jackknife procedure achieved an accuracy of 68.8% and SOV score of 71.4% using single sequence and an accu racy of 73.7% and SOV score of 77.3% using multiple sequence alignments. Co mbination of this method with DSC, PHD, PREDATOR, and NNSSP gives Q(3) = 76 .2% and SOV = 79.8%. (C) 2001 Wiley-Liss, Inc.