Prediction of solvent accessibility of amino acid residues: critical aspects

For predicting solvent accessibility from the sequence of amino acids in pr oteins, we use a logistic function trained on a non-redundant protein datab ase. Using a principal component analysis, we find that the prediction can be considered, in a good approximation. as a monofactorial problem: a cross ed effect of the burial propensity of amino acids and of their locations at positions flanking the amino acid of interest. Complementary effects depen d on the presence of certain amino acids (mostly P, G and C) at given posit ions. We have refined the predictive model (I) by adding supplementary inpu t data, (2) by using a strategy of prediction correction and (3) by adaptin g the decision rules according to the amino acid type. We obtain a best sco re of 77.6% correct prediction for a relative accessibility of 9%. However, compared to trivial strategy only based upon the frequencies of buried or exposed residues, the gain is less than 4%.