@article{open167,
          volume = {61},
          number = {2},
           month = {November},
          author = {Aarti Garg and Harpreet Kaur and G.P.S. Raghava},
            note = {Copyright of this article belongs to Wiley},
           title = {Real value prediction of solvent accessibility in proteins using multiple sequence alignment and secondary structure.},
       publisher = {Wiley},
            year = {2005},
         journal = {Proteins},
           pages = {318--24},
        keywords = {solvent accessibility; prediction; real value;
neural network; multiple alignment;
secondary structure},
             url = {http://crdd.osdd.net/open/167/},
        abstract = {The present study is an attempt to develop a neural network-based method for predicting the real value of solvent accessibility from the sequence using evolutionary information in the form of multiple sequence alignment. In this method, two feed-forward networks with a single hidden layer have been trained with standard back-propagation as a learning algorithm. The Pearson's correlation coefficient increases from 0.53 to 0.63, and mean absolute error decreases from 18.2 to 16\% when multiple-sequence alignment obtained from PSI-BLAST is used as input instead of a single sequence. The performance of the method further improves from a correlation coefficient of 0.63 to 0.67 when secondary structure information predicted by PSIPRED is incorporated in the prediction. The final network yields a mean absolute error value of 15.2\% between the experimental and predicted values, when tested on two different nonhomologous and nonredundant datasets of varying sizes. The method consists of two steps: (1) in the first step, a sequence-to-structure network is trained with the multiple alignment profiles in the form of PSI-BLAST-generated position-specific scoring matrices, and (2) in the second step, the output obtained from the first network and PSIPRED-predicted secondary structure information is used as an input to the second structure-to-structure network. Based on the present study, a server SARpred (http://www.imtech.res.in/raghava/sarpred/) has been developed that predicts the real value of solvent accessibility of residues for a given protein sequence. We have also evaluated the performance of SARpred on 47 proteins used in CASP6 and achieved a correlation coefficient of 0.68 and a MAE of 15.9\% between predicted and observed values.}
}