Prediction of contact numbers of amino acid residues using a neural network regression algorithm |
| |
Authors: | Afonnikov D A Morozov A V Kolchanov N A |
| |
Institution: | 1.Institute of Cytology and Genetics, Siberian Branch, Russian Academy of Sciences, ul. akademika Lavrent’eva 10, Novosibirsk, 630090, Russia ;2.Novosibirsk State University, ul. Pirogova 2, Novosibirsk, 630090, Russia ; |
| |
Abstract: | The profile of contact numbers of amino acid residues in proteins contains important information about the protein structure and is connected with the accessibility of residues to solvent. Here we propose a method for predicting the profile of contact numbers of residues in protein from its amino acid sequence. The method is based on regression using a neural network algorithm. The algorithm predicts two types of profiles, namely, the total number of contacts and the number of close contacts with the neighbors in the chain. The Pearson coefficient of correlation between the actual and predicted values of total contact numbers amounted to 0.526–0.703. As for the number of close contacts, this coefficient was higher (0.662–0.743) for all the considered threshold contact distances (6, 8, 10, and 12 Å). The program for prediction of contact numbers CONNP is available at http://wwwmgs2.bionet.nsc.ru/reloaded. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|