NETASA: neural network based prediction of solvent accessibility
Motivation: Prediction of the tertiary structure of a protein from its amino acid sequence is one of the most important problems in molecular biology. The successful prediction of solvent accessibility will be very helpful to achieve this goal. In the present work, we have implemented a server, NETA...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Oxford University Press
2002
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/40060/ http://psasir.upm.edu.my/id/eprint/40060/1/NETASA.pdf http://psasir.upm.edu.my/id/eprint/40060/7/bioinformatics_18_6_819.pdf |
| _version_ | 1848849318425919488 |
|---|---|
| author | Ahmad, Shandar Gromiha, M. Michael |
| author_facet | Ahmad, Shandar Gromiha, M. Michael |
| author_sort | Ahmad, Shandar |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Motivation: Prediction of the tertiary structure of a protein from its amino acid sequence is one of the most important problems in molecular biology. The successful prediction of solvent accessibility will be very helpful to achieve this goal. In the present work, we have implemented a server, NETASA for predicting solvent accessibility of amino acids using our newly optimized neural network algorithm. Several new features in the neural network architecture and training method have been introduced, and the network learns faster to provide accuracy values, which are comparable or better than other methods of ASA prediction. Results: Prediction in two and three state classification systems with several thresholds are provided. Our prediction method achieved the accuracy level upto 90% for training and 88% for test data sets. Three state prediction results provide a maximum 65% accuracy for training and 63% for the test data. Applicability of neural networks for ASA prediction has been confirmed with a larger data set and wider range of state thresholds. Salient differences between a linear and exponential network for ASA prediction have been analysed. |
| first_indexed | 2025-11-15T09:48:29Z |
| format | Article |
| id | upm-40060 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-15T09:48:29Z |
| publishDate | 2002 |
| publisher | Oxford University Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-400602024-07-24T07:26:35Z http://psasir.upm.edu.my/id/eprint/40060/ NETASA: neural network based prediction of solvent accessibility Ahmad, Shandar Gromiha, M. Michael Motivation: Prediction of the tertiary structure of a protein from its amino acid sequence is one of the most important problems in molecular biology. The successful prediction of solvent accessibility will be very helpful to achieve this goal. In the present work, we have implemented a server, NETASA for predicting solvent accessibility of amino acids using our newly optimized neural network algorithm. Several new features in the neural network architecture and training method have been introduced, and the network learns faster to provide accuracy values, which are comparable or better than other methods of ASA prediction. Results: Prediction in two and three state classification systems with several thresholds are provided. Our prediction method achieved the accuracy level upto 90% for training and 88% for test data sets. Three state prediction results provide a maximum 65% accuracy for training and 63% for the test data. Applicability of neural networks for ASA prediction has been confirmed with a larger data set and wider range of state thresholds. Salient differences between a linear and exponential network for ASA prediction have been analysed. Oxford University Press 2002 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/40060/1/NETASA.pdf text en http://psasir.upm.edu.my/id/eprint/40060/7/bioinformatics_18_6_819.pdf Ahmad, Shandar and Gromiha, M. Michael (2002) NETASA: neural network based prediction of solvent accessibility. Bioinformatics, 18 (6). pp. 819-824. ISSN 1367-4803; ESSN: 1367-4811 http://bioinformatics.oxfordjournals.org/content/18/6/819.abstract 10.1093/bioinformatics/18.6.819 |
| spellingShingle | Ahmad, Shandar Gromiha, M. Michael NETASA: neural network based prediction of solvent accessibility |
| title | NETASA: neural network based prediction of solvent accessibility |
| title_full | NETASA: neural network based prediction of solvent accessibility |
| title_fullStr | NETASA: neural network based prediction of solvent accessibility |
| title_full_unstemmed | NETASA: neural network based prediction of solvent accessibility |
| title_short | NETASA: neural network based prediction of solvent accessibility |
| title_sort | netasa: neural network based prediction of solvent accessibility |
| url | http://psasir.upm.edu.my/id/eprint/40060/ http://psasir.upm.edu.my/id/eprint/40060/ http://psasir.upm.edu.my/id/eprint/40060/ http://psasir.upm.edu.my/id/eprint/40060/1/NETASA.pdf http://psasir.upm.edu.my/id/eprint/40060/7/bioinformatics_18_6_819.pdf |