Combination of scoring schemes for protein docking
<p>Abstract</p> <p>Background</p> <p>Docking algorithms are developed to predict in which orientation two proteins are likely to bind under natural conditions. The currently used methods usually consist of a sampling step followed by a scoring step. We developed a weigh...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2007-08-01
|
| Series: | BMC Bioinformatics |
| Online Access: | http://www.biomedcentral.com/1471-2105/8/279 |
| _version_ | 1828487582479024128 |
|---|---|
| author | Schomburg Dietmar Heuser Philipp |
| author_facet | Schomburg Dietmar Heuser Philipp |
| author_sort | Schomburg Dietmar |
| collection | DOAJ |
| description | <p>Abstract</p> <p>Background</p> <p>Docking algorithms are developed to predict in which orientation two proteins are likely to bind under natural conditions. The currently used methods usually consist of a sampling step followed by a scoring step. We developed a weighted geometric correlation based on optimised atom specific weighting factors and combined them with our previously published amino acid specific scoring and with a comprehensive SVM-based scoring function.</p> <p>Results</p> <p>The scoring with the atom specific weighting factors yields better results than the amino acid specific scoring. In combination with SVM-based scoring functions the percentage of complexes for which a near native structure can be predicted within the top 100 ranks increased from 14% with the geometric scoring to 54% with the combination of all scoring functions. Especially for the enzyme-inhibitor complexes the results of the ranking are excellent. For half of these complexes a near-native structure can be predicted within the first 10 proposed structures and for more than 86% of all enzyme-inhibitor complexes within the first 50 predicted structures.</p> <p>Conclusion</p> <p>We were able to develop a combination of different scoring schemes which considers a series of previously described and some new scoring criteria yielding a remarkable improvement of prediction quality.</p> |
| first_indexed | 2024-12-11T09:53:20Z |
| format | Article |
| id | doaj.art-26f8ff5ee0114e8687154916f80d98c9 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-11T09:53:20Z |
| publishDate | 2007-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-26f8ff5ee0114e8687154916f80d98c92022-12-22T01:12:19ZengBMCBMC Bioinformatics1471-21052007-08-018127910.1186/1471-2105-8-279Combination of scoring schemes for protein dockingSchomburg DietmarHeuser Philipp<p>Abstract</p> <p>Background</p> <p>Docking algorithms are developed to predict in which orientation two proteins are likely to bind under natural conditions. The currently used methods usually consist of a sampling step followed by a scoring step. We developed a weighted geometric correlation based on optimised atom specific weighting factors and combined them with our previously published amino acid specific scoring and with a comprehensive SVM-based scoring function.</p> <p>Results</p> <p>The scoring with the atom specific weighting factors yields better results than the amino acid specific scoring. In combination with SVM-based scoring functions the percentage of complexes for which a near native structure can be predicted within the top 100 ranks increased from 14% with the geometric scoring to 54% with the combination of all scoring functions. Especially for the enzyme-inhibitor complexes the results of the ranking are excellent. For half of these complexes a near-native structure can be predicted within the first 10 proposed structures and for more than 86% of all enzyme-inhibitor complexes within the first 50 predicted structures.</p> <p>Conclusion</p> <p>We were able to develop a combination of different scoring schemes which considers a series of previously described and some new scoring criteria yielding a remarkable improvement of prediction quality.</p>http://www.biomedcentral.com/1471-2105/8/279 |
| spellingShingle | Schomburg Dietmar Heuser Philipp Combination of scoring schemes for protein docking BMC Bioinformatics |
| title | Combination of scoring schemes for protein docking |
| title_full | Combination of scoring schemes for protein docking |
| title_fullStr | Combination of scoring schemes for protein docking |
| title_full_unstemmed | Combination of scoring schemes for protein docking |
| title_short | Combination of scoring schemes for protein docking |
| title_sort | combination of scoring schemes for protein docking |
| url | http://www.biomedcentral.com/1471-2105/8/279 |
| work_keys_str_mv | AT schomburgdietmar combinationofscoringschemesforproteindocking AT heuserphilipp combinationofscoringschemesforproteindocking |