Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms.
Recently, predicting proteins three-dimensional (3D) structure from its sequence information has made a significant progress due to the advances in computational techniques and the growth of experimental structures. However, selecting good models from a structural model pool is an important and chal...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2014-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC4164442?pdf=render |
| _version_ | 1819125104807772160 |
|---|---|
| author | Balachandran Manavalan Juyong Lee Jooyoung Lee |
| author_facet | Balachandran Manavalan Juyong Lee Jooyoung Lee |
| author_sort | Balachandran Manavalan |
| collection | DOAJ |
| description | Recently, predicting proteins three-dimensional (3D) structure from its sequence information has made a significant progress due to the advances in computational techniques and the growth of experimental structures. However, selecting good models from a structural model pool is an important and challenging task in protein structure prediction. In this study, we present the first application of random forest based model quality assessment (RFMQA) to rank protein models using its structural features and knowledge-based potential energy terms. The method predicts a relative score of a model by using its secondary structure, solvent accessibility and knowledge-based potential energy terms. We trained and tested the RFMQA method on CASP8 and CASP9 targets using 5-fold cross-validation. The correlation coefficient between the TM-score of the model selected by RFMQA (TMRF) and the best server model (TMbest) is 0.945. We benchmarked our method on recent CASP10 targets by using CASP8 and 9 server models as a training set. The correlation coefficient and average difference between TMRF and TMbest over 95 CASP10 targets are 0.984 and 0.0385, respectively. The test results show that our method works better in selecting top models when compared with other top performing methods. RFMQA is available for download from http://lee.kias.re.kr/RFMQA/RFMQA_eval.tar.gz. |
| first_indexed | 2024-12-22T07:34:50Z |
| format | Article |
| id | doaj.art-743e6e5194dc4dd2a8098f99a3571b73 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-22T07:34:50Z |
| publishDate | 2014-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-743e6e5194dc4dd2a8098f99a3571b732022-12-21T18:33:55ZengPublic Library of Science (PLoS)PLoS ONE1932-62032014-01-0199e10654210.1371/journal.pone.0106542Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms.Balachandran ManavalanJuyong LeeJooyoung LeeRecently, predicting proteins three-dimensional (3D) structure from its sequence information has made a significant progress due to the advances in computational techniques and the growth of experimental structures. However, selecting good models from a structural model pool is an important and challenging task in protein structure prediction. In this study, we present the first application of random forest based model quality assessment (RFMQA) to rank protein models using its structural features and knowledge-based potential energy terms. The method predicts a relative score of a model by using its secondary structure, solvent accessibility and knowledge-based potential energy terms. We trained and tested the RFMQA method on CASP8 and CASP9 targets using 5-fold cross-validation. The correlation coefficient between the TM-score of the model selected by RFMQA (TMRF) and the best server model (TMbest) is 0.945. We benchmarked our method on recent CASP10 targets by using CASP8 and 9 server models as a training set. The correlation coefficient and average difference between TMRF and TMbest over 95 CASP10 targets are 0.984 and 0.0385, respectively. The test results show that our method works better in selecting top models when compared with other top performing methods. RFMQA is available for download from http://lee.kias.re.kr/RFMQA/RFMQA_eval.tar.gz.http://europepmc.org/articles/PMC4164442?pdf=render |
| spellingShingle | Balachandran Manavalan Juyong Lee Jooyoung Lee Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. PLoS ONE |
| title | Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. |
| title_full | Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. |
| title_fullStr | Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. |
| title_full_unstemmed | Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. |
| title_short | Random forest-based protein model quality assessment (RFMQA) using structural features and potential energy terms. |
| title_sort | random forest based protein model quality assessment rfmqa using structural features and potential energy terms |
| url | http://europepmc.org/articles/PMC4164442?pdf=render |
| work_keys_str_mv | AT balachandranmanavalan randomforestbasedproteinmodelqualityassessmentrfmqausingstructuralfeaturesandpotentialenergyterms AT juyonglee randomforestbasedproteinmodelqualityassessmentrfmqausingstructuralfeaturesandpotentialenergyterms AT jooyounglee randomforestbasedproteinmodelqualityassessmentrfmqausingstructuralfeaturesandpotentialenergyterms |