Consensus Fold Recognition by Predicted Model Quality

[摘要] Protein structure prediction has been a fundamental challenge in the biological field.In this post-genomic era, the need for automated protein structure predictionhas never been more evident and researchers are now focusing on developing computationaltechniques to predict three-dimensional structures with high throughput.Consensus-based protein structure prediction methods are state-of-the-artin automatic protein structure prediction. A consensus-based server combines the outputs of several individual servers and tendsto generate better predictions than any individual server. Consensus-basedmethods have proved to be successful in recent CASP (Critical Assessment of StructurePrediction).In this thesis, a Support Vector Machine (SVM) regression-based consensusmethod is proposed for protein fold recognition, a key component forhigh throughput protein structure prediction and protein function annotation.The SVM first extracts the features of a structural model by comparingthe model to the other models produced by all the individual servers. Then, theSVM predicts the quality of each model. The experimental results from severalLiveBench data sets confirm that our proposed consensus method, SVM regression,consistently performs better than any individual server. Based on this method, wedeveloped a meta server, the Alignment by Consensus Estimation (ACE).

[发布机构] University of Waterloo

[效力级别] Computer Science

[关键词] Biology;Computer Science;consensus;fold;recognition;prediction;protein;structure