2016/01/25 by Karolis Uziela, Uziela, Karolis, Björn Wallner +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Mathematics · #Algorithm #Artificial intelligence #Biomolecules (q-bio.BM) #Centroid #Computer science #Data mining #Energy (signal processing) #FOS: Biological sciences #Function (biology) #Geography #High resolution #Low resolution #Machine Learning in Bioinformatics #Machine learning #Mathematics #Physics #Protein Structure and Dynamics #Quality (philosophy) #RNA and protein synthesis mechanisms #Remote sensing #Resolution (logic) #State (computer science) #Statistics #q-bio.BM
paper · pdf · doi:10.48550/arxiv.1602.05832
published in arXiv (Cornell University) (Cornell University)
arxiv created 2016/01/25 · openalex publication_date 2016/01/25 · arxiv updated 2016/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Motivation: To assess the quality of a protein model, i.e. to estimate how close it is to its native structure, using no other information than the structure of the model has been shown to be useful for structure prediction. The state of the art method, ProQ2, is based on a machine learning approach that uses a number of features calculated from a protein model. Here, we examine if these features can be exchanged with energy terms calculated from Rosetta and if a combination of these terms can improve the quality assessment. Results: When using the full atom energy function from Rosetta in ProQRosFA the QA is on par with our previous state-of-the-art method, ProQ2. The method based on the low-resolution centroid scoring function, ProQRosCen, performs almost as well and the combination of all the three methods, ProQ2, ProQRosFA and ProQCenFA into ProQ3 show superior performance over ProQ2. Availability: ProQ3 is freely available on BitBucket at https://bitbucket.org/ElofssonLab/proq3