Prediction of protein tertiary structure to low resolution: performance for a large and structurally diverse test set

Eyrich, Volker A.; Standley, Daron M.; Friesner, Richard A.

doi:10.1006/jmbi.1999.2702

Cited by 49 publications

(29 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In tests of ab initio folding algorithms, short unstructured N-and C-terminal regions have been eliminated to bolster the performance of the method being tested. 3,7 In these cases, the investigators used knowledge of the native structure to decide what positions to exclude from the folding simulations. We have made these decisions based only on the MSA.…”

Section: Restricting Folding To Common Coresmentioning

confidence: 99%

“…One of the major hurdles that must be overcome in the development of consistently reliable ab initio protocols is the difficulty of discriminating near-native models from incorrect models. [3][4][5][6] The method our group has developed, Rosetta, is able to generate low root-mean-square deviation (RMSD) structures for most small proteins (good ϭ 3-7.5 Å RMSD, small ϭ Ͻ100 residues), but it is not always possible to recognize these structures amidst the larger population of incorrect decoys. 7 This work deals with this problem of recognition via two main approaches: the use of multiple sequence alignment (MSA) information and the use of global measures of hydrophobic core formation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving the performance of rosetta using multiple sequence alignment information and global measures of hydrophobic core formation

2001

View full text Add to dashboard Cite

Section: Restricting Folding To Common Coresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving the performance of rosetta using multiple sequence alignment information and global measures of hydrophobic core formation

2001

View full text Add to dashboard Cite

“…However, such hybrid methods are still limited to small proteins because of their large computational requirements. In particular, recent studies (20) suggest that it may be difficult to predict the structure of large ␤ proteins by using these methods, even if the native secondary structure of the protein is known. This is because the lowresolution potentials used to speed up the prediction process have to be enriched with hydrogen bonding terms, to properly model large cooperative structures like ␤ barrels (20).…”

mentioning

confidence: 99%

Toward predicting protein topology: An approach to identifying β hairpins

Cruz

Hutchinson

Shepherd

et al. 2002

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Although secondary structure prediction methods have recently improved, progress from secondary to tertiary structure prediction has been limited. A promising but largely unexplored route to this goal is to predict structure motifs from secondary structure knowledge. Here we present a novel method for the recognition of ␤ hairpins that combines secondary structure predictions and threading methods by using a database search and a neural network approach. The method successfully predicts 48 and 77%, respectively, of all of hairpin and nonhairpin ␤-coil-␤ motifs in a protein database. We find that the main contributors to motif recognition are predicted accessibility and turn propensities.

show abstract

“…This reduction is possible since proteins can form local conformational patterns like α-helices and β-sheets. Many have shown that predicting secondary structure can be a first step toward predicting 3D structure [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Prediction of protein secondary structure by mining structural fragment database

Cheng

Sen

Kloczkowski

et al. 2005

Polymer

View full text Add to dashboard Cite

A new method for predicting protein secondary structure from amino acid sequence has been developed. The method is based on multiple sequence alignment of the query sequence with all other sequences with known structure from the protein data bank (PDB) by using BLAST. The fragments of the alignments belonging to proteins from the PBD are then used for further analysis. We have studied various schemes of assigning weights for matching segments and calculated normalized scores to predict one of the three secondary structures: α-helix, β-sheet, or coil. We applied several artificial intelligence techniques: decision trees (DT), neural networks (NN) and support vector machines (SVM) to improve the accuracy of predictions and found that SVM gave the best performance. Preliminary data show that combining the fragment mining approach with GOR V (Kloczkowski et al, Proteins 49 (2002) 154-166) for regions of low sequence similarity improves the prediction accuracy.

show abstract

Prediction of protein tertiary structure to low resolution: performance for a large and structurally diverse test set

Cited by 49 publications

References 25 publications

Improving the performance of rosetta using multiple sequence alignment information and global measures of hydrophobic core formation

Improving the performance of rosetta using multiple sequence alignment information and global measures of hydrophobic core formation

Toward predicting protein topology: An approach to identifying β hairpins

Prediction of protein secondary structure by mining structural fragment database

Contact Info

Product

Resources

About