Real value prediction of protein solvent accessibility using enhanced PSSM features

Chang, Darby Tien Hao; Huang, Hsuan Yu; Syu, Yu Tang; Wu, Chih Peng

doi:10.1186/1471-2105-9-s12-s12

Cited by 26 publications

(31 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The estimated accuracy of sequence-based RLA prediction is lower compared to RSA prediction in soluble proteins, with PCC between predicted and observed values of about 0.5 for RLA, as opposed to about 0.6-0.7 PCC for state-of-the-art RSA prediction methods [29,[32][33][34]. However, we demonstrated on several different sets of decoys that by comparing predicted and observed RLAs one can largely discriminate native and native-like from misfolded structures.…”

Section: Discussioncontrasting

confidence: 52%

“…In this work, we focused on the relative lipid accessibility (RLA), which is a direct extension of the relative solvent accessibility notion used in the case of soluble proteins to characterize (in relative terms) the level of surface exposure for individual amino acid residues. Over the last two decades, many statistical and machine learning-based methods have been developed for the prediction of solvent accessibility in soluble proteins [26][27][28][29][30][31][32][33][34]. Recently, several methods have been proposed that extend these efforts to the prediction of lipid accessibility in alpha-helical transmembrane (TM) proteins, extrapolating from a limited, but steadily growing number of experimentally resolved structures [35][36][37].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Solvent and Lipid Accessibility Prediction as a Basis for Model Quality Assessment in Soluble and Membrane Proteins

Phatak¹,

Adamczak²,

Cao³

et al. 2011

CPPS

View full text Add to dashboard Cite

On-going efforts to improve protein structure prediction stimulate the development of scoring functions and methods for model quality assessment (MQA) that can be used to rank and select the best protein models for further refinement. In this work, sequence-based prediction of relative solvent accessibility (RSA) is employed as a basis for a simple MQA method for soluble proteins, and subsequently extended to the much less explored case of (alpha-helical) membrane proteins. In analogy to soluble proteins, the level of exposure to the lipid of amino acid residues in transmembrane (TM) domains is captured in terms of the relative lipid accessibility (RLA), which is predicted from sequence using low-complexity Support Vector Regression models. On an independent set of 23 TM proteins, the new SVR-based predictor yields correlation coefficient (CC) of 0.56 between the predicted and observed RLA profiles, as opposed to CC of 0.13 for a baseline predictor that utilizes TMLIP2H empirical lipophilicity scale (with standard deviations of about 0.15). A simple MQA approach is then defined by ranking models of membrane proteins in terms of consistency between predicted and observed RLA profiles, as a measure of similarity to the native structure. The new method does not require a set of decoy models to optimize parameters, circumventing current limitations in this regard. Several different sets of models, including those generated by fragment based folding simulations, and decoys obtained by swapping TM helices to mimic errors in template based assignment, are used to assess the new approach. Predicted RLA profiles can be used to successfully discriminate near native models from non-native decoys in most cases, significantly improving the separation of correct and incorrectly folded models compared to a simple baseline approach that utilizes TMLIP2H. As suggested by the robust performance of a simple MQA method for soluble proteins that utilizes more accurate RSA predictions, further significant improvements are likely to be achieved. The steady growth in the number of resolved membrane protein structures is expected to yield enhanced RLA predictions, facilitating further efforts to improve de novo and template based prediction of membrane protein structure.

show abstract

Section: Discussioncontrasting

confidence: 52%

Section: Introductionmentioning

confidence: 99%

Solvent and Lipid Accessibility Prediction as a Basis for Model Quality Assessment in Soluble and Membrane Proteins

Phatak¹,

Adamczak²,

Cao³

et al. 2011

CPPS

View full text Add to dashboard Cite

show abstract

“…The ASA values were computed based on the oligomeric states provided by OPM using DSSP with a probe radius of 1.4 Å 27 as with previous studies. 15,17,31,32 No further exploration on probe sizes was conducted because it has been shown that probe size has little or no effect on the performance of RSA predictors. 23 The ASA value of each amino acid type in an extended tripeptide conformation was adopted from a similar study.…”

Section: Methodsmentioning

confidence: 99%

Accurate Prediction of Contact Numbers for Multi-Spanning Helical Membrane Proteins

Mendenhall

Nguyen

et al. 2016

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Prediction of the three-dimensional (3D) structures of proteins by computational methods is acknowledged as an unsolved problem. Accurate prediction of important structural characteristics such as contact number is expected to accelerate the otherwise slow progress being made in the prediction of 3D structure of proteins. Here, we present a dropout neural network-based method, TMH-Expo, for predicting the contact number of transmembrane helix (TMH) residues from sequence. Neuronal dropout is a strategy where certain neurons of the network are excluded from back-propagation to prevent co-adaptation of hidden-layer neurons. By using neuronal dropout, overfitting was significantly reduced and performance was noticeably improved. For multi-spanning helical membrane proteins, TMH-Expo achieved a remarkable Pearson correlation coefficient of 0.69 between predicted and experimental values and a mean absolute error of only 1.68. In addition, among those membrane protein–membrane protein interface residues, 76.8% were correctly predicted. Mapping of predicted contact numbers onto structures indicates that contact numbers predicted by TMH-Expo reflect the exposure patterns of TMHs and reveal membrane protein–membrane protein interfaces, reinforcing the potential of predicted contact numbers to be used as restraints for 3D structure prediction and protein–protein docking. TMH-Expo can be accessed via a Web server at www.meilerlab.org.

show abstract

“…[17], there are 84 sequences in the training dataset that was randomly selected, named the Sma dataset, for feature selection. Every protein was divided into a number of small segments using a sliding window 11 amino acid residues long [17], where the central residue of the segment is the prediction target while the five nearest bilateral residues provide additional information. All the segments were grouped according to their central residues, and 20 RSA prediction models were built.…”

Section: Methodsmentioning

confidence: 99%

“…Each residue of a segment was represented by a 21-dimensional vector that contains 20 values representing effective frequencies of occurrence at respective positions in a multiple alignment and an extra value for the terminal flag as described in the article by Chang et al . [17]. Finally, the PSSM of a segment was represented by 231 values.…”

Section: Methodsmentioning

confidence: 99%

A hydrophobic spine stabilizes a surface-exposed α-helix according to analysis of the solvent-accessible surface area

Liou

Huang

2016

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundMost of hydrophilic and hydrophobic residues are thought to be exposed and buried in proteins, respectively. In contrast to the majority of the existing studies on protein folding characteristics using protein structures, in this study, our aim was to design predictors for estimating relative solvent accessibility (RSA) of amino acid residues to discover protein folding characteristics from sequences.MethodsThe proposed 20 real-value RSA predictors were designed on the basis of the support vector regression method with a set of informative physicochemical properties (PCPs) obtained by means of an optimal feature selection algorithm. Then, molecular dynamics simulations were performed for validating the knowledge discovered by analysis of the selected PCPs.ResultsThe RSA predictors had the mean absolute error of 14.11% and a correlation coefficient of 0.69, better than the existing predictors. The hydrophilic-residue predictors preferred PCPs of buried amino acid residues to PCPs of exposed ones as prediction features. A hydrophobic spine composed of exposed hydrophobic residues of an α-helix was discovered by analyzing the PCPs of RSA predictors corresponding to hydrophobic residues. For example, the results of a molecular dynamics simulation of wild-type sequences and their mutants showed that proteins 1MOF and 2WRP_H16I (Protein Data Bank IDs), which have a perfectly hydrophobic spine, have more stable structures than 1MOF_I54D and 2WRP do (which do not have a perfectly hydrophobic spine).ConclusionsWe identified informative PCPs to design high-performance RSA predictors and to analyze these PCPs for identification of novel protein folding characteristics. A hydrophobic spine in a protein can help to stabilize exposed α-helices.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-016-1368-z) contains supplementary material, which is available to authorized users.

show abstract

Real value prediction of protein solvent accessibility using enhanced PSSM features

Cited by 26 publications

References 33 publications

Solvent and Lipid Accessibility Prediction as a Basis for Model Quality Assessment in Soluble and Membrane Proteins

Solvent and Lipid Accessibility Prediction as a Basis for Model Quality Assessment in Soluble and Membrane Proteins

Accurate Prediction of Contact Numbers for Multi-Spanning Helical Membrane Proteins

A hydrophobic spine stabilizes a surface-exposed α-helix according to analysis of the solvent-accessible surface area

Contact Info

Product

Resources

About