Artificial Neural Network Modification of Simulation-Based Fitting:  Application to a Protein−Lipid System

Nazarov, Petr V.; Apanasovich, V. V.; Lutkovski, Vladimir M.; Yatskou, Mikalai M.; Koehorst, R.B.M.; Hemminga, M.A.

doi:10.1021/ci034149g

Cited by 16 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two-helix protein model is incorporated in a membrane as described before (3,12). A square region of a bilayer containing a certain number of randomly incorporated proteins (N P ) is considered.…”

Section: Model For M13 Major Coat Protein Incorporated Into a Lipid Bilayermentioning

confidence: 99%

FRET Study of Membrane Proteins: Determination of the Tilt and Orientation of the N-Terminal Domain of M13 Major Coat Protein

Nazarov

Koehorst

Vos

et al. 2007

Biophysical Journal

Self Cite

View full text Add to dashboard Cite

A formalism for membrane protein structure determination was developed. This method is based on steady-state FRET data and information about the position of the fluorescence maxima on site-directed fluorescent labeled proteins in combination with global data analysis utilizing simulation-based fitting. The methodology was applied to determine the structural properties of the N-terminal domain of the major coat protein from bacteriophage M13 reconstituted into unilamellar DOPC/DOPG (4:1 mol/mol) vesicles. For our purpose, the cysteine mutants A7C, A9C, N12C, S13C, Q15C, A16C, S17C, and A18C in the N-terminal domain of this protein were produced and specifically labeled with the fluorescence probe AEDANS. The energy transfer data from the natural Trp-26 to AEDANS were analyzed assuming a two-helix protein model. Furthermore, the polarity Stokes shift of the AEDANS fluorescence maxima is taken into account. As a result the orientation and tilt of the N-terminal protein domain with respect to the bilayer interface were obtained, showing for the first time, to our knowledge, an overall alpha-helical protein conformation from amino acid residues 12-46, close to the protein conformation in the intact phage.

show abstract

Section: Model For M13 Major Coat Protein Incorporated Into a Lipid Bilayermentioning

confidence: 99%

FRET Study of Membrane Proteins: Determination of the Tilt and Orientation of the N-Terminal Domain of M13 Major Coat Protein

Nazarov

Koehorst

Vos

et al. 2007

Biophysical Journal

Self Cite

View full text Add to dashboard Cite

show abstract

“…We also have employed a multi-layer perceptron (MLP) classifier to the five data sets used to investigate the occurrence of diagnostic biases for its comparable performance with respect to SVM and other classifiers such as decision trees [38, 39]. We still use the 5-fold cross validation is still for the convenience of comparisons.…”

Section: Discussionmentioning

confidence: 99%

Diagnostic biases in translational bioinformatics

Han

2015

BMC Med Genomics

View full text Add to dashboard Cite

BackgroundWith the surge of translational medicine and computational omics research, complex disease diagnosis is more and more relying on massive omics data-driven molecular signature detection. However, how to detect and prevent possible diagnostic biases in translational bioinformatics remains an unsolved problem despite its importance in the coming era of personalized medicine.MethodsIn this study, we comprehensively investigate the diagnostic bias problem by analyzing benchmark gene array, protein array, RNA-Seq and miRNA-Seq data under the framework of support vector machines for different model selection methods. We further categorize the diagnostic biases into different types by conducting rigorous kernel matrix analysis and provide effective machine learning methods to conquer the diagnostic biases.ResultsIn this study, we comprehensively investigate the diagnostic bias problem by analyzing benchmark gene array, protein array, RNA-Seq and miRNA-Seq data under the framework of support vector machines. We have found that the diagnostic biases happen for data with different distributions and SVM with different kernels. Moreover, we identify total three types of diagnostic biases: overfitting bias, label skewness bias, and underfitting bias in SVM diagnostics, and present corresponding reasons through rigorous analysis. Compared with the overfitting and underfitting biases, the label skewness bias is more challenging to detect and conquer because it can be easily confused as a normal diagnostic case from its deceptive accuracy. To tackle this problem, we propose a derivative component analysis based support vector machines to conquer the label skewness bias by achieving the rivaling clinical diagnostic results.ConclusionsOur studies demonstrate that the diagnostic biases are mainly caused by the three major factors, i.e. kernel selection, signal amplification mechanism in high-throughput profiling, and training data label distribution. Moreover, the proposed DCA-SVM diagnosis provides a generic solution for the label skewness bias overcome due to the powerful feature extraction capability from derivative component analysis. Our work identifies and solves an important but less addressed problem in translational research. It also has a positive impact on machine learning for adding new results to kernel-based learning for omics data.

show abstract

“…Neural Networks trained with the Marquart-Levenberg algorithm have been successfully used in bioinformatics problems such as the data analysis and parameter determination of Protein-Lipid System [29] and the prediction of MHC Class 11-binding Peptides [30]. The Neural Network Toolbox of MATLAB was used for performance comparison against the other methods.…”

Section: Methodsmentioning

confidence: 99%

Logic minimization and rule extraction for identification of functional sites in molecular sequences

2012

View full text Add to dashboard Cite

BackgroundLogic minimization is the application of algebraic axioms to a binary dataset with the purpose of reducing the number of digital variables and/or rules needed to express it. Although logic minimization techniques have been applied to bioinformatics datasets before, they have not been used in classification and rule discovery problems. In this paper, we propose a method based on logic minimization to extract predictive rules for two bioinformatics problems involving the identification of functional sites in molecular sequences: transcription factor binding sites (TFBS) in DNA and O-glycosylation sites in proteins. TFBS are important in various developmental processes and glycosylation is a posttranslational modification critical to protein functions.MethodsIn the present study, we first transformed the original biological dataset into a suitable binary form. Logic minimization was then applied to generate sets of simple rules to describe the transformed dataset. These rules were used to predict TFBS and O-glycosylation sites. The TFBS dataset is obtained from the TRANSFAC database, while the glycosylation dataset was compiled using information from OGLYCBASE and the Swiss-Prot Database.We performed the same predictions using two standard classification techniques, Artificial Neural Networks (ANN) and Support Vector Machines (SVM), and used their sensitivities and positive predictive values as benchmarks for the performance of our proposed algorithm. SVM were also used to reduce the number of variables included in the logic minimization approach.ResultsFor both TFBS and O-glycosylation sites, the prediction performance of the proposed logic minimization method was generally comparable and, in some cases, superior to the standard ANN and SVM classification methods with the advantage of providing intelligible rules to describe the datasets. In TFBS prediction, logic minimization produced a very small set of simple rules. In glycosylation site prediction, the rules produced were also interpretable and the most popular rules generated appeared to correlate well with recently reported hydrophilic/hydrophobic enhancement values of amino acids around possible O-glycosylation sites. Experiments with Self-Organizing Neural Networks corroborate the practical worth of the logic minimization method for these case studies.ConclusionsThe proposed logic minimization algorithm provides sets of rules that can be used to predict TFBS and O-glycosylation sites with sensitivity and positive predictive value comparable to those from ANN and SVM. Moreover, the logic minimization method has the additional capability of generating interpretable rules that allow biological scientists to correlate the predictions with other experimental results and to form new hypotheses for further investigation. Additional experiments with alternative rule-extraction techniques demonstrate that the logic minimization method is able to produce accurate rules from datasets with large numbers of variables and limited numbers of positive examples.

show abstract

Artificial Neural Network Modification of Simulation-Based Fitting: Application to a Protein−Lipid System

Cited by 16 publications

References 20 publications

FRET Study of Membrane Proteins: Determination of the Tilt and Orientation of the N-Terminal Domain of M13 Major Coat Protein

FRET Study of Membrane Proteins: Determination of the Tilt and Orientation of the N-Terminal Domain of M13 Major Coat Protein

Diagnostic biases in translational bioinformatics

Logic minimization and rule extraction for identification of functional sites in molecular sequences

Contact Info

Product

Resources

About