A three-state prediction of single point mutations on protein stability changes

Capriotti, Emidio; Fariselli, Piero; Rossi, Ivan; Casadio, Rita

doi:10.1186/1471-2105-9-s2-s6

Cited by 289 publications

(258 citation statements)

References 17 publications

Supporting

Mentioning

256

Contrasting

Order By: Relevance

“…Moreover, experimental data is affected by the error of measurement which can be as large as ± 0.48 kcal mol − 1 [37]. Hence, the strict classification of the 'small' stability changes as stabilising or destabilising can be misleading [34, 13]. …”

Section: Discussionmentioning

confidence: 99%

“…Hence, methods which over-fit on mutations in residue positions from the training set are unlikely to achieve good prediction performance on the test set (or in cross-validation). The unseen-residue evaluation has been previously adopted for the design of a three-state prediction method I-Mutant3.0 [34]. …”

Section: Methodsmentioning

confidence: 99%

“…These two methods had also been included in an independent assessment study [16]. We did not compare with I-Mutant3.0 [34] because it predicts stability changes into three states (stabilising, destabilising, and neutral).…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

2014

View full text Add to dashboard Cite

BackgroundReliable prediction of stability changes induced by a single amino acid substitution is an important aspect of computational protein design. Several machine learning methods capable of predicting stability changes from the protein sequence alone have been introduced. Prediction performance of these methods is evaluated on mutations unseen during training. Nevertheless, different mutations of the same protein, and even the same residue, as encountered during training are commonly used for evaluation. We argue that a faithful evaluation can be achieved only when a method is tested on previously unseen proteins with low sequence similarity to the training set.ResultsWe provided experimental evidence of the limitations of the evaluation commonly used for assessing the prediction performance. Furthermore, we demonstrated that the prediction of stability changes in previously unseen non-homologous proteins is a challenging task for currently available methods. To improve the prediction performance of our previously proposed method, we identified features which led to over-fitting and further extended the model with new features. The new method employs Evolutionary And Structural Encodings with Amino Acid parameters (EASE-AA). Evaluated with an independent test set of more than 600 mutations, EASE-AA yielded a Matthews correlation coefficient of 0.36 and was able to classify correctly 66% of the stabilising and 74% of the destabilising mutations. For real-value prediction, EASE-AA achieved the correlation of predicted and experimentally measured stability changes of 0.51.ConclusionsCommonly adopted evaluation with mutations in the same protein, and even the same residue, randomly divided between the training and test sets lead to an overestimation of prediction performance. Therefore, stability changes prediction methods should be evaluated only on mutations in previously unseen non-homologous proteins. Under such an evaluation, EASE-AA predicts stability changes more reliably than currently available methods.Electronic supplementary materialThe online version of this article (doi:10.1186/1471-2164-15-S1-S4) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

2014

View full text Add to dashboard Cite

show abstract

“…We considered the statistical accuracy of these three programs, I-Mutant improves the quality of the prediction of the free energy change caused by single point protein mutations by adopting a hypothesis of thermodynamic reversibility of the existing experimental data. The accuracy of prediction for sequence and structure based values were 78% and 84% with correlation coefficient of 0.56 and 0.69, respectively [59]. SIFT correctly predicted 69% of the substitutions associated with the disease that affect protein function.…”

Section: Rational Consideration Of Detrimental Point Mutationsmentioning

confidence: 92%

Computational analysis of deleterious missense mutations in aspartoacylase that cause Canavan’s disease

Sreevishnupriya

Chandrasekaran

Senthilkumar

et al. 2012

Sci. China Life Sci.

View full text Add to dashboard Cite

In this work, the most detrimental missense mutations of aspartoacylase that cause Canavan's disease were identified computationally and the substrate binding efficiencies of those missense mutations were analyzed. Out of 30 missense mutations, I-Mutant 2.0, SIFT and PolyPhen programs identified 22 variants that were less stable, deleterious and damaging respectively. Subsequently, modeling of these 22 variants was performed to understand the change in their conformations with respect to the native aspartoacylase by computing their root mean squared deviation (RMSD). Furthermore, the native protein and the 22 mutants were docked with the substrate NAA (N-Acetyl-Aspartic acid) to explain the substrate binding efficiencies of those detrimental missense mutations. Among the 22 mutants, the docking studies identified that 15 mutants caused lower binding affinity for NAA than the native protein. Finally, normal mode analysis determined that the loss of binding affinity of these 15 mutants was caused by altered flexibility in the amino acids that bind to NAA compared with the native protein. Thus, the present study showed that the majority of the substrate-binding amino acids in those 15 mutants displayed loss of flexibility, which could be the theoretical explanation of decreased binding affinity between the mutant aspartoacylases and NAA. missense mutation, Canavan's disease, aspartoacylase, NAA, flexibility Citation:Sreevishnupriya K, Chandrasekaran P, Senthilkumar A, et al. Computational analysis of deleterious missense mutations in aspartoacylase that cause Canavan's disease.

show abstract

“…I-Mutant3.0 predictions are performed starting either from the protein structure or from the protein sequence. I-Mutant3.0 programs can be used to predict the sign of the stability change upon mutation or as estimation of regression to predict changes in free energy (http://gpcr.biocomp.unibo.it/cgi/predictors/IMutant3.0/I-Mutant3.0.cgi) (24). MUpro (http://mupro.proteomics.ics.uci.edu/) uses both SVM and Neural Networks programs.…”

Section: Tools Used For Various Analyses Of Selected Ns-snpsmentioning

confidence: 99%

In Silico Data Mining of Single Nucleotide Polymorphisms in EZH2 and Their Role in Cancer

et al. 2017

View full text Add to dashboard Cite

Background: Enhancer of zeste homolog 2 (EZH2) is a catalytic subunit of Polycomb Repressor Complex 2. PRC2 catalyzes methylation of H3K27me and it silences specific gene transcriptions. EZH2 is known to play a vital role in cancer initiation, development, progression, metastasis, and drug resistance. The expression of EZH2 is regulated by a variety of oncogenic transcription factors, tumor suppressor micro-RNAs, and cancer-associated non-coding RNAs. Post-translational modifications also control EZH2 activity. The altered expression of EZH2 has major implication in altering cellular plasticity and, hence, understanding various deleterious mutations can help comprehend its role in cancer metastasis. Objectives: The aim of this study is to summarize the data from COSMIC into useful information from the perspective of severity of the mutations in EZH2 and their contributory role as a potential biomarker in diagnosis and therapeutics associated cancers. Methods: Data mining was carried out for various SNPs in EZH2 SET domain from COSMIC, and the severity of each mutation on the functionality of the enzyme was analyzed, using multiple online in-silico tools. The frequently deleterious SNPs were further subjected to advanced tools to understand the changes which render the enzyme functionally erratic during cancer. Results:The results obtained enhanced the understanding of EZH2 mutation and predicted the plausible biomarkers that could be targeted for the purpose of diagnosis and therapeutics. About 14 prospective biomarkers for various cancers were identified and, further, their role in altering the EZH2 function was discussed. Conclusions:The various predictive and prognostic impacts of these SNPs in the selected residues are discussed which can be efficiently targeted for an improved cancer diagnosis and designing appropriate treatment strategies.

show abstract

A three-state prediction of single point mutations on protein stability changes

Cited by 289 publications

References 17 publications

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

Computational analysis of deleterious missense mutations in aspartoacylase that cause Canavan’s disease

In Silico Data Mining of Single Nucleotide Polymorphisms in EZH2 and Their Role in Cancer

Contact Info

Product

Resources

About