A natural upper bound to the accuracy of predicting protein stability changes upon mutations

Montanucci, Ludovica; Martelli, Pier Luigi; Ben‐Tal, Nir; Fariselli, Piero

doi:10.1093/bioinformatics/bty880

Cited by 40 publications

(60 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a number of studies have compared ΔΔG predictors, showing heterogeneous correlations with experimental values on the order of R = 0.5 for many predictors 12 , 13 , 65 . However, a recent work has also revealed problems with the noise in experimental stability data used to benchmark the prediction methods, generally assessed through correlation values 66 . Taking noise and data distribution limitations into account, it is estimated that with currently available experimental data the best ΔΔG predictor output correlations should be in the range 0.7–0.8, while higher values would suggest overfitting 66 .…”

Section: Discussionmentioning

confidence: 99%

“…However, a recent work has also revealed problems with the noise in experimental stability data used to benchmark the prediction methods, generally assessed through correlation values 66 . Taking noise and data distribution limitations into account, it is estimated that with currently available experimental data the best ΔΔG predictor output correlations should be in the range 0.7–0.8, while higher values would suggest overfitting 66 . As such, even assuming that ‘true’ ΔΔG values were perfectly correlated with mutation pathogenicity, we would still expect these computational predictors to misclassify many variants.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of pathogenic missense mutations using protein stability predictors

Gerasimavicius

Liu

Marsh

2020

Sci Rep

View full text Add to dashboard Cite

Attempts at using protein structures to identify disease-causing mutations have been dominated by the idea that most pathogenic mutations are disruptive at a structural level. Therefore, computational stability predictors, which assess whether a mutation is likely to be stabilising or destabilising to protein structure, have been commonly used when evaluating new candidate disease variants, despite not having been developed specifically for this purpose. We therefore tested 13 different stability predictors for their ability to discriminate between pathogenic and putatively benign missense variants. We find that one method, FoldX, significantly outperforms all other predictors in the identification of disease variants. Moreover, we demonstrate that employing predicted absolute energy change scores improves performance of nearly all predictors in distinguishing pathogenic from benign variants. Importantly, however, we observe that the utility of computational stability predictors is highly heterogeneous across different proteins, and that they are all inferior to the best performing variant effect predictors for identifying pathogenic mutations. We suggest that this is largely due to alternate molecular mechanisms other than protein destabilisation underlying many pathogenic mutations. Thus, better ways of incorporating protein structural information and molecular mechanisms into computational variant effect predictors will be required for improved disease variant prioritisation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Identification of pathogenic missense mutations using protein stability predictors

Gerasimavicius

Liu

Marsh

2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…For example, a number of studies have compared ΔΔG predictors, showing heterogeneous correlations with experimental values on the order of R=0.5 for many predictors 12,13,60 . However, a recent work has also revealed problems with the noise in experimental stability data used to benchmark the prediction methods, generally assessed through correlation values 61 . Taking noise and data distribution limitations into account, it is estimated that with currently available experimental data the best ΔΔG predictor output correlations should be in the range 0.7-0.8, while higher values would suggest overfitting 61 .…”

Section: Discussionmentioning

confidence: 99%

“…However, a recent work has also revealed problems with the noise in experimental stability data used to benchmark the prediction methods, generally assessed through correlation values 61 . Taking noise and data distribution limitations into account, it is estimated that with currently available experimental data the best ΔΔG predictor output correlations should be in the range 0.7-0.8, while higher values would suggest overfitting 61 . As such, even assuming that 'true' ΔΔG values were perfectly correlated with mutation pathogenicity, we would still expect these computational predictors to misclassify many variants.…”

Section: Discussionmentioning

confidence: 99%

Identification of pathogenic missense mutations using protein stability predictors

Gerasimavicius

Liu

Marsh

2020

Preprint

View full text Add to dashboard Cite

Attempts at using protein structures to identify disease-causing mutations have been dominated by the idea that most pathogenic mutations are disruptive at a structural level. Therefore, computational stability predictors, which assess whether a mutation is likely to be stabilising or destabilising to protein structure, have been commonly used when evaluating new candidate disease variants, despite not having been developed specifically for this purpose. We therefore tested 12 different stability predictors for their ability to discriminate between pathogenic and putatively benign missense variants. We find that one method, FoldX, considerably outperforms all others in the identification of disease variants. Moreover, we demonstrate that employing absolute energy change scores improves performance of nearly all predictors. Importantly, however, we observe that the utility of computational stability predictors is highly heterogeneous across different proteins, and that they are all are inferior to the best performing variant effect predictors for identifying pathogenic mutations. We suggest that this is largely due to alternate molecular mechanisms other than protein destabilisation underlying many pathogenic mutations. Thus, better ways of incorporating protein structural information and molecular mechanisms into computational variant effect predictors will be required for improved disease variant prioritisation.

show abstract

“…This result is consistent with a recent theoretical estimate of a natural upper bound of the accuracy of DDG predictions. 50 These results suggest that there may still be room for improvement of computational DDG predictions.…”

Section: Prediction Of Conformational Stabilitymentioning

confidence: 97%

Engineering Stability, Viscosity, and Immunogenicity of Antibodies by Computational Design

Kuroda

Tsumoto

2020

Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

In recent years, computational methods have garnered much attention in protein engineering. A large number of computational methods have been developed to analyze the sequences and structures of proteins and have been used to predict the various properties. Antibodies are one of the emergent protein therapeutics, and thus, methods to control their physicochemical properties are highly desirable. However, despite the tremendous efforts of past decades, computational methods to predict the physicochemical properties of antibodies are still in their infancy. Experimental validations are certainly required for real-world applications, and the results should be interpreted with caution. Among the various properties of antibodies, we focus in this review on stability, viscosity, and immunogenicity, and we present the current status of computational methods to engineer such properties.

show abstract

A natural upper bound to the accuracy of predicting protein stability changes upon mutations

Cited by 40 publications

References 33 publications

Identification of pathogenic missense mutations using protein stability predictors

Identification of pathogenic missense mutations using protein stability predictors

Identification of pathogenic missense mutations using protein stability predictors

Engineering Stability, Viscosity, and Immunogenicity of Antibodies by Computational Design

Contact Info

Product

Resources

About