2022
DOI: 10.1016/j.sbi.2021.11.001
|View full text |Cite
|
Sign up to set email alerts
|

Artificial intelligence challenges for predicting the impact of mutations on protein stability

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
77
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 72 publications
(77 citation statements)
references
References 63 publications
0
77
0
Order By: Relevance
“…These experimental heat maps are compared with the computational heat maps of ΔΔG derived in the present work, using DeepDDG ( Figure 2c ), mCSM ( Figure 2d ), and SimBa-IB ( Figure 2e ). SimBa produces more stabilizing trends overall, as it was developed to handle destabilization biases (the method performs similarly to other methods in benchmarks despite this feature)[55, 74].…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…These experimental heat maps are compared with the computational heat maps of ΔΔG derived in the present work, using DeepDDG ( Figure 2c ), mCSM ( Figure 2d ), and SimBa-IB ( Figure 2e ). SimBa produces more stabilizing trends overall, as it was developed to handle destabilization biases (the method performs similarly to other methods in benchmarks despite this feature)[55, 74].…”
Section: Resultsmentioning
confidence: 99%
“…Remarkably, the computational data correlate extremely well with the binned experimental data, especially for DeepDDG, much more than normally seen. [74] Considering that the models were developed to predict fold stability effects, not expression (which also depends on effects at the nucleic acid level) and that we used the full S-protein structures whereas the experiments express RBD on the yeast surface with expected modifications, this result is very surprising. One interpretation of this result is that broader functional properties of the mutant space of the S-protein are in fact largely determined by a few simple features, due to underlying correlations.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…The methods represent three different design types–linear regression, machine learning, and force field-potential based–and are thus expected to provide a good indication of the maximal sensitivity toward method choice. SimBa has been tested both by us (Caldararu et al 2021b ) and in an independent benchmarking study (Pucci et al 2022 ) where it performed slightly above average in terms of error and R 2 , despite its simplicity. SimBa reduces biases by design, but was run in the nonsymmetric mode (IB) which typically has slightly higher accuracy for random mutations.…”
Section: Methodsmentioning
confidence: 99%
“…SimBa reduces biases by design, but was run in the nonsymmetric mode (IB) which typically has slightly higher accuracy for random mutations. (Bæk and Kepp 2022a ) I-Mutant (Capriotti et al 2005 , 2006 ) is a robust Support Vector Machine trained on ProTherm data which is not mutation-type or stability-balanced (Bæk and Kepp 2022a ; Pucci et al 2022 ) but has shown good general performance in many benchmarks, (Potapov et al 2009 ; Kepp 2014 , 2015 ; Pucci et al 2022 ) and has low structural sensitivity. (Caldararu et al 2021a ) CUPSAT (Parthiban et al 2006 ) uses environment-specific force fields to predict protein stability that is more sensitive to structure input.…”
Section: Methodsmentioning
confidence: 99%