SCONES: Self-Consistent Neural Network for Protein Stability Prediction Upon Mutation

2021 ◽  
Author(s):  
Yashas B. L. Samaga ◽  
Shampa Raghunathan ◽  
U. Deva Priyakumar
Keyword(s):  
Neural Network ◽  
Protein Stability ◽  
Stability Prediction ◽  
Self Consistent

SCONES: Self-Consistent Neural Network for Protein Stability Prediction Upon Mutation

2021 ◽  
Author(s):  
Yashas Samaga B L ◽  
Shampa Raghunathan ◽  
U. Deva Priyakumar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Protein Stability ◽  
Data Augmentation ◽  
Stability Prediction ◽  
Structural Environment ◽  
Self Consistent ◽  
The Difference ◽  
Protein Sequence Space ◽  
New Machine

<div>Engineering proteins to have desired properties by mutating amino acids at specific sites is commonplace. Such engineered proteins must be stable to function. Experimental methods used to determine stability at throughputs required to scan the protein sequence space thoroughly are laborious. To this end, many machine learning based methods have been developed to predict thermodynamic stability changes upon mutation. These methods have been evaluated for symmetric consistency by testing with hypothetical reverse mutations. In this work, we propose transitive data augmentation, evaluating transitive consistency, and a new machine learning based method, first of its kind, that incorporates both symmetric and transitive properties into the architecture. Our method, called SCONES, is an interpretable neural network that estimates a residue's contributions towards protein stability dG in its local structural environment. The difference between independently predicted contributions of the reference and mutant residues in a missense mutation is reported as dG. We show that this self-consistent machine learning architecture is immune to many common biases in datasets, relies less on data than existing methods, and is robust to overfitting.</div><div><br></div>

scholarly journals SCONES: Self-Consistent Neural Network for Protein Stability Prediction Upon Mutation

2021 ◽  
Author(s):  
Yashas Samaga B L ◽  
Shampa Raghunathan ◽  
U. Deva Priyakumar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Protein Stability ◽  
Data Augmentation ◽  
Stability Prediction ◽  
Structural Environment ◽  
Self Consistent ◽  
The Difference ◽  
Protein Sequence Space ◽  
New Machine

<div>Engineering proteins to have desired properties by mutating amino acids at specific sites is commonplace. Such engineered proteins must be stable to function. Experimental methods used to determine stability at throughputs required to scan the protein sequence space thoroughly are laborious. To this end, many machine learning based methods have been developed to predict thermodynamic stability changes upon mutation. These methods have been evaluated for symmetric consistency by testing with hypothetical reverse mutations. In this work, we propose transitive data augmentation, evaluating transitive consistency, and a new machine learning based method, first of its kind, that incorporates both symmetric and transitive properties into the architecture. Our method, called SCONES, is an interpretable neural network that estimates a residue's contributions towards protein stability dG in its local structural environment. The difference between independently predicted contributions of the reference and mutant residues in a missense mutation is reported as dG. We show that this self-consistent machine learning architecture is immune to many common biases in datasets, relies less on data than existing methods, and is robust to overfitting.</div><div><br></div>

scholarly journals Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling

PLoS ONE ◽  
2020 ◽  
Vol 15 (2) ◽  
pp. e0229418 ◽  
Author(s):  
Seyed Amir Hossein Hosseini ◽  
Chi Zhang ◽  
Sebastian Weingärtner ◽  
Steen Moeller ◽  
Matthias Stuber ◽  
...  
Keyword(s):  
Neural Network ◽  
Self Consistent ◽  
Coronary Mri

scholarly journals Protein stability engineering insights revealed by domain-wide comprehensive mutagenesis

2019 ◽  
Vol 116 (33) ◽  
pp. 16367-16377 ◽  
Author(s):  
Alex Nisthal ◽  
Connie Y. Wang ◽  
Marie L. Ary ◽  
Stephen L. Mayo
Keyword(s):  
Protein Stability ◽  
Amino Acid Type ◽  
Stability Prediction ◽  
Single Mutant ◽  
Prediction Tools ◽  
Prediction Algorithms ◽  
Automated Method ◽  
Acid Type ◽  
Stability Data ◽  
Neutral Effect

The accurate prediction of protein stability upon sequence mutation is an important but unsolved challenge in protein engineering. Large mutational datasets are required to train computational predictors, but traditional methods for collecting stability data are either low-throughput or measure protein stability indirectly. Here, we develop an automated method to generate thermodynamic stability data for nearly every single mutant in a small 56-residue protein. Analysis reveals that most single mutants have a neutral effect on stability, mutational sensitivity is largely governed by residue burial, and unexpectedly, hydrophobics are the best tolerated amino acid type. Correlating the output of various stability-prediction algorithms against our data shows that nearly all perform better on boundary and surface positions than for those in the core and are better at predicting large-to-small mutations than small-to-large ones. We show that the most stable variants in the single-mutant landscape are better identified using combinations of 2 prediction algorithms and including more algorithms can provide diminishing returns. In most cases, poor in silico predictions were tied to compositional differences between the data being analyzed and the datasets used to train the algorithm. Finally, we find that strategies to extract stabilities from high-throughput fitness data such as deep mutational scanning are promising and that data produced by these methods may be applicable toward training future stability-prediction tools.

scholarly journals Evaluation of the Dreicer runaway generation rate in the presence of high- impurities using a neural network

2019 ◽  
Vol 85 (6) ◽  
Author(s):  
L. Hesslow ◽  
L. Unnerfelt ◽  
O. Vallhagen ◽  
O. Embreus ◽  
M. Hoppe ◽  
...  
Keyword(s):  
Neural Network ◽  
Runaway Electron ◽  
The Self ◽  
Generation Rate ◽  
Integrated Modelling ◽  
Plasma Parameters ◽  
The Neural Network ◽  
Wide Range ◽  
Self Consistent ◽  
Computationally Expensive

Integrated modelling of electron runaway requires computationally expensive kinetic models that are self-consistently coupled to the evolution of the background plasma parameters. The computational expense can be reduced by using parameterized runaway generation rates rather than solving the full kinetic problem. However, currently available generation rates neglect several important effects; in particular, they are not valid in the presence of partially ionized impurities. In this work, we construct a multilayer neural network for the Dreicer runaway generation rate which is trained on data obtained from kinetic simulations performed for a wide range of plasma parameters and impurities. The neural network accurately reproduces the Dreicer runaway generation rate obtained by the kinetic solver. By implementing it in a fluid runaway-electron modelling tool, we show that the improved generation rates lead to significant differences in the self-consistent runaway dynamics as compared to the results using the previously available formulas for the runaway generation rate.

Sign in / Sign up

Export Citation Format

Share Document