Graph Signal Processing on protein residue networks helps in studying its biophysical properties

Srivastava, Divyanshu; Bagler, Ganesh; Kumar, Vibhor

doi:10.1016/j.physa.2023.128603

Cited by 3 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our approach against other methods which can use structure-based networks and amino-acid properties on nodes to model the biophysical property of proteins. One such method is based on the graph Fourier transform, recently proposed in our report [41]. The other method we used for comparison is based on a convolutional neural network which also uses graph structure to combine signals of an input vector of quantified property of amino acids.…”

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

“…In practice, getting a high number of training samples is too difficult, and under the constraints of a small dataset, it is most likely to overfit. We may, however, use the Fourier transform to get the amplitude of the signals required to reproduce any signal [41]. However, the Fourier transform has a basic limitation that all characteristics of a signal are global in scope.…”

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

“…In addition, the performance of CNN degrades progressively when this fraction is reduced slightly. We have also compared our method with the graph Fourier transform-based filtering method [41], as shown in Fig. 3A (see supplementary Fig.…”

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

“…2D and 2E that random forest has performed best among all models with R= 0.81 and RMSE=1.68. When we compared the RMSE for folding rate prediction reported by three other methods (Pred-PFR, FoldRate, SWFoldrate) [40], [41] (see supplementary table 5), we found that their performance was lower than proteinGW.…”

Section: ) Protein Folding Rate Prediction (Regression)mentioning

confidence: 99%

See 3 more Smart Citations

An Explainable Model Using Graph-Wavelet for Predicting Biophysical Properties of Proteins and Measuring Mutational Effects

Mishra,

Pandey,

Rawat

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Proteins hold multispectral patterns of different kinds of physicochemical features of amino acids in their structures, which can help understand proteins' behavior. Here, we propose a method based on the graph-wavelet transform of signals of features of amino acids in protein residue networks derived from their structures to achieve their abstract numerical representations. Such abstract representations of protein structures hand in hand with amino-acid features can be used for different purposes, such as modelling the biophysical property of proteins. Our method outperformed graph-Fourier and convolutional neural-networkbased methods in predicting the biophysical properties of proteins. Even though our method does not predict deleterious mutations, it can summarize the effect of an amino acid based on its location and neighbourhood in protein-structure using graph-wavelet to estimate its influence on the biophysical property of proteins. Such an estimate of the influence of amino-acid has the potential to explain the mechanism of the effect of deleterious non-synonymous mutations. Thus, our approach can reveal patterns of distribution of amino-acid properties in the structure of the protein in the context of a biophysical property for better classification and more insightful understanding.

show abstract

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

Section: B Comparing Graph Wavelet With Other Graph-signal Based Methodsmentioning

confidence: 99%

Section: ) Protein Folding Rate Prediction (Regression)mentioning

confidence: 99%

See 2 more Smart Citations

An Explainable Model Using Graph-Wavelet for Predicting Biophysical Properties of Proteins and Measuring Mutational Effects

Mishra,

Pandey,

Rawat

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…It was established early that graphs representing protein structures share the characteristics of small-world networks [ 40 , 41 , 42 , 43 ]. Critical amino acids [ 44 ], conserved amino-acids networks [ 45 ] in proteins, and signal propagation within the macromolecule were identified by using graphs [ 42 ]. Network models were applied to study protein flexibility [ 46 , 47 ], protein unfolding [ 48 ], and protein folding pathways [ 49 , 50 , 51 ].…”

Section: Introductionmentioning

confidence: 99%

Einstein Model of a Graph to Characterize Protein Folded/Unfolded States

Tyler,

Laforge,

Guzzo

et al. 2023

Molecules

View full text Add to dashboard Cite

The folded structures of proteins can be accurately predicted by deep learning algorithms from their amino-acid sequences. By contrast, in spite of decades of research studies, the prediction of folding pathways and the unfolded and misfolded states of proteins, which are intimately related to diseases, remains challenging. A two-state (folded/unfolded) description of protein folding dynamics hides the complexity of the unfolded and misfolded microstates. Here, we focus on the development of simplified order parameters to decipher the complexity of disordered protein structures. First, we show that any connected, undirected, and simple graph can be associated with a linear chain of atoms in thermal equilibrium. This analogy provides an interpretation of the usual topological descriptors of a graph, namely the Kirchhoff index and Randić resistance, in terms of effective force constants of a linear chain. We derive an exact relation between the Kirchhoff index and the average shortest path length for a linear graph and define the free energies of a graph using an Einstein model. Second, we represent the three-dimensional protein structures by connected, undirected, and simple graphs. As a proof of concept, we compute the topological descriptors and the graph free energies for an all-atom molecular dynamics trajectory of folding/unfolding events of the proteins Trp-cage and HP-36 and for the ensemble of experimental NMR models of Trp-cage. The present work shows that the local, nonlocal, and global force constants and free energies of a graph are promising tools to quantify unfolded/disordered protein states and folding/unfolding dynamics. In particular, they allow the detection of transient misfolded rigid states.

show abstract

An explainable model using Graph-Wavelet for predicting biophysical properties of proteins and measuring mutational effects

Mishra,

Pandey,

Rawat

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Proteins hold multispectral patterns of different kinds of physicochemical features of amino acids in their structures, which can help understand proteins’ behavior. Here, we propose a method based on the graph-wavelet transform of signals of features of amino acids in protein residue networks derived from their structures to achieve their abstract numerical representations. Such abstract representations of protein structures hand in hand with amino-acid features can be used for different purposes, such as modelling the biophysical property of proteins. Our method outperformed graph-Fourier and convolutional neural-network-based methods in predicting the biophysical properties of proteins. Even though our method does not predict deleterious mutations, it can summarize the effect of an amino acid based on its location and neighbourhood in protein-structure using graph-wavelet to estimate its influence on the biophysical property of proteins. Such an estimate of the influence of amino-acid has the potential to explain the mechanism of the effect of deleterious non-synonymous mutations. Thus, our approach can reveal patterns of distribution of amino-acid properties in the structure of the protein in the context of a biophysical property for better classification and more insightful understanding.

show abstract

Graph Signal Processing on protein residue networks helps in studying its biophysical properties

Cited by 3 publications

References 23 publications

An Explainable Model Using Graph-Wavelet for Predicting Biophysical Properties of Proteins and Measuring Mutational Effects

An Explainable Model Using Graph-Wavelet for Predicting Biophysical Properties of Proteins and Measuring Mutational Effects

Einstein Model of a Graph to Characterize Protein Folded/Unfolded States

An explainable model using Graph-Wavelet for predicting biophysical properties of proteins and measuring mutational effects

Contact Info

Product

Resources

About