Thermostability of Proteins Revisited Through Machine Learning Methodologies: From Nucleotide Sequence to Structure

Chakravorty, Debamitra; Khan, Mohd Faheem; Patra, Sanjukta

doi:10.2174/2211550105666151222183232

Cited by 7 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such hydrogen bonds are also known as short strong hydrogen bonds with a distance <2.7Å and have been previously reported to increase thermostability of lipases [ 56 ]. It is also worth mentioning here that these results corroborate our previous attempts to relate thermostabilizing features at all the hierarchies of protein organization through machine learning methodologies which revealed that main chain hydrogen bonds, inverse γ-turns and aromatic interactions were important to enhance protein thermostability [ 57 ]. Further, the third and fourth ranks consisted of the total percentage γ-turns (inverse and classic γ-turns) and total hydrogen bonds in a protein respectively.…”

Section: Discussionsupporting

confidence: 88%

“…Individually they may show positive or negative effect but globally their effects can balance out- in comparison to their mesostable counterparts, resulting in a subtler effect. Good examples can be found in the earlier works [ 2 , 54 – 57 ]. This can be observed for the feature of total percentage of hydrogen bonds and its sub-types (main-chain to main-chain, main-chain to side-chain and side-chain to side-chain) and total percentage of γ- turns with its sub-types (classic and inverse).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

RankProt: A multi criteria-ranking platform to attain protein thermostabilizing mutations and its in vitro applications - Attribute based prediction method on the principles of Analytical Hierarchical Process

Chakravorty

Patra

2018

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Attaining recombinant thermostable proteins is still a challenge for protein engineering. The complexity is the length of time and enormous efforts required to achieve the desired results. Present work proposes a novel and economic strategy of attaining protein thermostability by predicting site-specific mutations at the shortest possible time. The success of the approach can be attributed to Analytical Hierarchical Process and the outcome was a rationalized thermostable mutation(s) prediction tool- RankProt. Briefly the method involved ranking of 17 biophysical protein features as class predictors, derived from 127 pairs of thermostable and mesostable proteins. Among the 17 predictors, ionic interactions and main-chain to main-chain hydrogen bonds were the highest ranked features with eigen value of 0.091. The success of the tool was judged by multi-fold in silico validation tests and it achieved the prediction accuracy of 91% with AUC 0.927. Further, in vitro validation was carried out by predicting thermostabilizing mutations for mesostable Bacillus subtilis lipase and performing the predicted mutations by multi-site directed mutagenesis. The rationalized method was successful to render the lipase thermostable with optimum temperature stability and Tm increase by 20°C and 7°C respectively. Conclusively it can be said that it was the minimum number of mutations in comparison to the number of mutations incorporated to render Bacillus subtilis lipase thermostable, by directed evolution techniques. The present work shows that protein stabilizing mutations can be rationally designed by balancing the biophysical pleiotropy of proteins, in accordance to the selection pressure.

show abstract

Section: Discussionsupporting

confidence: 88%

Section: Discussionmentioning

confidence: 99%

RankProt: A multi criteria-ranking platform to attain protein thermostabilizing mutations and its in vitro applications - Attribute based prediction method on the principles of Analytical Hierarchical Process

Chakravorty

Patra

2018

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…This sequence is naturally the obvious target to probe for structural and functional differences. Indeed, the use of sequence information to analyse thermal behaviour is a quite common approach and follows two main themes (Haney et al (1999b); Chakravorty et al (2017); Gao and Ding (2017)).…”

Section: Sequence-based Features (Sf)mentioning

confidence: 99%

“…Amino acid composition of a protein refers to frequencies of each of 20 amino acids (normalized with respect to the total number of amino acids in the protein) that appear in a protein. This is the most common sequence feature of proteins that is used for thermal stability analysis (Chakravorty et al (2017), Gao and Ding (2017)). We optimized further by only considering the normalized frequencies of Alanine (A), Glutamine (Q), Glutamic acid (E), Histidine (H), Threonine (T).…”

Section: Amino Acid Composition (Aac)mentioning

confidence: 99%

“…They reported 90.4% accuracy (area under ROC was 0.96 and MCC was 0.81) by using network features along with amino acid and di-peptide composition frequencies. Chakravorty et al (2017) applied numerous machine learning techniques using three different aspects of proteins: nucleotide sequence, amino-acid composition and structural configuration. They marked the importance of amino acid composition over nucleotide sequences and structural configuration as a feature to be used for classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Supervised learning of protein thermal stability using sequence mining and distribution statistics of network centrality

Sharma

Bagler

Bera

2019

Preprint

View full text Add to dashboard Cite

Motivation:It is expected that the difference in the thermal stability of mesophilic and thermophilic proteins arises, in part at least, from the differences in their molecular structures and amino acid compositions. Existing machine learning approaches for supervised classification of proteins rely on the features derived from the structural networks and the amino acid sequences. However, the network features used leave out several important network centrality values, the statistic used is a simple average and the sequence features used are hand-picked leading to an accuracy of 90%. Results: We show that discriminating sub-sequences of the amino acid sequences can significantly improve classification accuracy compared to the existing approaches of counting amino acids, di-peptide or even tri-peptide bonds. We identify notions of network centrality, specifically that depends on the distances between Cα atoms, that appears to correlate better with thermal stability compared to the existing network features. We also show how to generate better statistics from the node-and edge-wise centrality values that more accurately captures the variations in their values for different types of proteins. These improved feature selection techniques make it possible to classify between thermophilic and mesophilic proteins with 96% accuracy and 99% area under ROC.

show abstract

Unravelling and Quantifying the Biophysical– Biochemical Descriptors Governing Protein Thermostability by Machine Learning

Kumar

Duggineni

Singhania

et al. 2023

Advcd Theory and Sims

View full text Add to dashboard Cite

Analysis of protein thermostability is vital in protein science to aid the understanding of evolutionary aspects of organic life as well as in protein engineering for modern day industrial applications. In the present study, supervised machine learning (ML) algorithms are employed to unravel potential patterns behind protein thermostability. This computational analysis conclusively shows inverse gamma turns, VIII turns, and the propensity of cysteine (Cys) to be the most important biophysical–biochemical attributes responsible for protein thermostability. From the propensity analysis of amino acids, polar residues, specifically glutamine (Gln) and serine (Ser), and charged residues, specifically glutamic acid (Glu) and lysine (Lys), are found to favor the enhancement of protein thermostability. The study demonstrates the feasibility of assigning quantifiable descriptors of thermostability which is expected to aid protein engineering.

show abstract

Thermostability of Proteins Revisited Through Machine Learning Methodologies: From Nucleotide Sequence to Structure

Cited by 7 publications

References 0 publications

RankProt: A multi criteria-ranking platform to attain protein thermostabilizing mutations and its in vitro applications - Attribute based prediction method on the principles of Analytical Hierarchical Process

RankProt: A multi criteria-ranking platform to attain protein thermostabilizing mutations and its in vitro applications - Attribute based prediction method on the principles of Analytical Hierarchical Process

Supervised learning of protein thermal stability using sequence mining and distribution statistics of network centrality

Unravelling and Quantifying the Biophysical– Biochemical Descriptors Governing Protein Thermostability by Machine Learning

Contact Info

Product

Resources

About