PhoglyStruct: prediction of phosphoglycerylated lysine residues using structural properties of amino acids

Abel Chandra, Alok Sharma, Abdollah Dehzangi, Shoba Ranganathan, Anjeela Jokhan, Kuo-Chen Chou, Tatsuhiko Tsunoda

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct.

LanguageEnglish
Article number17923
Pages1-11
Number of pages11
JournalScientific Reports
Volume8
DOIs
Publication statusPublished - 18 Dec 2018

Fingerprint

Lysine
Amino Acids
Biological Phenomena
Benchmarking
Neural Networks (Computer)
Proteome
Post Translational Protein Processing
Area Under Curve
Cell Biology
Software
Sensitivity and Specificity
Proteins

Bibliographical note

Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Cite this

Chandra, Abel ; Sharma, Alok ; Dehzangi, Abdollah ; Ranganathan, Shoba ; Jokhan, Anjeela ; Chou, Kuo-Chen ; Tsunoda, Tatsuhiko. / PhoglyStruct : prediction of phosphoglycerylated lysine residues using structural properties of amino acids. In: Scientific Reports. 2018 ; Vol. 8. pp. 1-11.
@article{3c14ff76457a490f9d87a07b3885dfc2,
title = "PhoglyStruct: prediction of phosphoglycerylated lysine residues using structural properties of amino acids",
abstract = "The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct.",
author = "Abel Chandra and Alok Sharma and Abdollah Dehzangi and Shoba Ranganathan and Anjeela Jokhan and Kuo-Chen Chou and Tatsuhiko Tsunoda",
note = "Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2018",
month = "12",
day = "18",
doi = "10.1038/s41598-018-36203-8",
language = "English",
volume = "8",
pages = "1--11",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Springer, Springer Nature",

}

PhoglyStruct : prediction of phosphoglycerylated lysine residues using structural properties of amino acids. / Chandra, Abel; Sharma, Alok; Dehzangi, Abdollah; Ranganathan, Shoba; Jokhan, Anjeela; Chou, Kuo-Chen; Tsunoda, Tatsuhiko.

In: Scientific Reports, Vol. 8, 17923, 18.12.2018, p. 1-11.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - PhoglyStruct

T2 - Scientific Reports

AU - Chandra, Abel

AU - Sharma, Alok

AU - Dehzangi, Abdollah

AU - Ranganathan, Shoba

AU - Jokhan, Anjeela

AU - Chou, Kuo-Chen

AU - Tsunoda, Tatsuhiko

N1 - Copyright the Author(s) 2018. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2018/12/18

Y1 - 2018/12/18

N2 - The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct.

AB - The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct.

UR - http://www.scopus.com/inward/record.url?scp=85058747730&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-36203-8

DO - 10.1038/s41598-018-36203-8

M3 - Article

VL - 8

SP - 1

EP - 11

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 17923

ER -