Prediction of HIV-1 protease cleavage site using a combination of sequence, structural, and physicochemical features

Onkar Singh, Emily Chia-Yu Su

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Background: The human immunodeficiency virus type 1 (HIV-1) aspartic protease is an important enzyme owing to its imperative part in viral development and a causative agent of deadliest disease known as acquired immune deficiency syndrome (AIDS). Development of HIV-1 protease inhibitors can help understand the specificity of substrates which can restrain the replication of HIV-1, thus antagonize AIDS. However, experimental methods in identification of HIV-1 protease cleavage sites are generally time-consuming and labor-intensive. Therefore, using computational methods to predict cleavage sites has become highly desirable. Results: In this study, we propose a prediction method in which sequence, structural, and physicochemical features are incorporated in various machine learning algorithms. Then, a bidirectional stepwise selection algorithm is incorporated in feature selection to identify discriminative features. Further, only the selected features are calculated by various encoding schemes and used as input for decision trees, logistic regression, and artificial neural networks. Moreover, a more rigorous three-way data split procedure is applied to evaluate the objective performance of cleavage site prediction. Four benchmark datasets collected from previous studies are used to evaluate the predictive performance. Conclusions: Experiment results showed that combinations of sequence, structure, and physicochemical features performed better than single feature type for identification of HIV-1 protease cleavage sites. In addition, incorporation of stepwise feature selection is effective to identify interpretable biological features to depict specificity of the substrates. Moreover, artificial neural networks perform significantly better than the other two classifiers. Finally, the proposed method achieved 80.0%~97.4% in accuracy and 0.815~0.995 evaluated by independent test sets in a three-way data split procedure.

Original languageEnglish
Article number478
JournalBMC Bioinformatics
Volume17
DOIs
Publication statusPublished - Dec 23 2016

Fingerprint

Protease
Viruses
Virus
HIV-1
Peptide Hydrolases
Prediction
Three-way Data
Feature Selection
Specificity
Artificial Neural Network
Feature extraction
Substrate Specificity
Substrate
Acquired Immunodeficiency Syndrome
Neural networks
Evaluate
Benchmarking
Substrates
Test Set
Decision Trees

Keywords

  • Cleavage sites
  • HIV-1 protease
  • Machine learning
  • Physicochemical properties
  • Pseudo amino acid composition
  • Sequence features
  • Structural features

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

@article{2d00e70ab27e4036b70666fe02d5ae4f,
title = "Prediction of HIV-1 protease cleavage site using a combination of sequence, structural, and physicochemical features",
abstract = "Background: The human immunodeficiency virus type 1 (HIV-1) aspartic protease is an important enzyme owing to its imperative part in viral development and a causative agent of deadliest disease known as acquired immune deficiency syndrome (AIDS). Development of HIV-1 protease inhibitors can help understand the specificity of substrates which can restrain the replication of HIV-1, thus antagonize AIDS. However, experimental methods in identification of HIV-1 protease cleavage sites are generally time-consuming and labor-intensive. Therefore, using computational methods to predict cleavage sites has become highly desirable. Results: In this study, we propose a prediction method in which sequence, structural, and physicochemical features are incorporated in various machine learning algorithms. Then, a bidirectional stepwise selection algorithm is incorporated in feature selection to identify discriminative features. Further, only the selected features are calculated by various encoding schemes and used as input for decision trees, logistic regression, and artificial neural networks. Moreover, a more rigorous three-way data split procedure is applied to evaluate the objective performance of cleavage site prediction. Four benchmark datasets collected from previous studies are used to evaluate the predictive performance. Conclusions: Experiment results showed that combinations of sequence, structure, and physicochemical features performed better than single feature type for identification of HIV-1 protease cleavage sites. In addition, incorporation of stepwise feature selection is effective to identify interpretable biological features to depict specificity of the substrates. Moreover, artificial neural networks perform significantly better than the other two classifiers. Finally, the proposed method achieved 80.0{\%}~97.4{\%} in accuracy and 0.815~0.995 evaluated by independent test sets in a three-way data split procedure.",
keywords = "Cleavage sites, HIV-1 protease, Machine learning, Physicochemical properties, Pseudo amino acid composition, Sequence features, Structural features",
author = "Onkar Singh and Su, {Emily Chia-Yu}",
year = "2016",
month = "12",
day = "23",
doi = "10.1186/s12859-016-1337-6",
language = "English",
volume = "17",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Prediction of HIV-1 protease cleavage site using a combination of sequence, structural, and physicochemical features

AU - Singh, Onkar

AU - Su, Emily Chia-Yu

PY - 2016/12/23

Y1 - 2016/12/23

N2 - Background: The human immunodeficiency virus type 1 (HIV-1) aspartic protease is an important enzyme owing to its imperative part in viral development and a causative agent of deadliest disease known as acquired immune deficiency syndrome (AIDS). Development of HIV-1 protease inhibitors can help understand the specificity of substrates which can restrain the replication of HIV-1, thus antagonize AIDS. However, experimental methods in identification of HIV-1 protease cleavage sites are generally time-consuming and labor-intensive. Therefore, using computational methods to predict cleavage sites has become highly desirable. Results: In this study, we propose a prediction method in which sequence, structural, and physicochemical features are incorporated in various machine learning algorithms. Then, a bidirectional stepwise selection algorithm is incorporated in feature selection to identify discriminative features. Further, only the selected features are calculated by various encoding schemes and used as input for decision trees, logistic regression, and artificial neural networks. Moreover, a more rigorous three-way data split procedure is applied to evaluate the objective performance of cleavage site prediction. Four benchmark datasets collected from previous studies are used to evaluate the predictive performance. Conclusions: Experiment results showed that combinations of sequence, structure, and physicochemical features performed better than single feature type for identification of HIV-1 protease cleavage sites. In addition, incorporation of stepwise feature selection is effective to identify interpretable biological features to depict specificity of the substrates. Moreover, artificial neural networks perform significantly better than the other two classifiers. Finally, the proposed method achieved 80.0%~97.4% in accuracy and 0.815~0.995 evaluated by independent test sets in a three-way data split procedure.

AB - Background: The human immunodeficiency virus type 1 (HIV-1) aspartic protease is an important enzyme owing to its imperative part in viral development and a causative agent of deadliest disease known as acquired immune deficiency syndrome (AIDS). Development of HIV-1 protease inhibitors can help understand the specificity of substrates which can restrain the replication of HIV-1, thus antagonize AIDS. However, experimental methods in identification of HIV-1 protease cleavage sites are generally time-consuming and labor-intensive. Therefore, using computational methods to predict cleavage sites has become highly desirable. Results: In this study, we propose a prediction method in which sequence, structural, and physicochemical features are incorporated in various machine learning algorithms. Then, a bidirectional stepwise selection algorithm is incorporated in feature selection to identify discriminative features. Further, only the selected features are calculated by various encoding schemes and used as input for decision trees, logistic regression, and artificial neural networks. Moreover, a more rigorous three-way data split procedure is applied to evaluate the objective performance of cleavage site prediction. Four benchmark datasets collected from previous studies are used to evaluate the predictive performance. Conclusions: Experiment results showed that combinations of sequence, structure, and physicochemical features performed better than single feature type for identification of HIV-1 protease cleavage sites. In addition, incorporation of stepwise feature selection is effective to identify interpretable biological features to depict specificity of the substrates. Moreover, artificial neural networks perform significantly better than the other two classifiers. Finally, the proposed method achieved 80.0%~97.4% in accuracy and 0.815~0.995 evaluated by independent test sets in a three-way data split procedure.

KW - Cleavage sites

KW - HIV-1 protease

KW - Machine learning

KW - Physicochemical properties

KW - Pseudo amino acid composition

KW - Sequence features

KW - Structural features

UR - http://www.scopus.com/inward/record.url?scp=85006866989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006866989&partnerID=8YFLogxK

U2 - 10.1186/s12859-016-1337-6

DO - 10.1186/s12859-016-1337-6

M3 - Article

C2 - 28155640

AN - SCOPUS:85006866989

VL - 17

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

M1 - 478

ER -