HIV-1 coreceptor usage prediction without multiple alignments: an application of string kernels

BackgroundHuman immunodeficiency virus type 1 (HIV-1) infects cells by means of ligand-receptor interactions. This lentivirus uses the CD4 receptor in conjunction with a chemokine coreceptor, either CXCR4 or CCR5, to enter a target cell. HIV-1 is characterized by high sequence variability. Nonetheless, within this extensive variability, certain features must be conserved to define functions and phenotypes. The determination of coreceptor usage of HIV-1, from its protein envelope sequence, falls into a well-studied machine learning problem known as classification. The support vector machine (SVM), with string kernels, has proven to be very efficient for dealing with a wide class of classification problems ranging from text categorization to protein homology detection. In this paper, we investigate how the SVM can predict HIV-1 coreceptor usage when it is equipped with an appropriate string kernel.ResultsThree string kernels were compared. Accuracies of 96.35% (CCR5) 94.80% (CXCR4) and 95.15% (CCR5 and CXCR4) were achieved with the SVM equipped with the distant segments kernel on a test set of 1425 examples with a classifier built on a training set of 1425 examples. Our datasets are built with Los Alamos National Laboratory HIV Databases sequences. A web server is available at http://genome.ulaval.ca/hiv-dskernel.ConclusionWe examined string kernels that have been used successfully for protein homology detection and propose a new one that we call the distant segments kernel. We also show how to extract the most relevant features for HIV-1 coreceptor usage. The SVM with the distant segments kernel is currently the best method described.

• Publication year

  2008

• Venue

  Retrovirology

• Publication date

  2008-12-04

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1186/1742-4690-5-110PMID 19055831PMCID 2637298
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• R5 and X4 HIV Viruses Differentially Modulate Host Gene Expression in Resting CD4+ T Cells

  2008cited by this paper
• Correlation between genotypic predictions based on V3 sequences and phenotypic determination of HIV-1 tropism

  2008cited by this paper
• Bioinformatic Prediction Programs Underestimate the Frequency of CXCR4 Usage by R5X4 HIV Type 1 in Brain and Other Tissues

  2008cited by this paper
• Prediction of R5, X4, and R5X4 HIV-1 Coreceptor Usage with Evolved Neural Networks

  2008cited by this paper
• Improved prediction of coreceptor usage and phenotype of HIV-1 based on combined features of V3 loop sequence using random forest.

  2007cited by this paper
• Structural Descriptors of gp120 V3 Loop for the Prediction of HIV-1 Coreceptor Usage

  2007cited by this paper
• Bioinformatics prediction of HIV coreceptor usage

  2007cited by this paper
• Predicting HIV Coreceptor Usage on the Basis of Genetic and Clinical Covariates

  2007cited by this paper
• Determining Human Immunodeficiency Virus Coreceptor Use in a Clinical Setting: Degree of Correlation between Two Phenotypic Assays and a Bioinformatic Model

  2006cited by this paper
• A Reliable Phenotype Predictor for Human Immunodeficiency Virus Type 1 Subtype C Based on Envelope V3 Sequences

  2006cited by this paper
• Remote homology detection based on oligomer distances

  2006influential reference
• Tutorial on Practical Prediction Theory for Classification

  2005influential reference
• Protein homology detection using string alignment kernels

  2004influential reference
• Kernel Methods for Pattern Analysis

  2004influential reference
• A New Perspective on V3 Phenotype Prediction

  2003influential reference
• Combining Pairwise Sequence Similarity and Support Vector Machines for Detecting Remote Protein Evolutionary and Structural Relationships

  2003cited by this paper
• Improved Coreceptor Usage Prediction and GenotypicMonitoring of R5-to-X4 Transition by Motif Analysis of HumanImmunodeficiency Virus Type 1 env V3 LoopSequences

  2003cited by this paper
• Combining pairwise sequence similarity and support vector machines for remote protein homology detection

  2002cited by this paper
• The Spectrum Kernel: A String Kernel for SVM Protein Classification

  2001cited by this paper
• Improved success of phenotype prediction of the human immunodeficiency virus type 1 from envelope variable loop 3 sequence using neural networks.

  2001cited by this paper
• Advances in kernel methods: support vector learning

  1999cited by this paper
• Making large scale SVM learning practical

  1998cited by this paper
• Statistical learning theory

  1998cited by this paper
• Use of Receiver Operating Characteristic (ROC) Analysis to Evaluate Sequence Matching

  1996cited by this paper
• Support-Vector Networks

  1995cited by this paper
• The impact of the syncytium-inducing phenotype of human immunodeficiency virus on disease progression.

  1994cited by this paper
• V3 loop of the human immunodeficiency virus type 1 Env protein: interpreting sequence variability

  1993cited by this paper
• Selection for specific sequences in the external envelope protein of human immunodeficiency virus type 1 upon primary infection

  1993cited by this paper
• Phenotype-associated sequence variation in the third variable domain of the human immunodeficiency virus type 1 gp120 molecule

  1992cited by this paper
• Bioinformatics Advance Access published January 22, 2004

  year unknowncited by this paper

• Encodings and models for antimicrobial peptide classification for multi-resistant pathogens

  2019cites this paper
• HIVCoR: A sequence-based tool for predicting HIV-1 CRF01_AE coreceptor usage

  2019cites this paper
• Futuristic Methods for Determining HIV Co-receptor Use

  2019cites this paper
• Application of locality sensitive discriminant analysis to predict protein fold pattern

  2017cites this paper
• Current Approaches in Computational Drug Resistance Prediction in HIV.

  2016cites this paper
• HIV coreceptor tropism determination and mutational pattern identification

  2016cites this paper
• Reliable Genotypic Tropism Tests for the Major HIV-1 Subtypes

  2015cites this paper
• Sequence variation and co-receptor tropism prediction of V 3 loop of HIV-1 from Kelantan , Malaysia

  2015influential citation
• Performance of commonly used genotypic assays and comparison with phenotypic assays of HIV-1 coreceptor tropism in acutely HIV-1-infected patients.

  2015cites this paper
• Short report Open Access

  2015cites this paper
• Assemblage adaptatif de génomes et de méta-génomes par passage de messages

  2014cites this paper
• Immunological Recovery After 24 Weeks of Antiretroviral Therapy in Patients With X4 Virus During Primary HIV Infection

  2014cites this paper
• Profile of HIV Type 1 Coreceptor Tropism Among Kenyan Patients from 2009 to 2010

  2013influential citation
• Hybrid Approach for Predicting Coreceptor Used by HIV-1 from Its V3 Loop Amino Acid Sequence

  2013influential citation
• Hierarchical Classification of Protein Folds Using a Novel Ensemble Classifier

  2013cites this paper
• Improved method for predicting protein fold patterns with ensemble classifiers.

  2012cites this paper
• Computational models for prediction of response to antiretroviral therapies.

  2012cites this paper
• Remote protein homology detection and fold recognition using two-layer support vector machine classifiers

  2011cites this paper
• POPISK: T-cell reactivity prediction using support vector machines and string kernels

  2011cites this paper
• Clinical significance of HIV-1 coreceptor usage

  2011cites this paper
• Position 22 of the V3 loop is associated with co-receptor usage and disease progression in HIV-1 subtype B isolates.

  2011cites this paper
• Machine learning on normalized protein sequences

  2011cites this paper
• Prediction of antimicrobial peptides using hyperparameter optimized support vector machines

  2011cites this paper
• Short-term HIV therapy response prediction using sequence information

  2011cites this paper
• Sequence-based prediction of HIV-1 coreceptor usage: utility of n-grams for representing gp120 V3 loops

  2011influential citation
• Recovery of Replication-Competent Residual HIV-1 from Plasma of a Patient Receiving Prolonged, Suppressive Highly Active Antiretroviral Therapy

  2010cites this paper
• HIV-1 Envelope Subregion Length Variation during Disease Progression

  2010cites this paper
• Co-receptor tropism prediction among 1045 Indian HIV-1 subtype C sequences: Therapeutic implications for India

  2010cites this paper
• Learning state machine-based string edit kernels

  2010cites this paper
• Poor performance of bioinformatics programs for genotypic prediction of coreceptor usage of HIV-1 group O isolates.

  2010cites this paper
• Étude transcriptomique de l'effet du VIH-1 sur le système immunitaire : purification de cellules infectées et effets des molécules de l'hôte

  2010cites this paper
• Comparative determination of HIV-1 co-receptor tropism by Enhanced Sensitivity Trofile, gp120 V3-loop RNA and DNA genotyping

  2010cites this paper
• Analysis of Physicochemical Properties on Prediction of R 5 , X 4 and R 5 X 4 HIV-1 Coreceptor Usage

  2009cites this paper
• Comparative analysis of cell culture and prediction algorithms for phenotyping of genetically diverse HIV-1 strains from Cameroon

  2009cites this paper
• Analysis of Physicochemical Properties on Prediction of R5, X4 and R5X4 HIV-1 Coreceptor Usage

  2009cites this paper
• Genotypic analysis of HIV-1 coreceptor usage

  2008cites this paper