HIVCoR: A sequence-based tool for predicting HIV-1 CRF01_AE coreceptor usage

Determination of HIV-1 coreceptor usage is strongly recommended before starting the coreceptor-specific inhibitors for HIV treatment. Currently, the genotypic assays are the most interesting tools due to they are more feasible than phenotypic assays. However, most of prediction models were developed and validated by data set of HIV-1 subtype B and C. The present study aims to develop a powerful and reliable model to accurately predict HIV-1 coreceptor usage for CRF01_AE subtype called HIVCoR. HIVCoR utilized random forest and support vector machine as the prediction model, together with amino acid compositions, pseudo amino acid compositions and relative synonymous codon usage frequencies as the input feature. The overall success rate of 93.79% was achieved from the external validation test on the objective benchmark dataset. Comparison results indicated that HIVCoR was superior to other bioinformatics tools and genotypic predictors. For the convenience of experimental scientists, a user-friendly webserver has been established at http://codes.bio/hivcor/.

[1]  Jeerayut Chaijaruwanich,et al.  HIV-1 CRF01_AE coreceptor usage prediction using kernel methods based logistic model trees , 2012, Comput. Biol. Medicine.

[2]  J. Sodroski,et al.  Contribution of the gp120 V3 loop to envelope glycoprotein trimer stability in primate immunodeficiency viruses , 2018, Virology.

[3]  Jeerayut Chaijaruwanich,et al.  Sequence based human leukocyte antigen gene prediction using informative physicochemical properties , 2015, Int. J. Data Min. Bioinform..

[4]  P. Massip,et al.  Genotypic Prediction of Human Immunodeficiency Virus Type 1 CRF02-AG Tropism , 2009, Journal of Clinical Microbiology.

[5]  D. Ho,et al.  Genotypic and phenotypic characterization of HIV-1 patients with primary infection. , 1993, Science.

[6]  Bette Korber,et al.  Structure of a V3-Containing HIV-1 gp120 Core , 2005, Science.

[7]  N. Heveker,et al.  Effect of Mutations in the Second Extracellular Loop of CXCR4 on Its Utilization by Human and Feline Immunodeficiency Viruses , 1999, Journal of Virology.

[8]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[9]  Virapong Prachayasittikul,et al.  HemoPred: a web server for predicting the hemolytic activity of peptides. , 2017, Future medicinal chemistry.

[10]  B. Korber,et al.  A new classification for HIV-1 , 1998, Nature.

[11]  Apilak Worachartcheewan,et al.  On the Origins of Hepatitis C Virus NS5B Polymerase Inhibitory Activity Using Machine Learning Approaches. , 2015, Current topics in medicinal chemistry.

[12]  John P. Moore,et al.  Stabilization of the gp120 V3 loop through hydrophobic interactions reduces the immunodominant V3-directed non-neutralizing response to HIV-1 envelope trimers , 2017, The Journal of Biological Chemistry.

[13]  J. Goudsmit,et al.  Minimal requirements for the human immunodeficiency virus type 1 V3 domain to support the syncytium-inducing phenotype: analysis by single amino acid substitution , 1992, Journal of virology.

[14]  Ola Spjuth,et al.  Towards Predicting the Cytochrome P450 Modulation: From QSAR to Proteochemometric Modeling. , 2017, Current drug metabolism.

[15]  M. Poljak,et al.  Global Dispersal Pattern of HIV Type 1 Subtype CRF01_AE: A Genetic Trace of Human Mobility Related to Heterosexual Sexual Activities Centralized in Southeast Asia. , 2015, The Journal of infectious diseases.

[16]  Virapong Prachayasittikul,et al.  Prediction of aromatase inhibitory activity using the efficient linear method (ELM) , 2015, EXCLI journal.

[17]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[18]  D. Richman,et al.  The impact of the syncytium-inducing phenotype of human immunodeficiency virus on disease progression. , 1994, The Journal of infectious diseases.

[19]  Oliver Hartley,et al.  V3: HIV's switch-hitter. , 2005, AIDS research and human retroviruses.

[20]  D. Struck,et al.  HIV-1 Tropism Determination Using a Phenotypic Env Recombinant Viral Assay Highlights Overestimation of CXCR4-Usage by Genotypic Prediction Algorithms for CRRF01_AE and CRF02_AG , 2013, PloS one.

[21]  Virapong Prachayasittikul,et al.  CryoProtect: A Web Server for Classifying Antifreeze Proteins from Nonantifreeze Proteins , 2017 .

[22]  J. Sodroski,et al.  A V3 Loop-Dependent gp120 Element Disrupted by CD4 Binding Stabilizes the Human Immunodeficiency Virus Envelope Glycoprotein Trimer , 2010, Journal of Virology.

[23]  Virapong Prachayasittikul,et al.  osFP: a web server for predicting the oligomeric states of fluorescent proteins , 2016, Journal of Cheminformatics.

[24]  I. Keet,et al.  Prognostic Value of HIV-1 Syncytium-Inducing Phenotype for Rate of CD4+ Cell Depletion and Progression to AIDS , 1993, Annals of Internal Medicine.

[25]  Dmitrij Frishman,et al.  SCOTCH: subtype A coreceptor tropism classification in HIV‐1 , 2018, Bioinform..

[26]  P. Massip,et al.  Genotypic Prediction of HIV-1 CRF01-AE Tropism , 2012, Journal of Clinical Microbiology.

[27]  Jeerayut Chaijaruwanich,et al.  Prediction of the disulphide bonding state of cysteines in proteins using Conditional Random Fields , 2011, Int. J. Data Min. Bioinform..

[28]  R. Swanstrom,et al.  Improved success of phenotype prediction of the human immunodeficiency virus type 1 from envelope variable loop 3 sequence using neural networks. , 2001, Virology.

[29]  Natalia Chueca,et al.  Evaluation of Eight Different Bioinformatics Tools To Predict Viral Tropism in Different Human Immunodeficiency Virus Type 1 Subtypes , 2008, Journal of Clinical Microbiology.

[30]  M. Thomson,et al.  Evaluation of genotypic tropism prediction tests compared with in vitro co-receptor usage in HIV-1 primary isolates of diverse subtypes. , 2012, The Journal of antimicrobial chemotherapy.

[31]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[32]  C. Nantasenamat,et al.  Privileged substructures for anti-sickling activity via cheminformatic analysis , 2018, RSC advances.

[33]  Stephen C. Peiper,et al.  Identification of a major co-receptor for primary isolates of HIV-1 , 1996, Nature.

[34]  Apilak Worachartcheewan,et al.  Predicting Metabolic Syndrome Using the Random Forest Method , 2015, TheScientificWorldJournal.

[35]  Dong-Sheng Cao,et al.  protr/ProtrWeb: R package and web server for generating various numerical representation schemes of protein sequences , 2015, Bioinform..

[36]  Thomas Lengauer,et al.  Structural Descriptors of gp120 V3 Loop for the Prediction of HIV-1 Coreceptor Usage , 2007, PLoS Comput. Biol..

[37]  P. Harrigan,et al.  Reliable Genotypic Tropism Tests for the Major HIV-1 Subtypes , 2015, Scientific Reports.

[38]  K. Chou.  Some remarks on protein attribute prediction and pseudo amino acid composition , 2010, Journal of Theoretical Biology.

[39]  HongjaiseeSayamon,et al.  Effect of Amino Acid Substitutions Within the V3 Region of HIV-1 CRF01_AE on Interaction with CCR5-Coreceptor , 2017 .

[40]  Virapong Prachayasittikul,et al.  Probing the origins of human acetylcholinesterase inhibition via QSAR modeling and molecular docking , 2016, PeerJ.

[41]  Stefano Alcaro,et al.  Identification and Structural Characterization of Novel Genetic Elements in the HIV-1 V3 Loop Regulating Coreceptor Usage , 2011, Antiviral therapy.

[42]  D. Webster,et al.  The utility of different bioinformatics algorithms for genotypic HIV-1 tropism testing in a large clinical cohort with multiple subtypes , 2014, AIDS.

[43]  H. Schuitemaker,et al.  Phenotype-associated sequence variation in the third variable domain of the human immunodeficiency virus type 1 gp120 molecule , 1992, Journal of virology.

[44]  Thomas Lengauer,et al.  Bioinformatics prediction of HIV coreceptor usage , 2007, Nature Biotechnology.

[45]  Kitsana Waiyamai,et al.  Prediction of human leukocyte antigen gene using k-nearest neighbour classifier based on spectrum kernel , 2013 .

[46]  Shungao Xu,et al.  Improved prediction of coreceptor usage and phenotype of HIV-1 based on combined features of V3 loop sequence using random forest. , 2007, Journal of microbiology.

[47]  G. Fogel,et al.  Prediction of R5, X4, and R5X4 HIV-1 Coreceptor Usage with Evolved Neural Networks , 2008, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[48]  M. Churchill,et al.  CoRSeqV3-C: a novel HIV-1 subtype C specific V3 sequence based coreceptor usage prediction algorithm , 2013, Retrovirology.

[49]  P. Massip,et al.  Genotypic prediction of HIV-1 subtype D tropism , 2011, Retrovirology.

[50]  Shinn-Ying Ho,et al.  SCMCRYS: Predicting Protein Crystallization Using an Ensemble Scoring Card Method with Estimating Propensity Scores of P-Collocated Amino Acid Pairs , 2013, PloS one.

[51]  D. Spandidos,et al.  Electrostatic modeling of peptides derived from the V3-loop of HIV-1 gp120: implications of the interaction with chemokine receptor CCR5. , 2007, International journal of molecular medicine.

[52]  J. Margolick,et al.  Improved Coreceptor Usage Prediction and GenotypicMonitoring of R5-to-X4 Transition by Motif Analysis of HumanImmunodeficiency Virus Type 1 env V3 LoopSequences , 2003, Journal of Virology.

[53]  Chang Liu,et al.  Detecting and understanding genetic and structural features in HIV-1 B subtype V3 underlying HIV-1 co-receptor usage , 2013, Bioinform..

[54]  Virapong Prachayasittikul,et al.  Navigating the chemical space of dipeptidyl peptidase-4 inhibitors , 2015, Drug design, development and therapy.

[55]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[56]  Virapong Prachayasittikul,et al.  Exploring the chemical space of influenza neuraminidase inhibitors , 2016, PeerJ.

[57]  Sébastien Lê,et al.  FactoMineR: An R Package for Multivariate Analysis , 2008 .

[58]  François Laviolette,et al.  HIV-1 coreceptor usage prediction without multiple alignments: an application of string kernels , 2008, Retrovirology.

[59]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .