Dataset Information

Prediction of R5, X4, and R5X4 HIV-1 coreceptor usage with evolved neural networks.

ABSTRACT: The HIV-1 genome is highly heterogeneous. This variation affords the virus a wide range of molecular properties, including the ability to infect cell types, such as macrophages and lymphocytes, expressing different chemokine receptors on the cell surface. In particular, R5 HIV-1 viruses use CCR5 as co-receptor for viral entry, X4 viruses use CXCR4, whereas some viral strains, known as R5X4 or D-tropic, have the ability to utilize both co-receptors. X4 and R5X4 viruses are associated with rapid disease progression to AIDS. R5X4 viruses differ in that they have yet to be characterized by the examination of the genetic sequence of HIV-1 alone. In this study, a series of experiments was performed to evaluate different strategies of feature selection and neural network optimization. We demonstrate the use of artificial neural networks trained via evolutionary computation to predict viral co-receptor usage. The results indicate identification of R5X4 viruses with predictive accuracy of 75.5%.

SUBMITTER: Lamers SL

PROVIDER: S-EPMC3523352 | biostudies-literature | 2008 Apr-Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of R5, X4, and R5X4 HIV-1 coreceptor usage with evolved neural networks.

Lamers Susanna L SL Salemi Marco M McGrath Michael S MS Fogel Gary B GB

IEEE/ACM transactions on computational biology and bioinformatics 20080401 2

The HIV-1 genome is highly heterogeneous. This variation affords the virus a wide range of molecular properties, including the ability to infect cell types, such as macrophages and lymphocytes, expressing different chemokine receptors on the cell surface. In particular, R5 HIV-1 viruses use CCR5 as co-receptor for viral entry, X4 viruses use CXCR4, whereas some viral strains, known as R5X4 or D-tropic, have the ability to utilize both co-receptors. X4 and R5X4 viruses are associated with rapid d ...[more]

PMID: 18451438

Similar Datasets

Project description:BackgroundHIV-1 is decorated with trimeric glycoprotein spikes that enable infection by engaging CD4 and a chemokine coreceptor, either CCR5 or CXCR4. The variable loop 3 (V3) of the HIV-1 envelope protein (Env) is the main determinant for coreceptor usage. The predominant CCR5 using (R5) HIV-1 Env has been intensively studied in function and structure, whereas the trimeric architecture of the less frequent, but more cytopathic CXCR4 using (X4) HIV-1 Env is largely unknown, as are the consequences of sequence changes in and near V3 on antigenicity and trimeric Env structure.ResultsSoluble trimeric gp140 Env constructs were used as immunogenic mimics of the native spikes to analyze their antigenic properties in the context of their overall 3D structure. We generated soluble, uncleaved, gp140 trimers from a prototypic T-cell line-adapted (TCLA) X4 HIV-1 strain (NL4-3) and a hybrid (NL4-3/ADA), in which the V3 spanning region was substituted with that from the primary R5 isolate ADA. Compared to an ADA (R5) gp140, the NL4-3 (X4) construct revealed an overall higher antibody accessibility, which was most pronounced for the CD4 binding site (CD4bs), but also observed for mAbs against CD4 induced (CD4i) epitopes and gp41 mAbs. V3 mAbs showed significant binding differences to the three constructs, which were refined by SPR analysis. Of interest, the NL4-3/ADA construct with the hybrid NL4-3/ADA CD4bs showed impaired CD4 and CD4bs mAb reactivity despite the presence of the essential elements of the CD4bs epitope. We obtained 3D reconstructions of the NL4-3 and the NL4-3/ADA gp140 trimers via electron microscopy and single particle analysis, which indicates that both constructs inherit a propeller-like architecture. The first 3D reconstruction of an Env construct from an X4 TCLA HIV-1 strain reveals an open conformation, in contrast to recently published more closed structures from R5 Env. Exchanging the X4 V3 spanning region for that of R5 ADA did not alter the open Env architecture as deduced from its very similar 3D reconstruction.Conclusions3D EM analysis showed an apparent open trimer configuration of X4 NL4-3 gp140 that is not modified by exchanging the V3 spanning region for R5 ADA.

Project description:HIV-1 cell entry commonly uses, in addition to CD4, one of the chemokine receptors CCR5 or CXCR4 as coreceptor. Knowledge of coreceptor usage is critical for monitoring disease progression as well as for supporting therapy with the novel drug class of coreceptor antagonists. Predictive methods for inferring coreceptor usage based on the third hypervariable (V3) loop region of the viral gene coding for the envelope protein gp120 can provide us with these monitoring facilities while avoiding expensive phenotypic tests. All simple heuristics (such as the 11/25 rule) as well as statistical learning methods proposed to date predict coreceptor usage based on sequence features of the V3 loop exclusively. Here, we show, based on a recently resolved structure of gp120 with an untruncated V3 loop, that using structural information on the V3 loop in combination with sequence features of V3 variants improves prediction of coreceptor usage. In particular, we propose a distance-based descriptor of the spatial arrangement of physicochemical properties that increases discriminative performance. For a fixed specificity of 0.95, a sensitivity of 0.77 was achieved, improving further to 0.80 when combined with a sequence-based representation using amino acid indicators. This compares favorably with the sensitivities of 0.62 for the traditional 11/25 rule and 0.73 for a prediction based on sequence information as input to a support vector machine and constitutes a statistically significant improvement. A detailed analysis and interpretation of structural features important for classification shows the relevance of several specific hydrogen-bond donor sites and aliphatic side chains to coreceptor specificity towards CCR5 or CXCR4. Furthermore, an analysis of side chain orientation of the specificity-determining residues suggests a major role of one side of the V3 loop in the selection of the coreceptor. The proposed method constitutes the first approach to an improved prediction of coreceptor usage based on an original integration of structural bioinformatics methods with statistical learning.

Dataset Information

Prediction of R5, X4, and R5X4 HIV-1 coreceptor usage with evolved neural networks.

Publications

Prediction of R5, X4, and R5X4 HIV-1 coreceptor usage with evolved neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets