Hybrid approach for predicting coreceptor used by HIV-1 from its V3 loop amino acid sequence

Abstract

Background: HIV-1 infects the host cell by interacting with the primary receptor CD4 and a coreceptor CCR5 or CXCR4. Maraviroc, a CCR5 antagonist binds to CCR5 receptor. Thus, it is important to identify the coreceptor used by the HIV strains dominating in the patient. In past, a number of experimental assays and in-silico techniques have been developed for predicting the coreceptor tropism. The prediction accuracy of these methods is excellent when predicting CCR5(R5) tropic sequences but is relatively poor for CXCR4(X4) tropic sequences. Therefore, any new method for accurate determination of coreceptor usage would be of paramount importance to the successful management of HIV-infected individuals.

Results: The dataset used in this study comprised 1799 R5-tropic and 598 X4-tropic third variable (V3) sequences of HIV-1. We compared the amino acid composition of both types of V3 sequences and observed that certain types of residues, e.g., Asparagine and Isoleucine, were preferred in R5-tropic sequences whereas residues like Lysine, Arginine, and Tryptophan were preferred in X4-tropic sequences. Initially, Support Vector Machine-based models were developed using amino acid composition, dipeptide composition, and split amino acid composition, which achieved accuracy up to 90%. We used BLAST to discriminate R5- and X4-tropic sequences and correctly predicted 93.16% of R5- and 75.75% of X4-tropic sequences. In order to improve the prediction accuracy, a Hybrid model was developed that achieved 91.66% sensitivity, 81.77% specificity, 89.19% accuracy and 0.72 Matthews Correlation Coefficient. The performance of our models was also evaluated on an independent dataset (256 R5- and 81 X4-tropic sequences) and achieved maximum accuracy of 84.87% with Matthews Correlation Coefficient 0.63.

Conclusion: This study describes a highly efficient method for predicting HIV-1 coreceptor usage from V3 sequences. In order to provide a service to the scientific community, a webserver HIVcoPred was developed (http://www.imtech.res.in/raghava/hivcopred/) for predicting the coreceptor usage.

Figure 1. Amino acid composition comparisons of two types of V3 sequence.

The Blue bar representing R5-tropic and red bar representing X4-tropic V3 sequences.

Figure 2. The composition of physico-chemical properties of R5- and X4-tropic V3 sequences.

The blue bar representing R5-tropic and red bar representing X4-tropic V3 sequences.

Figure 3. The ROC plots of four SVM models.

Performance of four SVM modules (AAC, DPC, SAAC, Hybrid) by the receiver operating characteristic (ROC) plot. In the graph, ‘A’ signifies the ‘AUC’ value of the respective model.

Figure 4. Sequence logos of R5-tropic (N = 1525) and X4-tropic (N = 408) V3 sequences.

The overall height of the stack indicates the sequences conservation at the specific site, while the height of the symbols within the stack indicates the relative frequency of each amino acid at the specific site. 'N' denotes the number of sequences used in the sequence logos.

Figure 5. The two sample logo of R5- (N = 1525) and X4-tropic (N = 408) V3 sequences.

The residues with significant difference in the frequency in two datasets are prominent at the specific sites. The positions with no residues are those where the frequency of an amino acid was approximately equal in two datasets.

Figure 6. The ROC plot of Binary, TSL and Binary+TSL based SVM models.

Performance of discrimination between the R5- and X4-tropic sequences by three SVM modules in the ROC plot. In the graph, ‘A’ signifies the ‘AUC’ value of the respective models.

Figure 7. Procedure of Modified SVM scores generation by the Hybrid approach.

The SVM score is first generated by SAAC based SVM model. Depending upon the top matched sequences and its E-value (in BLAST output) the SVM score has been modified by 1(+/−), which finally used in the prediction purpose.