HIV-1 Coreceptor Usage Prediction via Indexed Local Kernel Smoothing Methods and Grid-Based Multiple Statistical Validation

Human immunodeficiency virus type 1 (HIV-1) isolates differ in their use of coreceptors to enter target cells. This has important implications for both viral pathogenicity and susceptibility to entry inhibitors under development. Predicting HIV-1 coreceptor usage on the basis of sequence information is a challenging task due to the high variability of the HIV-1 genome. We present an efficient local smoothing kernel method, enhanced with a BLAST-based distance function, implemented by usage of multithreading grid procedures and indexing. Robust validation of the model is achieved through multiple cross-validation, along with statistical comparisons of results for performance assessment.