Abstract
BackgroundLinear regression models are used to quantitatively predict drug resistance, the phenotype, from the HIV-1 viral genotype. As new antiretroviral drugs become available, new resistance pathways emerge and the number of resistance associated mutations continues to increase. To accurately identify which drug options are left, the main goal of the modeling has been to maximize predictivity and not interpretability. However, we originally selected linear regression as the preferred method for its transparency as opposed to other techniques such as neural networks. Here, we apply a method to lower the complexity of these phenotype prediction models using a 3-fold cross-validated selection of mutations.ResultsCompared to standard stepwise regression we were able to reduce the number of mutations in the reverse transcriptase (RT) inhibitor models as well as the number of interaction terms accounting for synergistic and antagonistic effects. This reduction in complexity was most significant for the non-nucleoside reverse transcriptase inhibitor (NNRTI) models, while maintaining prediction accuracy and retaining virtually all known resistance associated mutations as first order terms in the models. Furthermore, for etravirine (ETR) a better performance was seen on two years of unseen data. By analyzing the phenotype prediction models we identified a list of forty novel NNRTI mutations, putatively associated with resistance. The resistance association of novel variants at known NNRTI resistance positions: 100, 101, 181, 190, 221 and of mutations at positions not previously linked with NNRTI resistance: 102, 139, 219, 241, 376 and 382 was confirmed by phenotyping site-directed mutants.ConclusionsWe successfully identified and validated novel NNRTI resistance associated mutations by developing parsimonious resistance prediction models in which repeated cross-validation within the stepwise regression was applied. Our model selection technique is computationally feasible for large data sets and provides an approach to the continued identification of resistance-causing mutations.
Highlights
Linear regression models are used to quantitatively predict drug resistance, the phenotype, from the HIV-1 viral genotype
Reverse Transcriptase Inhibitors For the reverse transcriptase inhibitors (RTI) a 3F model with lower complexity than the reference was found for AZT, 3TC, d4T, ABC, FTC, NVP, EFV and ETR (Table 1)
For the nucleoside reverse transcriptase inhibitors (NRTI) class of drugs the reduction in interaction terms and mutations used in 3F versus reference was 20.3% and 11.9%, respectively
Summary
Linear regression models are used to quantitatively predict drug resistance, the phenotype, from the HIV-1 viral genotype. We apply a method to lower the complexity of these phenotype prediction models using a 3-fold cross-validated selection of mutations. Linear regression models have been shown to be accurate in predicting drug susceptibility from the HIV-1 viral genotype, by calculating the inhibitory concentration 50% (IC50) log Fold-Change (FC) phenotype as a linear combination of parameters, which are mutations [1,2,3] and interaction terms (mutation pairs) [1]. Since June 2006, VirtualPhenotypeTM-LM has been a linear regression model that predicts the log FC based on mutations (first-order terms) and mutation pairs (second-order interaction terms accounting for synergistic and antagonistic effects). To evaluate the generalizability of the models, the prediction error was calculated on genotypes in an unseen data set with available measured phenotypes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
