Quantitative prediction of integrase inhibitor resistance from genotype through consensus linear regression modeling

Borght, Koen Van der; Verheyen, Ann; Feyaerts, Maxim; Wesenbeeck, Liesbeth Van; Verlinden, Yvan; Craenenbroeck, Elke Van; Vlijmen, Herman van

doi:10.1186/1743-422x-10-8

Cited by 9 publications

(19 citation statements)

References 26 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, based on the implementation of the REPTree algorithm with LOOCV testing on the 13-dimensional IN mutant feature vectors, Figure 5 displays a scatter plot of actual and predicted RAL log 10 (FC) values for the 202 IN mutants in the dataset. Only a single study on predictive models of RAL resistance could be identified in the literature [16], one that is sequence-based and involves consensus linear regression utilizing a genetic algorithm, which reports a validation R 2 correlation of 0.80 (r = 0.89) that is comparable to what is achieved here with our REPTree regression models. …”

Section: Regressionsupporting

confidence: 65%

“…Figure 2 (adapted from [16]) displays both a distribution of these phenotypes as well as the RAL biological cutoff of FC = 2.0 (or log 10 …”

Section: Ral Susceptibility and In Attributesmentioning

confidence: 99%

“…Genotype testing consists of identifying single mutations within a patient's viral sequences that are known to be associated with drug resistance, while phenotype testing quantifies the degree to which a drug inhibits a mutated HIV-1 target protein as compared to its wild-type, fully susceptible counterpart. Although genotypic tests can be executed rapidly at relatively low cost, phenotypic tests are advantageous with respect to complex mutational patterns, leading to heightened interest in models for accurately predicting phenotype from genotype [16].…”

Section: Introductionmentioning

confidence: 99%

“…The susceptibility of each mutant IN protein to RAL was reported as a fold change (FC) value obtained using the PhenoSense assay (Monogram Biosciences, South San Francisco, CA) [11], a quantity calculated to be the ratio of 50% inhibitory concentration (IC 50 ) for the mutant relative to that for a drug-sensitive, wild-type control. The IN mutants were classified as susceptible (FC ≤ 2.0) or resistant (FC > 2.0) to RAL based on a previously established biological cutoff [15,16], yielding 124 resistant (R) and 78 susceptible (S) IN mutants. All FC values were log-transformed prior to analysis.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fast and Accurate Structure-Based Prediction of Resistance to the HIV-1 Integrase Inhibitor Raltegravir

Masso

2013

Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics

View full text Add to dashboard Cite

Integration of reverse transcribed viral DNA into the human genome represents an essential step in the replication cycle of HIV-1, a process mediated by the viral enzyme integrase (IN). Raltegravir (RAL), an HIV-1 strand transfer inhibitor that binds integrase, is the first drug in its class to be approved for clinical use. As with HIV-1 protease and reverse transcriptase inhibitors, the degree of susceptibility to RAL can vary in patients due to mutations in the viral genome region that encodes IN. Employing a dataset of over two hundred translated IN sequences, each with a quantified susceptibility value and harboring a unique set of amino acid replacements relative to the native IN, here we develop and evaluate statistical learning models for predicting phenotype (i.e., RAL susceptibility) from genotype (i.e., translated IN sequences). Each IN mutant is represented as a feature vector of structure-based attributes obtained via an in silico mutagenesis approach that quantifies IN residue-specific environmental perturbations upon mutation. Cross-validated performance is consistent among four classification models (random forest, support vector machine, decision tree, and neural network), with balanced accuracy reaching 93%, and two regression models (reduced-error pruned tree, and support vector regression), with a correlation coefficient as high as r = 0.90.

show abstract

Section: Regressionsupporting

confidence: 65%

“…Figure 2 (adapted from [16]) displays both a distribution of these phenotypes as well as the RAL biological cutoff of FC = 2.0 (or log 10 …”

Section: Ral Susceptibility and In Attributesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast and Accurate Structure-Based Prediction of Resistance to the HIV-1 Integrase Inhibitor Raltegravir

Masso

2013

Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…In this article we extend our genetic algorithm (GA) variable selection methodology in [5] to allow for clustering in the data. We compare the performance of multi-model inference (MMI) using restricted maximum likelihood (REML) mixed-effects modeling [6,7] (MM) with ordinary least squares regression [8] (OLS) and compare GA-MMI with the commonly used penalized regression method Least Absolute Shrinkage and Selection Operator [9] (LASSO).…”

Section: Introductionmentioning

confidence: 99%

Multi-model inference using mixed effects from a linear regression based genetic algorithm

2014

Self Cite

View full text Add to dashboard Cite

BackgroundDifferent high-dimensional regression methodologies exist for the selection of variables to predict a continuous variable. To improve the variable selection in case clustered observations are present in the training data, an extension towards mixed-effects modeling (MM) is requested, but may not always be straightforward to implement.In this article, we developed such a MM extension (GA-MM-MMI) for the automated variable selection by a linear regression based genetic algorithm (GA) using multi-model inference (MMI). We exemplify our approach by training a linear regression model for prediction of resistance to the integrase inhibitor Raltegravir (RAL) on a genotype-phenotype database, with many integrase mutations as candidate covariates. The genotype-phenotype pairs in this database were derived from a limited number of subjects, with presence of multiple data points from the same subject, and with an intra-class correlation of 0.92.ResultsIn generation of the RAL model, we took computational efficiency into account by optimizing the GA parameters one by one, and by using tournament selection. To derive the main GA parameters we used 3 times 5-fold cross-validation. The number of integrase mutations to be used as covariates in the mixed effects models was 25 (chrom.size). A GA solution was found when R2MM > 0.95 (goal.fitness). We tested three different MMI approaches to combine the results of 100 GA solutions into one GA-MM-MMI model. When evaluating the GA-MM-MMI performance on two unseen data sets, a more parsimonious and interpretable model was found (GA-MM-MMI TOP18: mixed-effects model containing the 18 most prevalent mutations in the GA solutions, refitted on the training data) with better predictive accuracy (R2) in comparison to GA-ordinary least squares (GA-OLS) and Least Absolute Shrinkage and Selection Operator (LASSO).ConclusionsWe have demonstrated improved performance when using GA-MM-MMI for selection of mutations on a genotype-phenotype data set. As we largely automated setting the GA parameters, the method should be applicable on similar datasets with clustered observations.

show abstract

Random Forest Algorithm for Prediction of HIV Drug Resistance

Raposo

Rosa

Nobre

2020

STEAM-H: Science, Technology, Engineering, Agriculture, Mathematics &Amp; Health

View full text Add to dashboard Cite

Quantitative prediction of integrase inhibitor resistance from genotype through consensus linear regression modeling

Cited by 9 publications

References 26 publications

Fast and Accurate Structure-Based Prediction of Resistance to the HIV-1 Integrase Inhibitor Raltegravir

Fast and Accurate Structure-Based Prediction of Resistance to the HIV-1 Integrase Inhibitor Raltegravir

Multi-model inference using mixed effects from a linear regression based genetic algorithm

Random Forest Algorithm for Prediction of HIV Drug Resistance

Contact Info

Product

Resources

About