Prediction of HIV drug resistance from genotype with encoded three-dimensional protein structure

Yu, Xiaomei; Weber, Irene T.; Harrison, Robert W.

doi:10.1186/1471-2164-15-s5-s1

Cited by 32 publications

(43 citation statements)

References 45 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our previous work [7] showed that 5-fold cross validation was an appropriate statistical measure of quality for this dataset. All the sequences, including drug resistant and non-drug resistant mutants, were randomly assigned to one of five sets.…”

Section: Methodsmentioning

confidence: 99%

Automated prediction of HIV drug resistance from genotype data

Shen

Harrison

et al. 2016

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

BackgroundHIV/AIDS is a serious threat to public health. The emergence of drug resistance mutations diminishes the effectiveness of drug therapy for HIV/AIDS. Developing a computational prediction of drug resistance phenotype will enable efficient and timely selection of the best treatment regimens.ResultsA unified encoding of protein sequence and structure was used as the feature vector for predicting phenotypic resistance from genotype data. Two machine learning algorithms, Random Forest and K-nearest neighbor, were used. The prediction accuracies were examined by five-fold cross-validation on the genotype-phenotype datasets. A supervised machine learning approach for automatic prediction of drug resistance was developed to handle genotype-phenotype datasets of HIV protease (PR) and reverse transcriptase (RT). It predicts the drug resistance phenotype and its relative severity from a query sequence. The accuracy of the classification was higher than 0.973 for eight PR inhibitors and 0.986 for ten RT inhibitors, respectively. The overall cross-validated regression R2-values for the severity of drug resistance were 0.772–0.953 for 8 PR inhibitors and 0.773–0.995 for 10 RT inhibitors.ConclusionsMachine learning using a unified encoding of sequence and protein structure as a feature vector provides an accurate prediction of drug resistance from genotype data. A practical webserver for clinicians has been implemented.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated prediction of HIV drug resistance from genotype data

Shen

Harrison

et al. 2016

BMC Bioinformatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method accurately classified genotype data to predict drug resistance. In addition, it showed excellent correlation between predicted and observed levels of resistance in cross-validated regression analysis [19]. Mean shift clustering with regression analysis identified mutants, such as PR S17 , with high levels of resistance to multiple drugs that were representative of wide classes of drug-resistant proteins [20].…”

Section: Introductionmentioning

confidence: 99%

Structural Studies of a Rationally Selected Multi-Drug Resistant HIV-1 Protease Reveal Synergistic Effect of Distal Mutations on Flap Dynamics

et al. 2016

View full text Add to dashboard Cite

We report structural analysis of HIV protease variant PRS17 which was rationally selected by machine learning to represent wide classes of highly drug-resistant variants. Crystal structures were solved of PRS17 in the inhibitor-free form and in complex with antiviral inhibitor, darunavir. Despite its 17 mutations, PRS17 has only one mutation (V82S) in the inhibitor/substrate binding cavity, yet exhibits high resistance to all clinical inhibitors. PRS17 has none of the major mutations (I47V, I50V, I54ML, L76V and I84V) associated with darunavir resistance, but has 10,000-fold weaker binding affinity relative to the wild type PR. Comparable binding affinity of 8000-fold weaker than PR is seen for drug resistant mutant PR20, which bears 3 mutations associated with major resistance to darunavir (I47V, I54L and I84V). Inhibitor-free PRS17 shows an open flap conformation with a curled tip correlating with G48V flap mutation. NMR studies on inactive PRS17 D25N unambiguously confirm that the flaps adopt mainly an open conformation in solution very similar to that in the inhibitor-free crystal structure. In PRS17, the hinge loop cluster of mutations, E35D, M36I and S37D, contributes to the altered flap dynamics by a mechanism similar to that of PR20. An additional K20R mutation anchors an altered conformation of the hinge loop. Flap mutations M46L and G48V in PRS17/DRV complex alter the Phe53 conformation by steric hindrance between the side chains. Unlike the L10F mutation in PR20, L10I in PRS17 does not break the inter-subunit ion pair or diminish the dimer stability, consistent with a very low dimer dissociation constant comparable to that of wild type PR. Distal mutations A71V, L90M and I93L propagate alterations to the catalytic site of PRS17. PRS17 exhibits a molecular mechanism whereby mutations act synergistically to alter the flap dynamics resulting in significantly weaker binding yet maintaining active site contacts with darunavir.

show abstract

“…This second approach is also very popular and there exists machine learning software to predict resistance online [8, 9]. Different methods have been proposed, the most common ones being Linear Regression [10, 11], Artificial Neural Networks (ANN) [10, 12–14], Support Vector Machines (SVMs) [10, 15, 16], Decision Trees (DT) [10, 17] and their ensemble counterpart, Random Forests (RF) [15, 16, 18, 19]. Some machine learning studies have complemented the sequence data with structural information, e.g., [11, 15, 16, 18], or have benefited from the knowledge about major drug associated mutations to perform feature selection.…”

Section: Introductionmentioning

confidence: 99%

HIV drug resistance prediction with weighted categorical kernel functions

2019

View full text Add to dashboard Cite

Background Antiretroviral drugs are a very effective therapy against HIV infection. However, the high mutation rate of HIV permits the emergence of variants that can be resistant to the drug treatment. Predicting drug resistance to previously unobserved variants is therefore very important for an optimum medical treatment. In this paper, we propose the use of weighted categorical kernel functions to predict drug resistance from virus sequence data. These kernel functions are very simple to implement and are able to take into account HIV data particularities, such as allele mixtures, and to weigh the different importance of each protein residue, as it is known that not all positions contribute equally to the resistance. Results We analyzed 21 drugs of four classes: protease inhibitors (PI), integrase inhibitors (INI), nucleoside reverse transcriptase inhibitors (NRTI) and non-nucleoside reverse transcriptase inhibitors (NNRTI). We compared two categorical kernel functions, Overlap and Jaccard, against two well-known noncategorical kernel functions (Linear and RBF) and Random Forest (RF). Weighted versions of these kernels were also considered, where the weights were obtained from the RF decrease in node impurity. The Jaccard kernel was the best method, either in its weighted or unweighted form, for 20 out of the 21 drugs. Conclusions Results show that kernels that take into account both the categorical nature of the data and the presence of mixtures consistently result in the best prediction model. The advantage of including weights depended on the protein targeted by the drug. In the case of reverse transcriptase, weights based in the relative importance of each position clearly increased the prediction performance, while the improvement in the protease was much smaller. This seems to be related to the distribution of weights, as measured by the Gini index. All methods described, together with documentation and examples, are freely available at https://bitbucket.org/elies_ramon/catkern . Electronic supplementary material The online version of this article (10.1186/s12859-019-2991-2) contains supplementary material, which is available to authorized users.

show abstract

Prediction of HIV drug resistance from genotype with encoded three-dimensional protein structure

Cited by 32 publications

References 45 publications

Automated prediction of HIV drug resistance from genotype data

Automated prediction of HIV drug resistance from genotype data

Structural Studies of a Rationally Selected Multi-Drug Resistant HIV-1 Protease Reveal Synergistic Effect of Distal Mutations on Flap Dynamics

HIV drug resistance prediction with weighted categorical kernel functions

Contact Info

Product

Resources

About