HIV drug resistance prediction with weighted categorical kernel functions

Abstract

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.

RHIVDB: A Freely Accessible Database of HIV Amino Acid Sequences and Clinical Data of Infected Patients

“…Due to its high mutagenicity HIV is capable to develop resistance, to existing antiretroviral drugs ( Geronikaki et al, 2016 ). Data on the amino acid sequences of HIV proteins, including reverse transcriptase (RT), protease (PR), integrase (IN), and envelope protein (ENV), are important for the prediction of HIV drug resistance ( Liu and Shafer, 2006 ; Toor et al, 2011 ; Raposo and Nobre, 2017 ; Ramon et al, 2019 ; Steiner et al, 2020 ) and the so-called drug exposure, which is considered one of the features potentially associated with HIV drug resistance ( Pironti et al, 2017 ). With data from the (i) amino acid sequences of HIV proteins, (ii) drug combinations used to treat HIV-positive patients, and (iii) clinical data obtained from the patients, it is possible to build models predicting (a) drug exposure and HIV drug resistance and (b) therapeutic effectiveness based on the HIV sequence data and the treatment history ( Tarasova et al, 2020 ).…”

Revealing the Mutation Patterns of Drug-Resistant Reverse Transcriptase Variants of Human Immunodeficiency Virus through Proteochemometric Modeling

“…The support vector machine model was constructed based on the designed molecular descriptors with the EC 50 values to classify the compounds into active and inactive ones. Furthermore, weighted categorical kernel functions were introduced to evaluate the contribution of different positions on the resistance prediction [ 15 ]. Recently, Brand expanded the application of the prediction model and proposed a multi-label classification model to predict the cross-resistance between RT sequences and five nucleoside analogs [ 16 ].…”

A Computational Approach for the Prediction of Treatment History and the Effectiveness or Failure of Antiretroviral Therapy

“…Experimental tests allow for the evaluation of HIV-1 resistance against RT and PR inhibitors [7,8]. Several machine learning approaches predict the resistance and/or exposure of a particular HIV-1 variant to a drug on the basis of the nucleotide or amino acid sequences of the HIV-1 PR and RT [9][10][11][12][13][14][15][16][17]. Earlier, we reported computational approaches for predicting HIV-1 resistance to RT and PR inhibitors [10,18,19] based on sequences of HIV-1 variants collected from around the world, available from the Stanford HIV Resistance Database (STDB) [20].…”