Dataset Information

Improving fold resistance prediction of HIV-1 against protease and reverse transcriptase inhibitors using artificial neural networks.

ABSTRACT: Drug resistance in HIV treatment is still a worldwide problem. Predicting resistance to antiretrovirals (ARVs) before starting any treatment is important. Prediction accuracy is essential, as low-accuracy predictions increase the risk of prescribing sub-optimal drug regimens leading to patients developing resistance sooner. Artificial Neural Networks (ANNs) are a powerful tool that would be able to assist in drug resistance prediction. In this study, we constrained the dataset to subtype B, sacrificing generalizability for a higher predictive performance, and demonstrated that the predictive quality of the ANN regression models have definite improvement for most ARVs.Trained regression ANNs were optimized for eight protease inhibitors, six nucleoside reverse transcriptase (RT) inhibitors and four non-nucleoside RT inhibitors by experimenting combinations of rare variant filtering (none versus 1 residue occurrence) and ANN topologies (1-3 hidden layers with 2, 4, 6, 8 and 10 nodes per layer). Single hidden layers (5-20 nodes) were used for training where overfitting was detected. 5-fold cross-validation produced mean R2 values over 0.95 and standard deviations lower than 0.04 for all but two antiretrovirals.Overall, higher accuracies and lower variances (compared to results published in 2016) were obtained by experimenting with various preprocessing methods, while focusing on the most prevalent subtype in the raw dataset (subtype B).We thus highlight the need to develop and make available subtype-specific datasets for developing higher accuracy in drug-resistance prediction methods.

SUBMITTER: Sheik Amamuddy O

PROVIDER: S-EPMC5558779 | biostudies-other | 2017 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:UnlabelledHIV-1 protease (PR), reverse transcriptase (RT), and integrase (IN) variability presents a challenge to laboratories performing genotypic resistance testing. This challenge will grow with increased sequencing of samples enriched for proviral DNA such as dried blood spots and increased use of next-generation sequencing (NGS) to detect low-abundance HIV-1 variants. We analyzed PR and RT sequences from >100,000 individuals and IN sequences from >10,000 individuals to characterize variation at each amino acid position, identify mutations indicating APOBEC-mediated G-to-A editing, and identify mutations resulting from selective drug pressure. Forty-seven percent of PR, 37% of RT, and 34% of IN positions had one or more amino acid variants with a prevalence of ≥1%. Seventy percent of PR, 60% of RT, and 60% of IN positions had one or more variants with a prevalence of ≥0.1%. Overall 201 PR, 636 RT, and 346 IN variants had a prevalence of ≥0.1%. The median intersubtype prevalence ratios were 2.9-, 2.1-, and 1.9-fold for these PR, RT, and IN variants, respectively. Only 5.0% of PR, 3.7% of RT, and 2.0% of IN variants had a median intersubtype prevalence ratio of ≥10-fold. Variants at lower prevalences were more likely to differ biochemically and to be part of an electrophoretic mixture compared to high-prevalence variants. There were 209 mutations indicative of APOBEC-mediated G-to-A editing and 326 mutations nonpolymorphic treatment selected. Identification of viruses with a high number of APOBEC-associated mutations will facilitate the quality control of dried blood spot sequencing. Identifying sequences with a high proportion of rare mutations will facilitate the quality control of NGS.ImportanceMost antiretroviral drugs target three HIV-1 proteins: PR, RT, and IN. These proteins are highly variable: many different amino acids can be present at the same position in viruses from different individuals. Some of the amino acid variants cause drug resistance and occur mainly in individuals receiving antiretroviral drugs. Some variants result from a human cellular defense mechanism called APOBEC-mediated hypermutation. Many variants result from naturally occurring mutation. Some variants may represent technical artifacts. We studied PR and RT sequences from >100,000 individuals and IN sequences from >10,000 individuals to quantify variation at each amino acid position in these three HIV-1 proteins. We performed analyses to determine which amino acid variants resulted from antiretroviral drug selection pressure, APOBEC-mediated editing, and naturally occurring variation. Our results provide information essential to clinical, research, and public health laboratories performing genotypic resistance testing by sequencing HIV-1 PR, RT, and IN.

Project description:The South African national combination antiretroviral therapy (cART) roll-out program started in 2006, with over 4.4 million people accessing treatment since it was first introduced. HIV-1 drug resistance can hamper the success of cART. This study determined the patterns of HIV-1 drug-resistance associated mutations (RAMs) in People Living with HIV-1 (PLHIV-1). Receiving first (for children below 3 years of age) and second-line (for adults) cART regimens in South Africa. During 2017 and 2018, 110 patients plasma samples were selected, 96 samples including those of 17 children and infants were successfully analyzed. All patients were receiving a boosted protease inhibitor (bPI) as part of their cART regimen. The viral sequences were analyzed for RAMs through genotypic resistance testing. We performed genotypic resistance testing (GRT) for Protease inhibitors (PIs), Reverse transcriptase inhibitors (RTIs) and Integrase strand transfer inhibitors (InSTIs). Viral sequences were subtyped using REGAv3 and COMET. Based on the PR/RT sequences, HIV-1 subtypes were classified as 95 (99%) HIV-1 subtype C (HIV-1C) while one sample as 02_AG. Integrase sequencing was successful for 89 sequences, and all the sequences were classified as HIV-1C (99%, 88/89) except one sequence classified CRF02_AG, as observed in PR/RT. Of the 96 PR/RT sequences analyzed, M184V/I (52/96; 54%) had the most frequent RAM nucleoside reverse transcriptase inhibitor (NRTI). The most frequent non-nucleoside reverse transcriptase inhibitor (NNRTI) RAM was K103N/S (40/96, 42%). Protease inhibitor (PI) RAMs M46I and V82A were present in 12 (13%) of the sequences analyzed. Among the InSTI major RAM two (2.2%) sequences have Y143R and T97A mutations while one sample had T66I. The accessory RAM E157Q was identified in two (2.2%). The data indicates that the majority of the patients failed on bPIs didn't have any mutation; therefore adherence could be major issue in these groups of individuals. We propose continued viral load monitoring for better management of infected PLHIV.

Dataset Information

Improving fold resistance prediction of HIV-1 against protease and reverse transcriptase inhibitors using artificial neural networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets