scholarly journals Using machine learning and big data to explore the drug resistance landscape in HIV

2021 ◽  
Vol 17 (8) ◽  
pp. e1008873
Author(s):  
Luc Blassel ◽  
Anna Tostevin ◽  
Christian Julian Villabona-Arenas ◽  
Martine Peeters ◽  
Stéphane Hué ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Prediction Accuracy ◽  
Sequence Data ◽  
Transcriptase Inhibitor ◽  
Binary Representation ◽  
Resistance Mutations ◽  
Genetic Barrier ◽  
The Uk

Drug resistance mutations (DRMs) appear in HIV under treatment pressure. DRMs are commonly transmitted to naive patients. The standard approach to reveal new DRMs is to test for significant frequency differences of mutations between treated and naive patients. However, we then consider each mutation individually and cannot hope to study interactions between several mutations. Here, we aim to leverage the ever-growing quantity of high-quality sequence data and machine learning methods to study such interactions (i.e. epistasis), as well as try to find new DRMs. We trained classifiers to discriminate between Reverse Transcriptase Inhibitor (RTI)-experienced and RTI-naive samples on a large HIV-1 reverse transcriptase (RT) sequence dataset from the UK (n ≈ 55, 000), using all observed mutations as binary representation features. To assess the robustness of our findings, our classifiers were evaluated on independent data sets, both from the UK and Africa. Important representation features for each classifier were then extracted as potential DRMs. To find novel DRMs, we repeated this process by removing either features or samples associated to known DRMs. When keeping all known resistance signal, we detected sufficiently prevalent known DRMs, thus validating the approach. When removing features corresponding to known DRMs, our classifiers retained some prediction accuracy, and six new mutations significantly associated with resistance were identified. These six mutations have a low genetic barrier, are correlated to known DRMs, and are spatially close to either the RT active site or the regulatory binding pocket. When removing both known DRM features and sequences containing at least one known DRM, our classifiers lose all prediction accuracy. These results likely indicate that all mutations directly conferring resistance have been found, and that our newly discovered DRMs are accessory or compensatory mutations. Moreover, apart from the accessory nature of the relationships we found, we did not find any significant signal of further, more subtle epistasis combining several mutations which individually do not seem to confer any resistance.

scholarly journals Using machine learning and big data to explore the drug resistance landscape in HIV

2021 ◽  
Author(s):  
Luc Blassel ◽  
Anna Tostevin ◽  
Christian Julian Villabona-Arenas ◽  
Martine Peeters ◽  
Stephane Hue ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Prediction Accuracy ◽  
Sequence Data ◽  
Transcriptase Inhibitor ◽  
Binary Representation ◽  
Resistance Mutations ◽  
Genetic Barrier ◽  
The Uk

Drug resistance mutations (DRMs) appear in HIV under treatment pressure. DRMs are commonly transmitted to naive patients. The standard approach to reveal new DRMs is to test for significant frequency differences of mutations between treated and naive patients. However, we then consider each mutation individually and cannot hope to study interactions between several mutations. Here, we aim to leverage the ever-growing quantity of high-quality sequence data and machine learning methods to study such interactions (i.e. epistasis), as well as try to find new DRMs. We trained classifiers to discriminate between Reverse Transcriptase Inhibitor (RTI)-experienced and RTI-naive samples on a large HIV-1 reverse transcriptase (RT) sequence dataset from the UK (n ≈ 55; 000), using all observed mutations as binary representation features. To assess the robustness of our findings, our classifiers were evaluated on independent data sets, both from the UK and Africa. Important representation features for each classifier were then extracted as potential DRMs. To find novel DRMs, we repeated this process by removing either features or samples associated to known DRMs. When keeping all known resistance signal, we detected sufficiently prevalent known DRMs, thus validating the approach. When removing features corresponding to known DRMs, our classifiers retained some prediction accuracy, and six new mutations significantly associated with resistance were identified. These six mutations have a low genetic barrier, are correlated to known DRMs, and are spatially close to either the RT active site or the regulatory binding pocket. When removing both known DRM features and sequences containing at least one known DRM, our classifiers lose all prediction accuracy. These results likely indicate that all mutations directly conferring resistance have been found, and that our newly discovered DRMs are accessory or compensatory mutations. Moreover, we did not find any significant signal of epistasis, beyond the standard resistance scheme associating major DRMs to auxiliary mutations.

scholarly journals Using machine learning and big data to explore the drug resistance landscape in HIV

2021 ◽  
Author(s):  
Luc Blassel ◽  
Anna Tostevin ◽  
Christian Julian Villabona-Arenas ◽  
Martine Peeters ◽  
Stéphane Hué ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Binding Pocket ◽  
Resistance Mutations ◽  
Genetic Barrier ◽  
Drug Resistance Mutations ◽  
The Uk ◽  
Treatment Pressure ◽  
New Mutations

AbstractDrug resistance mutations (DRMs) appear in HIV under treatment pressure. DRMs are commonly transmitted to naive patients. The standard approach to reveal new DRMs is to test for significant frequency differences of mutations between treated and naive patients. However, we then consider each mutation individually and cannot hope to study interactions between several mutations. Here, we aim to leverage the ever-growing quantity of high-quality sequence data and machine learning methods to study such interactions (i.e. epistasis), as well as try to find new DRMs.We trained classifiers to discriminate between Reverse Transcriptase Inhibitor (RTI)-experienced and RTI-naive samples on a large HIV-1 reverse transcriptase (RT) sequence dataset from the UK (n ≈ 55, 000), using all observed mutations as binary representation features. To assess the robustness of our findings, our classifiers were evaluated on independent data sets, both from the UK and Africa. Important representation features for each classifier were then extracted as potential DRMs. To find novel DRMs, we repeated this process by removing either features or samples associated to known DRMs.When keeping all known resistance signal, we detected sufficiently prevalent known DRMs, thus validating the approach. When removing features corresponding to known DRMs, our classifiers retained some prediction accuracy, and six new mutations significantly associated with resistance were identified. These six mutations have a low genetic barrier, are correlated to known DRMs, and are spatially close to either the RT active site or the regulatory binding pocket. When removing both known DRM features and sequences containing at least one known DRM, our classifiers lose all prediction accuracy. These results likely indicate that all mutations directly conferring resistance have been found, and that our newly discovered DRMs are accessory or compensatory mutations. Moreover, we did not find any significant signal of epistasis, beyond the standard resistance scheme associating major DRMs to auxiliary mutations.Author summaryAlmost all drugs to treat HIV target the Reverse Transcriptase (RT) and Drug resistance mutations (DRMs) appear in HIV under treatment pressure. Resistant strains can be transmitted and limit treatment options at the population level. Classically, multiple statistical testing is used to find DRMs, by comparing virus sequences of treated and naive populations. However, with this method, each mutation is considered individually and we cannot hope to reveal any interaction (epistasis) between them. Here, we used machine learning to discover new DRMs and study potential epistasis effects. We applied this approach to a very large UK dataset comprising ≈ 55, 000 RT sequences. Results robustness was checked on different UK and African datasets.Six new mutations associated to resistance were found. All six have a low genetic barrier and show high correlations with known DRMs. Moreover, all these mutations are close to either the active site or the regulatory binding pocket of RT. Thus, they are good candidates for further wet experiments to establish their role in drug resistance. Importantly, our results indicate that epistasis seems to be limited to the classical scheme where primary DRMs confer resistance and associated mutations modulate the strength of the resistance and/or compensate for the fitness cost induced by DRMs.

Diversity of HIV-1 subtypes and transmitted drug-resistance mutations among minority HIV-1 variants in a Turkish cohort

2021 ◽  
Vol 19 ◽  
Author(s):  
Rabia Can Sarinoglu ◽  
Uluhan Sili ◽  
Ufuk Hasdemir ◽  
Burak Aksu ◽  
Guner Soyletir ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Transcriptase Inhibitor ◽  
Transmitted Drug Resistance ◽  
Resistance Mutations ◽  
Drug Resistance Mutations ◽  
Subtype B ◽  
Treatment Naïve ◽  
Reverse Transcriptase Inhibitor ◽  
Hiv 1

Background: The World Health Organization (WHO) recommends the surveillance of transmitted drug resistance mutations (TDRMs) to ensure the effectiveness and sustainability of HIV treatment programs. Objective: Our aim was to determine the TDRMs and evaluate the distribution of HIV-1 subtypes using and compared next-generation sequencing (NGS) and Sanger-based sequencing (SBS) in a cohort of 44 antiretroviral treatment-naïve patients. Methods: All samples that were referred to the microbiology laboratory for HIV drug resistance analysis between December 2016 and February 2018 were included in the study. After exclusions, 44 treatment-naive adult patients with a viral load of >1000 copies/mL were analyzed. DNA sequencing for reverse transcriptase and protease regions was performed using both DeepChek ABL single round kit and Sanger-based ViroSeq HIV-1 Genotyping System. The mutations and HIV-1 subtypes were analyzed using the Stanford HIVdb version 8.6.1 Genotypic Resistance software, and TDRMs were assessed using the WHO surveillance drug-resistance mutation database. HIV-1 subtypes were confirmed by constructing a maximum-likelihood phylogenetic tree using Los Alamos IQ-Tree software. Results: NGS identified nucleos(t)ide reverse transcriptase inhibitor (NRTI)-TDRMs in 9.1% of the patients, non-nucleos(t)ide reverse transcriptase inhibitor (NNRTI)-TDRMs in 6.8% of the patients, and protease inhibitor (PI)-TDRMs in 18.2% of the patients at a detection threshold of ≥1%. Using SBS, 2.3% and 6.8% of the patients were found to have NRTI- and NNRTI-TDRMs, respectively, but no major PI mutations were detected. M41L, L74I, K65R, M184V, and M184I related to NRTI, K103N to NNRTI, and N83D, M46I, I84V, V82A, L24I, L90M, I54V to the PI sites were identified using NGS. Most mutations were found in low-abundance (frequency range: 1.0% - 4.7%) HIV-1 variants, except M41L and K103N. The subtypes of the isolates were found as follows; 61.4% subtype B, 18.2% subtype B/CRF02_AG recombinant, 13.6% subtype A, 4.5% CRF43_02G, and 2.3% CRF02_AG. All TDRMs, except K65R, were detected in HIV-1 subtype B isolates.. Conclusion: The high diversity of protease site TDRMs in the minority HIV-1 variants and prevalence of CRFs were remarkable in this study. All minority HIV-1 variants were missed by conventional sequencing. TDRM prevalence among minority variants appears to be decreasing over time at our center.

scholarly journals Development of HIV drug resistance in a cohort of adults on first-line antiretroviral therapy in Tanzania during the stavudine era

2020 ◽  
Author(s):  
Raphael Z Sangeda ◽  
Perpétua Gómes ◽  
Soo-Yon Rhee ◽  
Fausta Mosha ◽  
Ricardo J. Camacho ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Nucleoside Reverse Transcriptase Inhibitor ◽  
Transcriptase Inhibitor ◽  
Resistance Mutations ◽  
First Line ◽  
Nnrti Resistance ◽  
One Year ◽  
Reverse Transcriptase Inhibitor

Abstract As more HIV patients start combination antiretroviral therapy (cART), the emergence of HIV drug resistance (HIVDR) is inevitable. This will have consequences for the transmission of HIVDR, the success of ART, and the nature and trend of the epidemic. We recruited a cohort of 223 patients starting or continuing their first-line cART in Tanzania during the stavudine era in 2010. Patients were then followed up for one year. From those with a viral load test at baseline and follow-up time, 34% were failing virologically at the one-year endpoint. From 41 patients, protease and reverse transcriptase genotyping were successful. Eighteen samples were from therapy-naïve patients and 23 samples were taken under therapy either baseline for patients already under cART at study entry, or follow-up sample. The isolates were mostly subtype A, followed by C and D at 41.5%, 22% and 12.2% of the patients, respectively. No transmitted HIVDR was detected, as scored using the surveillance drug resistance mutations (DRMs) list. However, in 3 of the 18 samples from therapy-naïve patients, the clinical Rega interpretation algorithm scored 44D or 138A as non-nucleoside reverse transcriptase inhibitor (NNRTI) resistance-associated polymorphisms. The most observed nucleoside reverse transcriptase inhibitor (NRTI) mutation was 184V. The mutation was found in 16 patients causing resistance to lamivudine and emtricitabine. Nineteen patients had NNRTI resistance mutations, the most common of which was 103N observed in 8 patients. These high levels of resistance calls for regular drug resistance surveillance in Tanzania to control the emergence and transmission of HIVDR.

scholarly journals Development of HIV Drug Resistance in a Cohort of Adults on First-Line Antiretroviral Therapy in Tanzania during the Stavudine Era

2021 ◽  
Vol 12 (4) ◽  
pp. 847-861
Author(s):  
Raphael Z. Sangeda ◽  
Perpétua Gómes ◽  
Soo-Yon Rhee ◽  
Fausta Mosha ◽  
Ricardo J. Camacho ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Nucleoside Reverse Transcriptase Inhibitor ◽  
Transcriptase Inhibitor ◽  
Resistance Mutations ◽  
First Line ◽  
Nnrti Resistance ◽  
One Year ◽  
Reverse Transcriptase Inhibitor

As more HIV patients start combination antiretroviral therapy (cART), the emergence of HIV drug resistance (HIVDR) is inevitable. This will have consequences for the transmission of HIVDR, the success of ART, and the nature and trend of the epidemic. We recruited a cohort of 223 patients starting or continuing their first-line cART in Tanzania towards the end of the stavudine era in 2010. Patients were then followed for one year. Of those with a viral load test at baseline and follow-up time, 34% had a detectable viral load at the one-year endpoint. For 41 patients, protease and reverse transcriptase genotyping were successful. Eighteen samples were from cART-naïve patients, and 23 samples were taken under therapy either at baseline for cART-experienced patients or from follow-up samples for both cART–naïve and cART–experienced patients. The isolates were subtype A, followed by C and D in 41.5%, 22%, and 12.2% of the patients, respectively. No transmitted HIVDR was detected, as scored using the surveillance drug resistance mutations (DRMs) list. However, in 3 of the 18 samples from cART-naïve patients, the clinical Rega interpretation algorithm scored 44D or 138A as non-nucleoside reverse transcriptase inhibitor (NNRTI) resistance-associated polymorphisms. The most observed nucleoside reverse transcriptase inhibitor (NRTI) mutation was 184V. The mutation was found in 16 patients, causing resistance to lamivudine and emtricitabine. Nineteen patients had NNRTI resistance mutations, the most common of which was 103N, observed in eight patients. These high levels of resistance call for regular drug resistance surveillance in Tanzania to inform the control of the emergence and transmission of HIVDR.

scholarly journals In VitroResistance Profile of the Candidate HIV-1 Microbicide Drug Dapivirine

2011 ◽  
Vol 56 (2) ◽  
pp. 751-756 ◽  
Author(s):  
Susan M. Schader ◽  
Maureen Oliveira ◽  
Ruxandra-Ilinca Ibanescu ◽  
Daniela Moisi ◽  
Susan P. Colby-Germinario ◽  
...  
Keyword(s):  
Drug Resistance ◽  
Reverse Transcriptase ◽  
Sexual Transmission ◽  
Transcriptase Inhibitor ◽  
Resistance Mutations ◽  
Drug Resistance Mutations ◽  
Development Of Resistance ◽  
Sexual Transmission Of Hiv ◽  
Hiv 1

ABSTRACTAntiretroviral-based microbicides may offer a means to reduce the sexual transmission of HIV-1. Suboptimal use of a microbicide may, however, lead to the development of drug resistance in users that are already, or become, infected with HIV-1. In such cases, the efficacy of treatments may be compromised since the same (or similar) antiretrovirals used in treatments are being developed as microbicides. To help predict which drug resistance mutations may develop in the context of suboptimal use, HIV-1 primary isolates of different subtypes and different baseline resistance profiles were used to infect primary cellsin vitroin the presence of increasing suboptimal concentrations of the two candidate microbicide antiretrovirals dapivirine (DAP) and tenofovir (TFV) alone or in combination. Infections were ongoing for 25 weeks, after which reverse transcriptase genotypes were determined and scrutinized for the presence of any clinically recognized reverse transcriptase drug resistance mutations. Results indicated that suboptimal concentrations of DAP alone facilitated the emergence of common nonnucleoside reverse transcriptase inhibitor resistance mutations, while suboptimal concentrations of DAP plus TFV gave rise to fewer mutations. Suboptimal concentrations of TFV alone did not frequently result in the development of resistance mutations. Sensitivity evaluations for stavudine (d4T), nevirapine (NVP), and lamivudine (3TC) revealed that the selection of resistance as a consequence of suboptimal concentrations of DAP may compromise the potential for NVP to be used in treatment, a finding of potential relevance in developing countries.

Sign in / Sign up

Export Citation Format

Share Document