Related Experiment Video
Updated: Jun 6, 2026
14:23
A Restriction Enzyme Based Cloning Method to Assess the In vitro Replication Capacity of HIV-1 Subtype C Gag-MJ4 Chimeric Viruses
Published on: August 31, 2014
Machine Learning Identifies Potential Accessory Resistance-Associated Mutations in HIV-1 Integrase.
Alfred Ssekagiri1, Deogratius Ssemwanga1, David Patrick Kateete2
1Uganda Virus Research Institute.
Research Square
|June 5, 2026
Summary
Machine learning identified novel HIV-1 integrase mutations associated with integrase strand transfer inhibitor (INSTI) resistance, even without major mutations. These findings aid in understanding treatment failure and developing new resistance detection methods.
Area of Science:
- Virology
- Genetics
- Computational Biology
Background:
- Integrase strand transfer inhibitors (INSTIs) are crucial for HIV treatment but can fail due to resistance.
- Identifying novel resistance pathways is challenging with conventional methods, especially in resource-limited settings.
- Machine learning (ML) offers a scalable solution to analyze complex HIV-1 genomic data for unrecognized resistance patterns.
Purpose of the Study:
- To apply interpretable machine learning algorithms to HIV-1 integrase sequences.
- To identify novel mutations and mutation patterns associated with INSTI resistance.
- To explore potential epistatic interactions contributing to treatment failure.
Main Methods:
- Analysis of 41,247 publicly available HIV-1 integrase sequences using Random Forests (RF), Support Vector Machines (SVM), Logistic Regression (LR), and Gradient Boosting Machines (GBM).
- Training classifiers to distinguish treatment status based on HIV-1 integrase mutation profiles.
- Utilizing relative risk (RR) analysis to identify co-occurring mutation pairs.
Main Results:
- The RF classifier achieved high accuracy (0.94) and AUC (0.98) in identifying resistance-associated mutations.
- Several novel mutations (e.g., S283G, T112V, D278A) were significantly more prevalent in ART-experienced sequences.
- Nine significant co-occurring mutation pairs with major INSTI resistance mutations were identified, clustering within known resistance pathways.
Conclusions:
- Interpretable machine learning is effective in uncovering potential accessory mutations linked to HIV-1 INSTI resistance.
- These identified mutations may influence INSTI resistance through interactions with major resistance mutations.
- Further experimental validation is necessary to confirm the impact of these mutations on treatment outcomes and ART resistance evolution.
Related Concept Videos
03:18Non-LTR Retrotransposons
As the name suggests, non-LTR retrotransposons lack the long terminal repeats characteristic of the LTR retrotransposons. Additionally, both LTR and non-LTR retrotransposons use distinct mechanisms of mobilization. Non-LTR retrotransposons are further divided into two classes - Long interspersed nuclear elements (LINEs) and short interspersed nuclear elements (SINEs), both of which occur abundantly in most mammals, including humans. Some of the active non-LTR retrotransposons in humans are L1...
00:36Viral Mutations
A mutation is a change in the sequence of bases of DNA or RNA in a genome. Some mutations occur during replication of the genome due to errors made by the polymerase enzymes that replicate DNA or RNA. Unlike DNA polymerase, RNA polymerase is prone to errors because it is not capable of “proofreading” its work. Viruses with RNA-based genomes, like HIV, therefore accrue mutations faster than viruses with DNA-based genomes. Because mutation and recombination provide the raw material for adaptive...