Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A new perspective on V3 phenotype prediction.

Satish Pillai1, Benjamin Good, Douglas Richman

  • 1University of California, San Diego, La Jolla, California 92093, USA. satish@biomail.ucsd.edu

AIDS Research and Human Retroviruses
|March 20, 2003
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Spontaneous Pulmonary Herniation: A Case Report.

The Journal of emergency medicine·2026
Same author

QMAP: a benchmark for standardized evaluation of antimicrobial peptide MIC and hemolytic activity regression.

Scientific reports·2026
Same author

A cluster of acidic residues in the cytoplasmic domain of SARS-CoV-2 Spike is required for virion-incorporation and infectivity.

PloS one·2026
Same author

Turncoat antibodies unmasked in a model of autoimmune demyelination: From biology to therapy.

Proceedings of the National Academy of Sciences of the United States of America·2025
Same author

HIV serologic reactivity varies with time of ART initiation in persons on long-term ART.

Journal of clinical microbiology·2025
Same author

Extracting a COVID-19 signature from a multi-omic dataset.

Frontiers in bioinformatics·2025
Same journal

Identification of a Complex HIV-1 Circulating Recombinant Form (CRF203_cpx) Originating from Three Main Circulating Recombinant Forms in China.

AIDS research and human retroviruses·2026
Same journal

Near Full-Length Genome Characterization of a Novel Second-Generation HIV-1 CRF01_AE/CRF07_BC Recombinant Identified in an MSM Individual in Guizhou, China.

AIDS research and human retroviruses·2026
Same journal

Evolving Indications and Diagnostic Spectrum of Bone Marrow Examination in People with HIV During the Antiretroviral Therapy Era: A 6-Year Retrospective Study.

AIDS research and human retroviruses·2026
Same journal

A Conserved Natural Killer Cell Transcriptional Fingerprint in Rhesus Macaque Models of Acute Viral Infections.

AIDS research and human retroviruses·2026
Same journal

Perceived Ethical Risks of HIV Phylogenetic Research: Insights from Professional Stakeholders in Uganda.

AIDS research and human retroviruses·2026
Same journal

Genomic Characterization of Two Novel Human Immunodeficiency Virus-1 Recombinant Forms (CRF01_AE and B) in Men Who Have Sex with Men in Hebei, China.

AIDS research and human retroviruses·2026
See all related articles

Predicting HIV-1 coreceptor usage, crucial for pathology, is improved using machine learning on V3 loop sequences. This enhances understanding of viral entry and disease progression.

Area of Science:

  • Virology
  • Computational Biology
  • Immunology

Background:

  • HIV-1 coreceptor usage dictates viral tropism and disease pathology.
  • The V3 loop of the viral envelope glycoprotein is the primary determinant of coreceptor usage.
  • Previous sequence-based prediction methods relied on smaller, less reliable datasets.

Purpose of the Study:

  • To develop a superior phenotypic classifier for HIV-1 coreceptor usage.
  • To leverage modern machine learning techniques for improved prediction accuracy.
  • To utilize the current, comprehensive database of V3 loop sequences with known phenotypes.

Main Methods:

  • Application of machine learning algorithms to a large dataset of V3 loop sequences.
  • Training predictive models on sequences with experimentally determined coreceptor usage phenotypes.

Related Experiment Videos

  • Statistical analysis of sequence data to identify key predictive features.

    • Main Results:

    • Developed machine learning classifiers that outperform previous methods.
    • Demonstrated the effectiveness of ML in predicting HIV-1 coreceptor usage from V3 loop sequences.
    • Provided publicly accessible classifiers and sequence data for further research.

    Conclusions:

    • Machine learning offers a powerful approach for accurate HIV-1 coreceptor usage prediction.
    • Accurate prediction of coreceptor usage can inform therapeutic strategies and disease management.
    • The developed tools and data facilitate advancements in HIV-1 research.