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

Microarray expression profiling in melanoma reveals a BRAF mutation signature.

Sandra Pavey1, Peter Johansson, Leisl Packer

  • 1Queensland Institute of Medical Research, 300 Herston Rd, Herston, Queensland 4006, Australia.

Oncogene
|March 30, 2004
PubMed
Summary

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

A BRN2:MYC transcriptional axis regulates interconversion between therapy-resistant and tumorigenic phenotypes in melanoma.

Cell reports·2025
Same author

Assessment of the Influence of UVR in Cutaneous Melanoma.

Photodermatology, photoimmunology & photomedicine·2025
Same author

Spatial Transcriptomics Reveals Novel Mechanisms Involved in Perineural Invasion in Pancreatic Ductal Adenocarcinomas.

Cancers·2025
Same author

Pathogenesis of polypropylene mesh complications in female pelvic floor surgery.

American journal of obstetrics and gynecology·2025
Same author

Homicide Rates Across County, Race, Ethnicity, Age, and Sex in the US: A Global Burden of Disease Study.

JAMA network open·2025
Same author

Ten Americas: a systematic analysis of life expectancy disparities in the USA.

Lancet (London, England)·2024

Machine learning accurately predicts BRAF mutations in melanoma cell lines using gene expression. This approach identifies distinct molecular signatures, aiding in understanding melanoma subtypes and signaling pathway activation.

Area of Science:

  • Genomics
  • Bioinformatics
  • Cancer Biology

Background:

  • Melanoma harbors frequent BRAF and NRAS mutations, key drivers of the mitogen-activated protein kinase (MAPK) pathway.
  • Accurate prediction of these mutations is crucial for targeted therapy and understanding melanoma heterogeneity.

Purpose of the Study:

  • To develop a machine learning model for predicting BRAF mutations in melanoma cell lines.
  • To identify gene expression signatures associated with BRAF mutation status.
  • To explore the relationship between BRAF, NRAS mutations, and MAPK pathway activation.

Main Methods:

  • Microarray gene expression profiling of 61 melanoma cell lines.
  • Machine learning, specifically support vector machines, for classification.
  • Hierarchical clustering and multidimensional scaling for data visualization and analysis.

Related Experiment Videos

Main Results:

  • BRAF mutations were present in 69% of cell lines; NRAS mutations in 11%.
  • A classifier using 83 genes accurately distinguished BRAF mutant from wild-type samples.
  • NRAS-mutated samples showed an intermediate gene expression profile between BRAF mutant and wild-type samples.

Conclusions:

  • Gene expression profiling combined with machine learning is effective for predicting BRAF mutations in melanoma.
  • Distinct transcriptional signatures exist for BRAF and NRAS mutations, alongside a common MAPK activation signature.
  • These findings highlight the complex signaling interplay and transcriptional consequences of BRAF/NRAS mutations in melanoma.