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

Predicting cancer drug response by proteomic profiling.

Yan Ma1, Zhenyu Ding, Yong Qian

  • 1Department of Statistics, West Virginia University, USA.

Clinical Cancer Research : an Official Journal of the American Association for Cancer Research
|August 11, 2006
PubMed
Summary

Proteomic profiling accurately predicts anticancer drug response in cell lines, advancing personalized medicine. This protein-based approach offers a new foundation for predicting treatment effectiveness in tumors.

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

Preoperative GNRI Predicts Postoperative Constipation after Fixation of Extracapsular Hip Fractures in Older Adults.

Geriatric orthopaedic surgery & rehabilitation·2026
Same author

Associations of sleep disturbance with somatic and cognitive-affective depressive symptom dimensions in adolescents: The moderating role of body mass index.

Sleep health·2026
Same author

An integrative genetic and transcriptomic study reveals a causal link and candidate biomarkers between tuberculosis and asthma.

Frontiers in genetics·2026
Same author

Pathological changes and therapeutic strategies for sarcopenia.

EFORT open reviews·2026
Same author

Sleep traits, screen use, and emotional and behavioral problems: A short-term longitudinal cross-lagged panel network analysis.

Addictive behaviors·2026
Same author

Protocol for EACH-ADHF trial: efficacy and safety of early comprehensive rehabilitation in patients with acute decompensated heart failure - a multicentre, randomised controlled trial.

BMJ open·2026

Area of Science:

  • Biochemistry
  • Genomics
  • Pharmacology

Background:

  • Personalized medicine requires accurate prediction of individual drug responses.
  • Gene-drug correlations are studied via transcriptional profiling in pharmacogenomics.
  • Proteomic profiling offers a more direct approach to functional and pharmacologic challenges in drug response.

Purpose of the Study:

  • To determine if proteomic signatures of untreated cells can predict drug response.
  • To develop a machine learning model for chemosensitivity classification based solely on proteomic data.
  • To create tissue-independent classifiers for drug response prediction.

Main Methods:

  • Developed a machine learning system using random forests, Relief, and nearest neighbor algorithms.

Related Experiment Videos

  • Measured protein expression levels in 60 human cancer cell lines (NCI-60) using reverse-phase protein lysate microarrays and 52 antibodies.
  • Generated 118 chemosensitivity classifiers for various anticancer drugs, independent of cell tissue origin.

    • Main Results:

    • Achieved significantly higher accuracy (P < 0.02) in predicting chemosensitivity compared to random prediction for 118 anticancer agents.
    • Demonstrated the feasibility of predicting sensitive, intermediate, and resistant drug responses.
    • Identified proteomic determinants for 5-fluorouracil chemosensitivity as potential diagnostic markers for colon cancer.

    Conclusions:

    • Proteomic approaches are feasible for accurately predicting anticancer drug sensitivity.
    • This study establishes a foundation for predicting drug response using protein markers in untreated tumors.
    • Protein-based prediction holds promise for advancing personalized cancer therapy.