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

Classification algorithms for phenotype prediction in genomics and proteomics.

Habtom W Ressom1, Rency S Varghese, Zhen Zhang

  • 1Lombardi Comprehensive Cancer Center, 3970 Reservoir Rd NW, Washington, DC 20057, USA. hwr@georgetown.edu

Frontiers in Bioscience : a Journal and Virtual Library
|November 6, 2007
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

MAE-UNETR++: Masked Autoencoder Pretraining for 3-D Lung Nodule Segmentation.

bioRxiv : the preprint server for biology·2026
Same author

Evaluation of metabolite biomarker candidates in detecting HCC in patients with liver cirrhosis.

Metabolomics : Official journal of the Metabolomic Society·2026
Same author

Glycoproteome Profiling of Human Serum for Hepatocellular Carcinoma Biomarker Discovery.

Journal of proteome research·2026
Same author

Proteomic profiling of olfactory exfoliates from people with subjective cognitive complaints reveal networks of olfactory biomarkers of cognitive performance.

Frontiers in aging neuroscience·2026
Same author

Editorial: Exploring epigenetic mechanisms in cancer.

Frontiers in oncology·2026
Same author

A Polymeric Zwitterionic Hydrophilic Probe for Mapping the Human Serum Endogenous Glycopeptidome.

Journal of separation science·2026
Same journal

The CD44 protein family: roles in embryogenesis and tumor progression.

Frontiers in bioscience : a journal and virtual library·2017
Same journal

Four varieties of voltage-gated proton channels.

Frontiers in bioscience : a journal and virtual library·2017
Same journal

Lurie's tubercle-count method to test TB vaccine efficacy in rabbits.

Frontiers in bioscience : a journal and virtual library·2017
Same journal

Optical spectroscopy of breast biopsies and human breast cancer xenografts in nude mice.

Frontiers in bioscience : a journal and virtual library·2017
Same journal

The colostrum-deprived, artificially-reared, neonatal pig as a model animal for studying rotavirus gastroenteritis.

Frontiers in bioscience : a journal and virtual library·2017
Same journal

Action of polypeptide growth factors in colon cancer; development of new therapeutic approaches.

Frontiers in bioscience : a journal and virtual library·2017
See all related articles

This study reviews computational methods for molecular cancer classification. It highlights feature selection from gene and mass spectrometry data for accurate phenotype prediction using machine learning algorithms.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Molecular cancer classification is crucial for personalized medicine.
  • Accurate phenotype prediction relies on identifying relevant biological features.
  • High-throughput data (microarray, mass spectrometry) generate complex datasets.

Purpose of the Study:

  • To provide an overview of statistical and machine learning algorithms for feature selection and pattern classification.
  • To discuss the application of these computational methods in molecular cancer classification and phenotype prediction.
  • To focus on gene selection from microarray data and peak selection from mass spectrometry data.

Main Methods:

  • Review of statistical and machine learning-based feature selection techniques.

Related Experiment Videos

  • Overview of pattern classification algorithms.
  • Application of selected features for phenotype prediction.

    • Main Results:

    • Computational methods enable effective gene and peak selection from complex biological data.
    • Feature selection is a critical step for successful pattern classification in cancer research.
    • The reviewed algorithms demonstrate potential for accurate molecular cancer classification.

    Conclusions:

    • Statistical and machine learning approaches are powerful tools for molecular cancer classification.
    • Effective feature selection from microarray and mass spectrometry data is key to phenotype prediction.
    • These computational strategies advance the field of precision oncology.