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

Feature-specific penalized latent class analysis for genomic data.

E Andrés Houseman1, Brent A Coull, Rebecca A Betensky

  • 1Department of Biostatistics, Harvard School of Public Health, 655 Huntington Avenue, Boston, Massachusetts 02115, USA. ahousema@hsph.harvard.edu

Biometrics
|December 13, 2006
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

Mixtures of key components of the external exposome in association with MRI biomarkers of brain structure: Multi-Ethnic Study of Atherosclerosis.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Workflow for Statistical Analysis of Environmental Mixtures.

Environmental health perspectives·2026
Same author

Scalable Gaussian process regression via median posterior inference for estimating the health effects of an environmental mixture.

Biometrics·2026
Same author

Aspirin and Preterm Birth Among Pregnant People With Increased Heat Exposure: Secondary Analysis of a Randomized Clinical Trial.

JAMA network open·2026
Same author

Associations between self-reported personal care products use and menstrual cycle length and regularity in a US digital cohort.

Environment international·2026
Same author

Redlining, Community Wealth, and Air Pollution: A Tale of Three Cities-Boston, Nashville, and Detroit.

Journal of urban health : bulletin of the New York Academy of Medicine·2026
Same journal

Fast penalized generalized estimating equations for large longitudinal functional datasets.

Biometrics·2026
Same journal

Causally-interpretable random-effects meta-analysis.

Biometrics·2026
Same journal

Statistical inference for mean function of partially observed functional time series.

Biometrics·2026
Same journal

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026
Same journal

Finite mixtures of linear quantile regressions with concomitant variables: a solution to endogeneity in longitudinal data modeling.

Biometrics·2026
Same journal

Discussion on "INTACT: a method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
See all related articles

This study introduces penalized latent class models for analyzing genomic data with many categorical variables. These methods improve analysis of loss of heterozygosity (LOH) data and reveal associations with patient survival.

Area of Science:

  • Genomics
  • Statistical Genetics
  • Bioinformatics

Background:

  • Genomic datasets often feature numerous categorical variables and limited subject numbers.
  • Missing or non-informative variables are common challenges in genomic data analysis.
  • Loss of heterozygosity (LOH) is a dichotomous genomic variable frequently studied.

Purpose of the Study:

  • To extend latent class models for high-dimensional genomic data analysis.
  • To develop penalized regression methods for handling complex genomic variable structures.
  • To identify features that improve predictive power in genomic analyses.

Main Methods:

  • Utilized a latent class model framework with penalized regression (ridge and LASSO).
  • Developed an orthogonal transformation to map marker space to a feature space.

Related Experiment Videos

  • Applied methods to loss of heterozygosity (LOH) data from 93 brain tumor patients.

    • Main Results:

    • Penalized latent class models successfully estimated parameters where unpenalized methods failed.
    • The orthogonal map enhanced the predictive power of the constrained model.
    • Derived posterior classes showed significant association with patient survival outcomes.

    Conclusions:

    • Penalized latent class models offer a robust approach for high-dimensional genomic data.
    • The developed methods provide improved analytical capabilities for LOH data.
    • Identified genomic features are linked to survival in brain tumor patients, suggesting clinical relevance.