What question did this study set out to answer?

To assess whether a random forest–based variable selection technique, the Relative Recurrency Variable Importance Metric (r2VIM), can identify functional genetic variants as effectively as traditional linear regression.

October 1, 2016BMC ProceedingsOpen Access

Comparison of parametric and machine methods for variable selection in simulated Genetic Analysis Workshop 19 data

View Full Paper

Ask AI

Bookmark

Authors

EHEmily Holzinger SSSilke Szymczak JMJames D. Malley

Discussion

Member takes

Overview

Simulation study reveals a random forest variable selection method matches linear regression for identifying functional variants, highlighting the utility of machine learning in genetic analysis.

Key Points

To assess whether a random forest–based variable selection technique, the Relative Recurrency Variable Importance Metric (r2VIM), can identify functional genetic variants as effectively as traditional linear regression.
Analyzed simulated systolic blood pressure phenotypes and genetic data from unrelated individuals in the Genetic Analysis Workshop 19 dataset.
Evaluated the detection of functional variants using r2VIM alongside linear regression applying standard Bonferroni significance thresholds.
r2VIM successfully detected functional variants alongside nonfunctional variables at rates aligning with Bonferroni-corrected linear regression when applying an optimal importance threshold (numerical counts not reported).
The variable selection metric demonstrated proof-of-concept as an alternative to stringent parametric regression for isolating genetic signals (numerical effect sizes not reported).

Cite This Study

Holzinger et al. (2016) studied this question.

synapsesocial.com/papers/6a869a0da94eefd7bf5130a4 https://doi.org/10.1186/s12919-016-0021-1

View Full Paper

Ask AI

Bookmark

October 1, 2016BMC ProceedingsOpen Access

Comparison of parametric and machine methods for variable selection in simulated Genetic Analysis Workshop 19 data

View Full Paper

Ask AI

Bookmark

Authors

EHEmily Holzinger SSSilke Szymczak JMJames D. Malley

Discussion

Member takes

Overview

Simulation study reveals a random forest variable selection method matches linear regression for identifying functional variants, highlighting the utility of machine learning in genetic analysis.

Key Points

To assess whether a random forest–based variable selection technique, the Relative Recurrency Variable Importance Metric (r2VIM), can identify functional genetic variants as effectively as traditional linear regression.
Analyzed simulated systolic blood pressure phenotypes and genetic data from unrelated individuals in the Genetic Analysis Workshop 19 dataset.
Evaluated the detection of functional variants using r2VIM alongside linear regression applying standard Bonferroni significance thresholds.
r2VIM successfully detected functional variants alongside nonfunctional variables at rates aligning with Bonferroni-corrected linear regression when applying an optimal importance threshold (numerical counts not reported).
The variable selection metric demonstrated proof-of-concept as an alternative to stringent parametric regression for isolating genetic signals (numerical effect sizes not reported).

Cite This Study

Holzinger et al. (2016) studied this question.

synapsesocial.com/papers/6a869a0da94eefd7bf5130a4 https://doi.org/10.1186/s12919-016-0021-1

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark