Identifying SNPs predictive of phenotype using random forests

By Alexandre Bureau, Josée Dupuis, Kathleen Falls, Kathryn L. Lunetta, B. Hayward, T. Keith, P. van Eerdewegh. Genetic Epidemiology, 2005

388 citations recorded by the source corpus.

Subfields: Genetics, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/8f36c987892be0f18048c9011267b49157d216eb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Genetics

In Molecular Biology

Citations in the corpus

A REVIEW OF STATISTICAL METHODS FOR DETERMINATION OF RELATIVE IMPORTANCE OF CORRELATED PREDICTORS AND IDENTIFICATION OF DRIVERS OF CONSUMER LIKING (2012, background): “There are many applications of variable-importance measures yielded by RFs (cf., e.g., Lunetta et al. 2004; Bureau et al. 2005; Huang et al. 2005; Berk et al. 2006; Diaz-Uriarte and de Andres 2006; Qi et al. 2006).”
A random forest approach to the detection of epistatic interactions in case-control studies (2009, methodology): “Many machine learning methods have also been applied to this research field from the viewpoint of binary classification and feature selection [18-24].”
An Introduction to Recursive Partitioning: Rationale, Application and Characteristics of Classification and Regression Trees, Bagging and Random Forests (2009, neutral): “Therefore, Bureau et al. (2005) and Heidema et al. (2006) pointed out that the recursive partitioning strategy is a clear advantage of random forests as opposed to more common methods like logistic regression in high-dimensional settings.”
Bias in random forest variable importance measures: Illustrations, sources and a solution (2007, methodology): “[1], who detect SNP-SNP interactions in the case-control context by means of computing a random forest variable importance measure for each polymorphism.”
Detecting gene-gene interactions that underlie human diseases (2009, methodology): “( Box 2 ), which has been used in several genetic studie”
Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics (2012, methodology): “In contrast, Bureau et al. [11] suggest to permute values of possibly interacting predictors together when calculating the permutation VIM.”
Random Forests for Genomic Data Analysis (2012, methodology): “Bureau et al. [53] applied RF on 42 SNPs from the asthma susceptibility gene ADAM33 to achieve 44% misclassi ﬁ cation rate.”
Epigenetic correlates of plant phenotypic plasticity: DNA methylation differs between prickly and nonprickly leaves in heterophyllous Ilex aquifolium (Aquifoliaceae) trees (2013, methodology): “…on random forests (Breiman, 2001; Hastie, Tibshirani & Friedman, 2009; for applications of random forests in genomics and ecology, see, for example, Bureau et al., 2005; Cutler et al., 2007) to identify all individual MSAP markers that were relevant to the binary classification of leaves into…”
Boruta – A System for Feature Selection (2010, methodology): “It has been often used for analysis when both classifier and identification of important variables were the goals of the study, see for example [13] [14].”
Genomic Selection in Plant Breeding: A Comparison of Models (2012, background): “They could also be useful in the prediction of breeding values (Moser et al., 2009; González-Recio and Forni, 2011) and identifi cation of causal polymorphisms (Bureau et al., 2005).”
Protein Networks as Logic Functions in Development and Cancer (2011, background): “Motivated by [36], we also assess the importance of pairs of genes in a tree — in our study these pairs are constrained by the network neighborhood.”
A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction (2022, background): “For example, Bureau et al. (Bureau et al., 2005), identi ﬁ ed relevant SNPs from a dataset of just 42 SNPs. Lopez et al. (López et al., 2018) implemented a random forest algorithm to identify relevant SNPs from a dataset that contains a total of 101 SNPs that have been previously associated with typ”
Detecting gene-gene interactions using a permutation-based random forest method (2016, background): “Although RF implicitly considers interactions, further work is required to separate main effects from interactions in RF since VIMs as estimated in RF reflect both main and interaction effects [24, 25].”
A Review of Ensemble Methods in Bioinformatics (2010, methodology): “The same group [59] then applied the random forests algorithm in the context of the case-control association study.”
Empirical characterization of random forest variable importance measures (2008, background): “Another simulation study was conducted which examined variable importance in the context of categorical predictor variables (single nucleotide polymorphisms (SNPs)) (Bureau et al., 2005).”
Zeileis Conditional Variable Importance for Random Forests (2015, background): “Recently, the variable importance measures yielded by random forests have also been suggested for the selection of relevant predictor variables in the analysis of microarray data, DNA sequencing and other applications [2-5].”