U.S. Department of EnergyOffice of Scientific and Technical Information
Evaluating the Performance of Random Forest and Iterative Random Forest Based Methods when Applied to Gene Expression Data
Abstract
Gene-to-gene networks, such as Gene Regulatory Networks (GRN) and Predictive Expression Networks (PEN) capture relationships between genes and are beneficial for use in downstream biological analyses. There exists multiple network inference tools to produce these gene-to-gene networks from matrices of gene expression data. Random Forest-Leave One Out Prediction (RF-LOOP) is a method that has been shown to be efficient at producing these gene-to-gene networks, frequently known as GEne Network Inference with Ensemble of trees (GENIE3). Here we validate that iterative Random Forest-Leave One Out Prediction (iRF-LOOP) produces higher quality networks than GENIE3. We use both synthetic and empirical networks from the Dialogue for Reverse Engineering Assessment and Methods (DREAM) Challenges by Sage Bionetworks, as well as two additional empirical networks created from Arabidopsis thaliana and Populus trichocarpa expression data.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Publication Date:
- DOE Contract Number:
- AC05-00OR22725
- Research Org.:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Biological and Environmental Research (BER). Biological Systems Science Division
- Subject:
- iRF-Loop, expression network, Populus Trichocarpa
- OSTI Identifier:
- 1871691
- DOI:
- https://doi.org/10.25983/1871691
Citation Formats
Walker, Angela M, Cliff, Ashley, Romero, Jonathon, Shah, Manesh, Jones, Piet, Gazola, Joao Gabriel Felipe Machado, Jacobson, Daniel, and Kainer, David. Evaluating the Performance of Random Forest and Iterative Random Forest Based Methods when Applied to Gene Expression Data. United States: N. p., 2022.
Web. doi:10.25983/1871691.
Walker, Angela M, Cliff, Ashley, Romero, Jonathon, Shah, Manesh, Jones, Piet, Gazola, Joao Gabriel Felipe Machado, Jacobson, Daniel, & Kainer, David. Evaluating the Performance of Random Forest and Iterative Random Forest Based Methods when Applied to Gene Expression Data. United States. doi:https://doi.org/10.25983/1871691
Walker, Angela M, Cliff, Ashley, Romero, Jonathon, Shah, Manesh, Jones, Piet, Gazola, Joao Gabriel Felipe Machado, Jacobson, Daniel, and Kainer, David. 2022.
"Evaluating the Performance of Random Forest and Iterative Random Forest Based Methods when Applied to Gene Expression Data". United States. doi:https://doi.org/10.25983/1871691. https://www.osti.gov/servlets/purl/1871691. Pub date:Thu Jun 09 04:00:00 UTC 2022
@article{osti_1871691,
title = {Evaluating the Performance of Random Forest and Iterative Random Forest Based Methods when Applied to Gene Expression Data},
author = {Walker, Angela M and Cliff, Ashley and Romero, Jonathon and Shah, Manesh and Jones, Piet and Gazola, Joao Gabriel Felipe Machado and Jacobson, Daniel and Kainer, David},
abstractNote = {Gene-to-gene networks, such as Gene Regulatory Networks (GRN) and Predictive Expression Networks (PEN) capture relationships between genes and are beneficial for use in downstream biological analyses. There exists multiple network inference tools to produce these gene-to-gene networks from matrices of gene expression data. Random Forest-Leave One Out Prediction (RF-LOOP) is a method that has been shown to be efficient at producing these gene-to-gene networks, frequently known as GEne Network Inference with Ensemble of trees (GENIE3). Here we validate that iterative Random Forest-Leave One Out Prediction (iRF-LOOP) produces higher quality networks than GENIE3. We use both synthetic and empirical networks from the Dialogue for Reverse Engineering Assessment and Methods (DREAM) Challenges by Sage Bionetworks, as well as two additional empirical networks created from Arabidopsis thaliana and Populus trichocarpa expression data.},
doi = {10.25983/1871691},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Jun 09 04:00:00 UTC 2022},
month = {Thu Jun 09 04:00:00 UTC 2022}
}