Evaluating the performance of random forest and iterative random forest based methods when applied to gene expression data

Angelica M Walker; Ashley Cliff; Jonathon Romero; Manesh B Shah; Piet Jones; Joao Gabriel Felipe Machado Gazolla; Daniel A Jacobson; David Kainer

doi:10.1016/j.csbj.2022.06.037

Evaluating the performance of random forest and iterative random forest based methods when applied to gene expression data

Comput Struct Biotechnol J. 2022 Jun 22:20:3372-3386. doi: 10.1016/j.csbj.2022.06.037. eCollection 2022.

Authors

Angelica M Walker¹, Ashley Cliff¹, Jonathon Romero¹, Manesh B Shah², Piet Jones¹, Joao Gabriel Felipe Machado Gazolla², Daniel A Jacobson², David Kainer²

Affiliations

¹ The Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee Knoxville, 821 Volunteer Blvd, Knoxville 37996, TN, USA.
² Computational and Predictive Biology, Oak Ridge National Laboratory, 1 Bethel Valley Rd, Oak Ridge 37830, TN, USA.

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). Random Forest can be replaced in this process by iterative Random Forest (iRF), which performs variable selection and boosting. Here we validate that iterative Random Forest-Leave One Out Prediction (iRF-LOOP) produces higher quality networks than GENIE3 (RF-LOOP). 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.

Keywords: GENIE3, GEne Network Inference with Ensemble of trees; GRN, Gene Regulatory Network; Gene expression networks; Iterative random forest; Network biology; PEN, Predictive Expression Network; RF, Random Forest; RF-LOOP, Random Forest Leave One Out Prediction; Random forest; iRF, iterative Random Forest; iRF-LOOP, iterativeRandom Forest Leave One Out Prediction.