OutPredict: multiple datasets can improve prediction of expression and inference of causality

Abstract

the ability to accurately predict the causal relationships from transcription factors to genes would greatly enhance our understanding of transcriptional dynamics. this could lead to applications in which one or more transcription factors could be manipulated to effect a change in genes leading to the enhancement of some desired trait. Here we present a method called outpredict that constructs a model for each gene based on time series (and other) data and that predicts gene's expression in a previously unseen subsequent time point. the model also infers causal relationships based on the most important transcription factors for each gene model, some of which have been validated from previous physical experiments. The method benefits from known network edges and steady-state data to enhance predictive accuracy. our results across B. subtilis, Arabidopsis, e.coli, Drosophila and the DREAM4 simulated in silico dataset show improved predictive accuracy ranging from 40% to 60% over other state-of-the-art methods. We find that gene expression models can benefit from the addition of steady-state data to predict expression values of time series. Finally, we validate, based on limited available data, that the influential edges we infer correspond to known relationships significantly more than expected by chance or by state-of-the-art methods.

Validation of a high-confidence regulatory network for gene-to-NUE phenotype in field-grown rice

“…Additionally, in this study, we demonstrate that the accuracy of rice TARGET data is comparable to in planta data at validating network predictions (Supplementary Figure 6B). This finding suggests that rice TARGET data can be used to validate GRN predictions in rice, as was shown in Arabidopsis (Varala et al, 2018;Brooks et al, 2019;Brooks et al,2020;Cirrone et al, 2020). In our study, we validated that OsbZIP23 regulates both nitrogen and water-related genes including, NIA1 which is involved in nitrate assimilation (Subudhi et al, 2020), OsDhn1 which is induced by drought (Lee et al, 2013), OsPIP1;2 which is an aquaporin that improves yield (Xu et al, 2019), ABCG4 which is involved in abiotic stress responses (Matsuda et al, 2012), and OsPP2C30 which a core regulator in the ABA signaling pathway (Zong et al, 2016).…”

Integrative omics approaches for biosynthetic pathway discovery in plants

“…This tool can handle time-series data to infer GRNs. OutPredict 55 is another random-forest-based method that can incorporate priors (curated regulatory data) together with the dynamic time-series data. It has been successful in inferring causal edges between a TF and a target gene.…”

An Adaptive Stacking Ensemble Approach to Network Inference Outperforms Any Single Method

“…High weights correspond to regulatory edges. Examples include GENIE3 7 , a faster alternative GRNBoost2 8 , and the inference method OutPredict 9 . OutPredict also takes prior information (e.g., binding data) into account during training and test.…”