Through the application of an advanced machine learning approach for large-scale functional data integration, the authors performed, for the first time, a systematic regulatory annotation for nearly all Arabidopsis genes. Extensive validation using different types of experimental datasets revealed a strong enrichment for functional interactions. Predicting transcription factor functions based on an integrative network (iGRN) indicated that for various biological processes many known regulators could be recovered. Experimental validation confirmed 13 novel regulators involved in reactive oxygen species stress regulation, demonstrating that the iGRN offers a high-quality starting point to enhance our understanding of gene regulation in plants.
