Combining Motifs, CRE Activity, And Gene Expression Data Using ML Greatly Improves the Accuracy of Tissue-Specific TF Network Maps
MotivationReconstructing tissue-specific transcription factor (TF) networks remains challenging. TF motif-based methods often lack functional validation, while expression-based methods struggle to distinguish direct binding from indirect regulation. Integration of diverse data types is necessary to accurately prioritize functional targets directly bound by TFs across human tissues. ResultsWe introduce METANet, a supervised ensemble learning framework that combines TF motifs, cis-regulatory element activity, and linear and non-linear expression-derived features to predict TF binding. Applied to 36 human tissues, METANet significantly outperforms established methods in identifying direct, functional targets of TFs validated by ChIP-seq and gene ontology. Furthermore, METANet captures tissue-specific regulation comparable to existing methods, allowing the identification of reproducible gene-trait associations. Availability and ImplementationAll code and network maps are freely available at Zenodo https://doi.org/10.5281/zenodo.17309371. Contactbrent@wustl.edu.