Predictive regulatory models in Drosophila melanogaster by integrative inference of transcriptional networks
- Daniel Marbach1,
- Sushmita Roy2,
- Ferhat Ay3,
- Patrick E. Meyer2,
- Rogerio Candeias2,
- Tamer Kahveci4,
- Christopher A. Bristow2 and
- Manolis Kellis2,5
- 1 Massachusetts Institute of Technology;
- 2 MIT;
- 3 MIT, University of Florida;
- 4 University of Florida
- ↵* Corresponding author; email: manoli{at}mit.edu
Abstract
Gaining insights on gene regulation from large-scale functional datasets is a grand challenge in systems biology. In this paper, we develop and apply methods for transcriptional regulatory network inference from diverse functional genomics datasets, and demonstrate their value for gene function and gene expression prediction. We formulate the network inference problem in a machine learning framework and use both supervised and unsupervised methods to predict regulatory edges by integrating transcription factor (TF) binding, evolutionarily-conserved sequence motifs, gene expression, and chromatin modification datasets as input features. Applying these methods to Drosophila melanogaster, we predict ~300k regulatory edges in a network of ~600 TFs and 12k target genes. We validate our predictions using known regulatory interactions, gene functional annotations, tissue-specific expression, protein-protein interactions, and three-dimensional maps of chromosome conformation. We use the inferred network to identify putative functions for hundreds of previously-uncharacterized genes, including many in nervous system development, which are independently confirmed based on their tissue-specific expression patterns. Lastly, we use the regulatory network to predict target gene expression levels as a function of TF expression, and find significantly higher predictive power for integrative networks than for motif or ChIP-based networks. Our work reveals the complementarity between physical evidence of regulatory interactions (TF binding, motif conservation) and functional evidence (coordinated expression or chromatin patterns), and demonstrates the power of data integration for network inference and studies of gene regulation at the systems level.
