Iterative Random Forests to detect predictive and stable high-order interactions

Abstract

Genomics has revolutionized biology, enabling the interrogation of whole transcriptomes, genome-wide binding sites for proteins, and many other molecular processes. However, individual genomic assays measure elements that interact in vivo as components of larger molecular machines. Understanding how these high-order interactions drive gene expression presents a substantial statistical challenge. Building on Random Forests (RF), Random Intersection Trees (RITs), and through extensive, biologically inspired simulations, we developed the iterative Random Forest algorithm (iRF). iRF trains a feature-weighted ensemble of decision trees to detect stable, high-order interactions with same order of computational cost as RF. We demonstrate the utility of iRF for high-order interaction discovery in two prediction problems: enhancer activity in the early Drosophila embryo and alternative splicing of primary transcripts in human derived cell lines. In Drosophila, among the 20 pairwise transcription factor interactions iRF identifies as stable (returned in more than half of bootstrap replicates), 80% have been previously reported as physical interactions. Moreover, novel third-order interactions, e.g. between Zelda (Zld), Giant (Gt), and Twist (Twi), suggest high-order relationships that are candidates for follow-up experiments. In human-derived cells, iRF re-discovered a central role of H3K36me3 in chromatin-mediated splicing regulation, and identified novel 5th and 6th order interactions, indicative of multi-valent nucleosomes with specific roles in splicing regulation. By decoupling the order of interactions from the computational cost of identification, iRF opens new avenues of inquiry into the molecular mechanisms underlying genome biology.

References in corpus (1)

• Predictive learning via rule ensembles

Cited by in corpus (20)

• Interpretable machine learning: definitions, methods, and applications
• Veridical Data Science
• A Debiased MDI Feature Importance Measure for Random Forests
• Learning stable and predictive structures in kinetic systems: Benefits of a causal approach
• PLIT: An alignment-free computational tool for identification of long non-coding RNAs in plant transcriptomic datasets
• SHAFF: Fast and consistent SHApley eFfect estimates via random Forests
• Provable Boolean Interaction Recovery from Tree Ensemble obtained via Random Forests
• Signed iterative random forests to identify enhancer-associated transcription factor binding
• Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance
• Sharp Analysis of a Simple Model for Random Forests
• Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees
• Learning High-Order Interactions via Targeted Pattern Search
• A stability-driven protocol for drug response interpretable prediction (staDRIP)
• Lessons from a human-in-the-loop machine learning approach for identifying vacant, abandoned, and deteriorated properties in Savannah, Georgia
• Stable discovery of interpretable subgroups via calibration in causal studies
• A cautionary tale on fitting decision trees to data from additive models: generalization lower bounds
• Tree Boosted Varying Coefficient Models
• A Self-Penalizing Objective Function for Scalable Interaction Detection
• JigSaw: A tool for discovering explanatory high-order interactions from random forests
• Data-informed Emulators for Multi-Physics Simulations