Deep and Probabilistic Models for Gene Regulatory Network Inference
Machine Learning
Summary
The authors focus on improving ways to map how proteins called transcription factors control genes. They create two new tools: one that uses a smart math model to make better guesses about these connections and shows how sure it is about each guess, and another that uses a learned understanding of DNA sequences to predict these connections across different species. Their approach combines DNA-based predictions with careful statistical methods to get clearer and more reliable gene control maps, even when full information isn’t available. This helps study gene regulation in many different biological systems more effectively.
Authors
Claudia Skok Gibbs
Abstract
Gene regulatory networks (GRNs) link transcription factor (TF) proteins to their target genes, yet reconstructing these networks from genome-wide data remains challenging under practical and methodological constraints. Many methods couple modeling assumptions to a specific inference procedure and rely on heuristic model selection, while evaluation is constrained by incomplete reference networks and point-estimate outputs that lack uncertainty. GRN reconstruction also depends on prior knowledge to constrain TF-gene interactions, yet available priors are often assay-dependent and difficult to transfer across species and less-characterized systems. In this thesis, we develop two complementary frameworks that address these limitations. In the first, PMF-GRN casts GRN inference as a probabilistic graphical model optimized by variational inference, enabling principled model selection and uncertainty-aware edge estimates. In the second, GLM-Prior addresses the prior bottleneck by fine-tuning the pretrained Nucleotide Transformer to predict TF-target gene interactions directly from nucleotide sequence, while generalizing across yeast, mouse, and human settings. Together, PMF-GRN and GLM-Prior motivate a dual-stage view of GRN reconstruction in which sequence-derived priors provide a transferable starting scaffold and probabilistic inference refines regulatory estimates with quantified uncertainty under incomplete evaluation resources.