Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

2025-01-17

AI Summary

To address inference distortion in gene regulatory network (GRN) reconstruction from single-cell gene expression data—caused by selection bias (e.g., preferential detection of highly expressed genes) and unobserved confounders (e.g., non-coding RNAs)—this paper proposes the first nonparametric causal inference framework jointly modeling selection bias and latent confounders. Grounded in causal graphical models, perturbation-invariance principles, and generalized method of moments estimation, the method requires only multi-gene perturbation experiments and a lightweight graph-structure prior, without strong distributional assumptions, and achieves partial identifiability. Evaluated on synthetic benchmarks and real single-cell datasets (mESC, PBMC), it significantly outperforms state-of-the-art methods—including GENIE3, PIDC, and SCENIC—with an average 28% improvement in area under the precision–recall curve (AUPRC), markedly enhancing recovery accuracy of true regulatory interactions.

Technology Category

• Reasoning under Uncertainty: Graphical Models
• Machine Learning: Probabilistic Circuits and Graphical Models
• Game Theory and Economic Paradigms: Imperfect Information

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Gene Regulatory Network Inference (GRNI) aims to identify causal relationships among genes using gene expression data, providing insights into regulatory mechanisms. A significant yet often overlooked challenge is selection bias, a process where only cells meeting specific criteria, such as gene expression thresholds, survive or are observed, distorting the true joint distribution of genes and thus biasing GRNI results. Furthermore, gene expression is influenced by latent confounders, such as non-coding RNAs, which add complexity to GRNI. To address these challenges, we propose GISL (Gene Regulatory Network Inference in the presence of Selection bias and Latent confounders), a novel algorithm to infer true regulatory relationships in the presence of selection and confounding issues. Leveraging data obtained via multiple gene perturbation experiments, we show that the true regulatory relationships, as well as selection processes and latent confounders can be partially identified without strong parametric models and under mild graphical assumptions. Experimental results on both synthetic and real-world single-cell gene expression datasets demonstrate the superiority of GISL over existing methods.

Problem

• Gene Regulatory Network Inference
• Selection Bias
• Unobserved Confounders

Innovation

• GISL
• Gene Regulatory Network Inference (GRNI)
• Bias Correction