Global-Local Dirichlet Processes for Identifying Pan-Cancer Subpopulations Using Both Shared and Cancer-Specific Data

2025-09-26

AI Summary

To address the challenge of jointly modeling both globally shared and group-specific variables in clustered genomic data, this paper proposes the Global-Local Dirichlet Process (GLocal DP), a Bayesian nonparametric model. The GLocal DP unifies heterogeneous multi-omics molecular profiles with cancer-specific clinical variables (e.g., CEA, BMI, smoking pack-years), explicitly capturing both population-level structure and within-group fine-grained heterogeneity. Leveraging stick-breaking constructions and finite mixture approximations, we develop an efficient variational inference algorithm for posterior estimation. Applied to pan-gastrointestinal cancer data, the model identifies clinically and molecularly coordinated subtypes that remain undetected by conventional clustering methods. These refined subtypes enhance biological interpretability and significantly improve characterization of tumor heterogeneity and disease progression mechanisms.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

We consider the problem of clustering grouped data for which the observations may include group-specific variables in addition to the variables that are shared across groups. This type of data is common in cancer genomics where the molecular information is usually accompanied by cancer-specific clinical information. Existing grouped clustering methods only consider the shared variables, thereby ignoring valuable information from the cancer-specific variables. To allow for these cancer-specific variables to aid in the clustering, we propose a novel Bayesian nonparametric approach, termed global-local (GLocal) Dirichlet process, that models the ``global-local'' structure of the observations across groups. We characterize the GLocal Dirichlet process using the stick-breaking representation and the representation as a limit of a finite mixture model, which leads to an efficient posterior inference algorithm. We illustrate our model with extensive simulations and a real pan-gastrointestinal cancer dataset. The cancer-specific clinical variables included carcinoembryonic antigen level, patients' body mass index, and the number of cigarettes smoked per day. These important clinical variables refine the clusters of gene expression data and allow us to identify finer sub-clusters, which is not possible in their absence. This refinement aids in the better understanding of tumor progression and heterogeneity. Moreover, our proposed method is applicable beyond the field of cancer genomics to a general grouped clustering framework in the presence of group-specific idiosyncratic variables.

Problem

• Clustering grouped data with shared and group-specific variables
• Identifying cancer subpopulations using genomic and clinical data
• Developing Bayesian nonparametric method for pan-cancer analysis

Innovation

• GLocal Dirichlet process models global-local structure
• Stick-breaking representation enables efficient posterior inference
• Incorporates cancer-specific variables to refine clustering results