Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data
Abstract
Diagnostic errors and mislabeling are common in biomedicine, which compromise the reliability of predictive models and data-driven outcomes. Stratifying unlabeled biomedical data based on complex relationships between features eliminates the need for data labels and overcomes the limitations of supervised learning. Traditional clustering methods assume restrictive data distributions, making them suboptimal for capturing complex dependencies in high-dimensional biomedical data. This paper introduces a novel cluster-friendly data presentation framework that integrates the non-Gaussian and non-linear feature dependence of copula models with an ensemble of causal structure discovery (CSD) methods based on Directed Acyclic Graphs (DAGs). While copulas model flexible multivariate distributions by relaxing assumptions related to multivariate normality, linear dependence, and symmetric relationships, an ensemble of DAG-based CSD methods identifies stable causal relationships between features. When clustered using K-means, the new data representation obtained by the proposed copula-adapted DAG (CopDAG) ranks first among the 12 methods in normalized clustering accuracy and adjusted Rand index across 16 biomedical datasets. Our CopDAG method predicts ground-truth class labels directly from feature relationships without data annotations and supervised learning, while also providing cluster visualizations and explainable causal structures of the biomedical data features.
Related
- Morse-Maxwell Theory for Directed Acyclic Graph
- Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic Graphs
- Semiparametric Bayesian structure learning of nonparanormal directed acyclic graphs with local--global shrinkage
- Data-Driven Learning of Directed Acyclic Graphs in Gaussian Linear Structural Equation Models with Latent Variables
- Nonparanormal Bayesian Learning of Directed Acyclic Graphs under Gamma and Inverse-Gamma Innovation Priors: Closed-Form Scores and Informed Sampling
BibTeX
@misc{rathnasekara2026copula,
title = {{Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data}},
author = {Heranga K. Rathnasekara and Norou Diawara and Manar D. Samad},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.16240},
eprint = {2609.16240},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.16240},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Copula Adapted Directed Acyclic Graph for Cluster Representation of Biomedical Data
AU - Heranga K. Rathnasekara
AU - Norou Diawara
AU - Manar D. Samad
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.16240
UR - https://arxiv.org/abs/2609.16240
AB - Diagnostic errors and mislabeling are common in biomedicine, which compromise the reliability of predictive models and data-driven outcomes. Stratifying unlabeled biomedical data based on complex relationships between features eliminates the need for data labels and overcomes the limitations of supervised learning. Traditional clustering methods assume restrictive data distributions, making them suboptimal for capturing complex dependencies in high-dimensional biomedical data. This paper introduces a novel cluster-friendly data presentation framework that integrates the non-Gaussian and non-linear feature dependence of copula models with an ensemble of causal structure discovery (CSD) methods based on Directed Acyclic Graphs (DAGs). While copulas model flexible multivariate distributions by relaxing assumptions related to multivariate normality, linear dependence, and symmetric relationships, an ensemble of DAG-based CSD methods identifies stable causal relationships between features. When clustered using K-means, the new data representation obtained by the proposed copula-adapted DAG (CopDAG) ranks first among the 12 methods in normalized clustering accuracy and adjusted Rand index across 16 biomedical datasets. Our CopDAG method predicts ground-truth class labels directly from feature relationships without data annotations and supervised learning, while also providing cluster visualizations and explainable causal structures of the biomedical data features.
ER -