Bayesian Modeling and Causal Inference

Causal reasoning is domain-specific in the human brain

This study investigates whether causal reasoning in the human brain involves a unified system or domain-specific regions, finding distinct brain networks for social and physical causal reasoning.

Sparse dynamic graphical models for longitudinal non-Gaussian data

The paper introduces a latent Gaussian dynamic graphical model for longitudinal non-Gaussian data, showing it can recover both contemporaneous and lag-one temporal dependence structures in microbiome data.

Emergent representations of graphical structure in mechanistic neural models of causal judgment

This paper shows that recurrent neural networks can learn and represent causal structures from observational data, forming implicit beliefs about the full graphical structure even when trained only on pairwise queries.

A normative account of human temporal structure learning

This study develops a Bayesian model of temporal structure learning and shows it aligns with human behavior in predicting outcomes across different temporal environments.

Bootstrap-based criteria for identifying differences between learned Bayesian networks

This paper develops bootstrap-based criteria to identify meaningful differences between Bayesian networks and demonstrates their effectiveness using simulated data.

Bayesian Network Structure Learning: The NewCalibrated Minimum Uncertainty Criterion andDiscriminative Power Evaluation Framework

This paper introduces a calibrated Minimum Uncertainty criterion for Bayesian network structure learning and evaluates scoring criteria's discriminative power using real biomedical data.

DeepCEF: A Deep Causal Estimation Framework for Complex Biological Systems Integrating Local Scores, Independence Tests, and Relation Attributes

This paper introduces a deep learning framework for causal estimation in complex biological systems, combining local scores, independence tests, and variable attributes to improve accuracy and adaptability.

Statistical Causal Discovery in Developing and Refining Adverse Outcome Pathway (AOP)

This paper applies statistical causal discovery to ecotoxicology data to improve adverse outcome pathway models by identifying causal relationships and handling missing data.

Identifiability of Bayesian Models of Cognition

This study investigates the identifiability of Bayesian cognitive models from behavioral data, showing that key components can be reliably recovered under certain conditions.

Macro-level causal discovery from single-time-point observations of ecological dynamical systems

The paper shows that causal discovery algorithms can identify macro-level causal structures from single-time-point ecological data by detecting clustered super-unshielded colliders.

Probabilistic Graphical Modeling under Heterogeneity

This paper introduces GraphR, a Bayesian method for probabilistic graphical modeling under sample heterogeneity, showing improved performance in network estimation and computational efficiency.

MRSL: A phenome-wide causal discovery algorithm based on GWAS summary data

MRSL uses GWAS summary data to discover causal relationships between biomarkers and diseases, achieving higher accuracy and speed than existing methods.

Causal inference using deep-learning variable selection identifies and incorporates direct and indirect causalities in complex biological systems

This paper introduces causalDeepVASE, a deep-learning method for causal inference that identifies both direct and indirect causal relationships in biological systems, outperforming existing methods in simulated and biological data.

GRASP: a Bayesian network structure learning method using adaptive sequential Monte Carlo

GRASP is a Bayesian network structure learning method that uses adaptive sequential Monte Carlo to improve network discovery from genomic data.

BNMCMC: a software for learning and visualizing Bayesian networks using MCMC methods

BNMCMC is a software tool for inferring and visualizing Bayesian networks using MCMC methods, improving upon standard samplers by avoiding local optima.

Exploiting General Independence Criteria For Network Inference

This study compares generalised independence criteria for network inference, finding that distance covariance performs well on biological datasets.