Markov Chains and Monte Carlo Methods

Simulation-based inference of epidemiological and phylodynamic models via Neural Posterior Estimation

This paper applies Neural Posterior Estimation to infer parameters in epidemiological and phylodynamic models using Ebola outbreak data, showing accurate and reliable posterior estimates.

Collective Posterior Inference from Highly Variable Empirical Replicates

The paper introduces a method for fast and robust collective posterior inference from multiple noisy replicates, achieving state-of-the-art accuracy and efficiency.

Likelihood-Free Parameter Inference for Spatiotemporal Stochastic Biological Models using Neural Posterior Estimation

The paper develops a neural posterior estimation framework for parameter inference in spatiotemporal stochastic biological models, demonstrating its effectiveness across multiple cell migration models.

MCMC-CE: A Novel and Efficient Algorithm for Estimating Small Right-Tail Probabilities of Quadratic Forms with Applications in Genomics

The paper introduces MCMC-CE, an algorithm for estimating small right-tail probabilities of quadratic forms, showing improved accuracy and efficiency in genomics applications.

Generation of virtual populations for quantitative systems pharmacology through advanced sampling methods

This paper evaluates DREAM(ZS) for generating virtual populations in QSP, showing it outperforms Metropolis-Hastings in parameter space exploration and correlation preservation.

An automated convergence diagnostic for phylogenetic MCMC analyses

The paper introduces an automated convergence diagnostic for phylogenetic MCMC analyses, demonstrating high accuracy in detecting convergence issues and enabling real-time evaluation.

hopsy - a methods marketplace for convex polytope sampling in Python

hopsy provides a Python platform for accessing Markov chain Monte Carlo sampling algorithms for convex polytopes, enabling collaboration between developers and users.

Missing data in amortized simulation-based neural posterior estimation

This paper addresses missing data in amortized simulation-based neural posterior estimation by proposing methods to encode and handle missing values, showing improved robustness in inference.

Posterior marginalization accelerates Bayesian inference for dynamical systems

This paper introduces a method to accelerate Bayesian inference for dynamical systems by marginalizing the posterior distribution, improving computational efficiency by up to 50 times in effective sample size.

Informative and adaptive distances and summary statistics in sequential approximate Bayesian computation

This paper improves approximate Bayesian computation by combining adaptive scale normalization with regression-based summary statistics and sensitivity weights, enhancing accuracy and efficiency on heterogeneous data.

Optimus: a general purpose adaptive optimisation engine in R

Optimus is an R-based optimisation engine that enables flexible and adaptive parameter sampling for computational biology tasks.

Efficient inference for agent-based models of real-world phenomena

This paper compares machine learning methods to improve inference efficiency for agent-based simulations of real-world phenomena like tumor growth and disease spread.

Flexible and efficient simulation-based inference for models of decision-making

This paper introduces MNLE, a simulation-based inference method for decision-making models, showing it is more efficient and accurate than existing methods.

Efficient Bayesian inference for mechanistic modelling with high-throughput data

The paper introduces a minibatch Bayesian inference method to efficiently analyze high-throughput imaging data, revealing density-dependent interactions in wound healing.

A flexible Bayesian framework for unbiased estimation of timescales

This paper introduces a Bayesian framework for estimating timescales from dynamic processes, showing it outperforms standard methods on synthetic and primate cortex data.

Parallel power posterior analyses for fast computation of marginal likelihoods in phylogenetics

The paper introduces a parallelization strategy to speed up marginal likelihood estimation in Bayesian phylogenetics, reducing runtime significantly with multiple CPUs.

Convergence Assessment for Bayesian Phylogenetic Analysis using MCMC simulation

This paper develops and tests convergence assessment methods for Bayesian phylogenetic analysis using MCMC simulations and implements them in an R package.

An Introduction to Thermodynamic Integration and Application to Dynamic Causal Models

This paper introduces thermodynamic integration for Bayesian model selection and averaging in dynamic causal models, demonstrating its feasibility with efficient implementation and parallel processing.

Likelihood-free nested sampling for biochemical reaction networks

This paper introduces a likelihood-free nested sampling method for Bayesian inference in stochastic biochemical reaction networks, providing an unbiased evidence estimator and posterior samples with a novel termination criterion.

A new Bayesian methodology for nonlinear model calibration in Computational Systems Biology

This paper introduces a Bayesian method for nonlinear model calibration using omics data, showing it outperforms existing methods in robustness and computational efficiency.

Efficient Exact Inference for Dynamical Systems with Noisy Measurements using Sequential Approximate Bayesian Computation

The paper introduces an efficient algorithm for ABC that accounts for measurement noise, improving parameter estimation accuracy in dynamical systems with noisy data.

GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation

GpABC is a Julia package that implements ABC methods with Gaussian process emulation for parameter inference and model selection in systems biology models.

Evaluating probabilistic programming and fast variational Bayesian inference in phylogenetics

This study compares variational inference and MCMC methods for phylogenetic inference using Stan, finding variational methods faster but less accurate.

Guided proposals for efficient weighted stochastic simulation

The paper introduces an importance density for importance sampling to estimate rare event probabilities in biochemical systems, showing improved performance over existing methods.

pyABC: distributed, likelihood-free inference

pyABC provides a distributed and scalable framework for likelihood-free inference using ABC-SMC, enabling efficient computation and customization for complex models.

Effective Online Bayesian Phylogenetics Via Sequential Monte Carlo With Guided Proposals

This paper develops and evaluates online Bayesian phylogenetic inference methods using sequential Monte Carlo with guided proposals, showing reduced computation time compared to MCMC-based methods without significant accuracy loss.