Actions Panel
Bayesian Workflow in Pumas
Why Bayesian in Pumas? A wide of priors and error models, both marginal and joint MCMC, and the fastest ODE solvers. Come experience it!
When and where
Date and time
June 30 · 8:30am - July 1 · 5pm CEST
Location
Palexco Convention and Exhibition Centre Mlle. de Trasatlánticos 15003 A Coruña Spain
Refund Policy
About this event
- 1 day 8 hours
- Mobile eTicket
Bayesian Workflow in Pumas
Presented by Pumas-AI, Inc.
This hands-on workshop is designed for novices in Bayesian methods and relatively experienced individuals dealing with pharmacometrics. Pharmaceutical Modelling and Simulation (Pumas) is a domain-specific extension of the Julia differential equation solver libraries for performing analyses of pharmacometric models. Attendees will learn Bayesian methods and how to build Bayesian PKPD workflows in Pumas.
At the end of the workshop, participants will:
- Gain an understanding of Bayesian methods
- Gain an overview of the Pumas modelling interface
- Learn how to specify priors for parameter values
- Gain an understanding of Markov Chain Monte Carlo sampling methods
- Learn how to perform Bayesian inference for models using Pumas
- Learn how to perform post-processing of results for reporting
- Learn how to perform cross-validation and model selection
June 30, 2023
13:00-14:30 Why Bayesian?
14:30-15:30 Introduction to probability and Bayesian statistics
15:30-15:45 Coffee Break
15:45-17:00 Hands-on: Bayesian Pharmacokinetic Model
July 1, 2023
08:30-09:00 Hands -on: Population Pharmacokinetic Modeling - Overview of Pumas
09:00-10:00 Hierarchical Models in Pumas
10:00-10:15 Coffee Break
10:15-11:15 Hands-on: Bayesian Population Pharmacokinetic Modeling Model
11:15-12:30 Hands-on: Posterior predictions and simulations
12:30-13:30 Lunch Break
13:30-15:30 Markov Chain Monte Carlo and Convergence Diagnostics
15:45-16:00 Coffee Break
16:00-17:00 Hands-on: Cross-validation and model evaluation
Tags
About the organizer
Pumas-AI’s vision is to double pharmaceutical and patient care success by democratizing tools and education in the health care data analytics space. Pumas is its first product developed to provide analytic capabilities for drug/biotech development and therapeutic decision making. It leverages the power of the Julia programming language to combine modern AI with traditional mechanistic models to gain massive computational efficiency. Pumas-AI was founded by members of the University of Maryland School of Pharmacy (UMB) and boasts of a team backed by scientists from the Applied Mathematics Department at MIT, JuliaHub, Inc. and domain experts from UMB.