PEtab.jl - Efficient Parameter Estimation for Dynamic Models
The Julia Programming Language via YouTube
Master Production-Ready Machine Learning, Step by Step
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Overview
AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off Coursera Plus Annual.
Unlock All Certificates
Explore efficient parameter estimation for dynamic models in biology and pharmaceutical research using PEtab.jl, a Julia package leveraging the SciML ecosystem. Learn how to import problems specified in the PEtab standard format, utilize SBMLImporter.jl for importing SBML models, and set up parameter estimation problems directly in Julia using Catalyst.jl or ModelingToolkit.jl. Discover various gradient computation methods, including ForwardDiff and SciMLSensitivity, and gain insights on selecting the most appropriate approach. Evaluate the performance of PEtab.jl compared to existing tools like pyPESTO and AMICI through an extensive benchmark on real models with real data, addressing the question of Julia's suitability for parameter estimation in dynamic models within biological and pharmaceutical contexts.
Syllabus
PEtab.jl - Efficient parameter estimation for dynamic models | Persson | JuliaCon 2024
Taught by
The Julia Programming Language