AI 中文总结
该研究推出PEtab SciML格式，用于联合估计机制与ML模型参数，支持多种混合模式，配套多语言库与基准，可实现可复现高效的动态SciML模型训练。
AI 中文摘要
摘要：结合机制常微分方程（ODE）与机器学习（ML）组件的动态科学机器学习（SciML）模型，其应用范围涵盖从学习未知生物过程到将辅助数据模态整合进动态建模等场景。为实现可复现且高效的SciML训练，我们推出PEtab SciML——一种可互操作的数据格式，用于指定参数估计问题，其中机制模型与ML模型的参数可从时间序列数据中联合估计。PEtab SciML支持现实问题设置中的多种ML ODE混合模式，配套提供参考Python库，以及分别由AMICI和该链接提供的Python/JAX与Julia下游建模支持，还有一组真实数据基准。可用性与实现：PEtab SciML可在GitHub（该链接）获取，参考Python包可从PyPI安装，且在Linux、macOS和Windows上持续接受测试与支持。
英文摘要
Summary: Dynamic scientific machine learning (SciML) models that combine mechanistic ordinary differential equations (ODEs) with machine learning (ML) components have applications ranging from learning unknown biological processes to integrating auxiliary data modalities into dynamic modelling. To enable reproducible and efficient SciML training, we introduce PEtab SciML, an interoperable data format for specifying parameter estimation problems in which mechanistic and ML model parameters are jointly estimated from time series data. PEtab SciML supports several ML ODE hybridization patterns in realistic problem setups. It is accompanied by a reference Python library and downstream modelling support in Python/JAX and Julia, provided by AMICI and PEtab$.$jl, respectively, and a collection of real data benchmarks. Availability and implementation: PEtab SciML is available on GitHub (https://github.com/PEtab-dev/petab_sciml). The reference Python package is installable from PyPI and is continuously tested and supported on Linux, macOS, and Windows.
