Atmospheric bioaerosols modelling and AI-powered simulation: From pollen protein sequencing to machine learning based molecular dynamics

Ziel

ILMATICS pioneers an integrated experimental–computational framework to reveal how allergenic pollen proteins influence both public health and cloud microphysics. The project establishes an end-to-end pipeline linking molecular sequence data to environmental and climatic impacts. Specifically, ILMATICS will (i) use Oxford Nanopore Technology (ONT) to directly sequence and identify allergenic and ice-active pollen proteins; (ii) develop a next-generation machine-learning force field (ML-FF) framework that achieves near-quantum accuracy in simulating protein–water interactions; (iii) perform molecular simulations and laboratory freezing experiments to uncover the mechanisms of ice nucleation; and (iv) refine the Adsorption Freezing Model (AFM) using simulation-derived parameters to better describe real atmospheric processes.

This uniquely timed effort leverages recent advances in nanopore protein sequencing and ML-FF methods, along with the PI’s access to Finnish Meteorological Institute (FMI) sequencing facilities, expertise in nucleation theory, and collaboration with EPFL’s Portable Ice Nucleation Experiment (PINE) cloud chamber for world-class validation. By connecting molecular mechanisms of pollen proteins to both allergy and cloud formation, ILMATICS will deliver new predictive tools for national meteorological and health infrastructures, directly supporting EU missions on climate adaptation and public health. The outcome will transform our understanding of pollen as a dual biological–climatic agent, enabling improved daily-life forecasts, reduced health risks, and enhanced climate resilience.

Wissenschaftliches Gebiet (EuroSciVoc)

Dieses Projekt wurde noch nicht bei EuroSciVoc klassifiziert.
Schlagen Sie die Wissenschaftsbereiche vor, die Ihrer Einschätzung nach besonders relevant sind, und helfen Sie uns, unseren Klassifizierungsdienst zu verbessern.