PFAS Rigidity Modeling
Applying Hybrid GNN architectures to predict the structural rigidity and environmental persistence of Per- and Polyfluoroalkyl Substances (PFAS) in industrial water cycles.
Commerical
Incentive.
Commercial filtration systems lack the ability to predict molecular degradation at scale. This research aims to identify "Unicorn" leads for biodegradable alternatives before synthesis.
Strategic
Execution.
The "Dual Brain" architecture combines Graph Convolutional Networks (GCN) with RDKit molecular descriptors. We utilized transfer learning from the ChEMBL database to specialize our toxicity prediction on fluorinated chains.
Research Stack
Derived Value.
Our model identified 14 candidates for alternative surfactants that demonstrate a 60% higher degradation rate in standardized environmental simulations while maintaining industrial surfactant efficiency.