Fig. 3: Schematic overview of our newly developed FLSF (FLuorescence prediction with fluoroScaFfold-driven model) and its prediction performance.
From: A modular artificial intelligence framework to facilitate fluorophore design
a The model architecture of FLSF. A domain-knowledge-derived fingerprint based on the 728 fluorescent-scaffold subgroups (called fluoroscaffold) is fused with a message-passing neural network (MPNN) for the feature extraction of the input fluorophore. The feature extraction of the solvent molecule is based on MPNN. The feature vectors of both the fluorophore and the solvent are input together to output a prediction of the property of interest. MLP: multilayer perceptron. b The overall prediction performance of FLSF for different photophysical parameters. λabs: maximum absorption wavelength; λem: maximum emission wavelength; ΦPL: photoluminescence quantum yield; εmax: molar absorption coefficient. c Comparison between FLSF (red points) and TD-DFT (time-dependent density functional theory) calculations (gray points) for λabs (left) and λem (right) prediction. MAE mean absolute error, R2 the coefficient of determination. Source data are provided as a Source data file.
