Fast and Accurate Prediction of Refractive Index of Organic Liquids with Graph Machines

The refractive index (RI) of liquids is a key physical property molecular compounds and materials. In addition to its ubiquitous role in physics, it also exploited impart specific optical properties (transparency, opacity, gloss) materials various end-use products. Since few methods exist accurately estimate this property, we have designed graph machine model (GMM) capable predicting the RI liquid organic containing up 16 different types atoms effective discriminating between stereoisomers. Using 8267 carefully checked values from literature corresponding 2D structures, GMM provides training root mean square relative error less than 0.5%, i.e., an RMSE 0.004 for estimation compounds. predictive ability compared that obtained by several fragment-based approaches. Finally, Docker-based tool proposed predict solely their SMILES code. developed easy apply, as shown video tutorials provided on YouTube.