A smile is all you need: predicting limiting activity coefficients from SMILES with natural language processing
Benedikt Winter, Clemens Winter, Johannes Schilling, André Bardow
Abstract
SPT is a natural language processing model that predicts limiting activity coefficients from SMILES. High accuracy is achieved by pre-training the model on millions of synthetic data points and fine-tuning the model on limited experimental data.
Topics & Concepts
LimitingNatural (archaeology)Computer scienceNatural language processingEngineeringGeologyMechanical engineeringPaleontologyProcess Optimization and IntegrationBusiness Process Modeling and AnalysisAdvanced Data Processing Techniques