PureP-ML is a powerful tool designed for Pure Component Property Prediction using machine learning-based models. By simply inputting the compound’s SMILES (Simplified Molecular Input Line Entry System, is a line notation specification for describing chemical structures), users can quickly determine the estimated property values of organic chemicals, refrigerants, and other pure chemical compounds.
PureP-ML offers two models, the GP-WP model and the GC-ML model for estimating the property values of pure chemical compounds.
The 20 estimated property values predicted by the GP-WP model
Normal boiling point (Tb)
Critical volume (Vc)
Critical temperature (Tc)
Critical pressure (Pc)
Autoignition temperature (AiT)
Bioconcentration factor (Bcf)
Gibbs energy of formation at 298 K (Gf)
Standard enthalpy of formation (Hf)
Enthalpy of fusion at 298 K (Hfus)
Hildebrand solubility parameter (HsolP)
Enthalpy of vaporization at 298 K (Hv)
LC50 (fathead minnow) (Lc50_fm)
Toxicity (oral rat) (Ld50)
Liquid molar volume at 298 K (Lmv)
Octanol–water partition coefficient (log(P))
Aqueous solubility (log(WS))
Permissible exposure limit (Osha_twa)
Photochemical oxidation potential (Pco)
Acid dissociation constant (PKa)
Normal melting point (Tm)
The 25 estimated property values predicted by the GC-ML model
