Projects per year
Abstract
We report a method to predict physicochemical properties of druglike molecules using a classical statistical mechanics based solvent model combined with machine learning. The RISMMOLINF method introduced here provides an accurate technique to characterize solvation and desolvation processes based on solutesolvent correlation functions computed by the 1D Reference Interaction Site Model of the Integral Equation Theory of Molecular Liquids. These functions can be obtained in a matter of minutes for most small organic and druglike molecules using existing software (RISMMOL) (Sergiievskyi, V. P.; Hackbusch, W.; Fedorov, M. V. J. Comput. Chem. 2011, 32, 19821992.). Predictions of caco2 cell permeability and hydration free energy obtained using the RISMMOLINF method are shown to be more accurate than the stateoftheart tools for benchmark datasets. Due to the importance of solvation and desolvation effects in biological systems, it is anticipated that the RISMMOLINF approach will find many applications in biophysical and biomedical property prediction.
Original language  English 

Pages (fromto)  3420–3432 
Number of pages  13 
Journal  Molecular Pharmaceutics 
Volume  12 
Issue number  9 
Early online date  26 Jul 2015 
DOIs  
Publication status  Published  8 Sep 2015 
Keywords
 ADME
 ADMET
 bioavailability
 caco2
 drug discovery
 druglike
 hydration free energy
 IET
 integral equation theory of molecular liquids
 permeability
 QSAR
 QSPR
 Random Forest
 reference interaction site model
 RISM
 solvation free energy
 statistical mechanics
Fingerprint
Dive into the research topics of 'Fast and general method to predict the physicochemical properties of druglike molecules using the integral equation theory of molecular liquids'. Together they form a unique fingerprint.Projects
 1 Active

Accurate permeability prediction for “New Modalities” compounds using 3D RISM
1/10/18 → 30/09/21
Project: Research