Repository logo

pkCSM: Predicting Small-Molecule Pharmacokinetic and Toxicity Properties Using Graph-Based Signatures.

Change log


Pires, Douglas EV 
Blundell, Tom L 
Ascher, David B 


Drug development has a high attrition rate, with poor pharmacokinetic and safety properties a significant hurdle. Computational approaches may help minimize these risks. We have developed a novel approach (pkCSM) which uses graph-based signatures to develop predictive models of central ADMET properties for drug development. pkCSM performs as well or better than current methods. A freely accessible web server (, which retains no information submitted to it, provides an integrated platform to rapidly evaluate pharmacokinetic and toxicity properties.



Animals, Caco-2 Cells, Computer Graphics, Cyprinidae, Databases, Pharmaceutical, Drug Design, Drug-Related Side Effects and Adverse Reactions, Humans, Models, Theoretical, Pharmacokinetics, Rats, Small Molecule Libraries, Software, Tetrahymena pyriformis, Toxicity Tests, User-Computer Interface

Journal Title

J Med Chem

Conference Name

Journal ISSN


Volume Title



American Chemical Society (ACS)
Medical Research Council (MR/M026302/1)
Medical Research Council (MR/N501864/1)
Newton Fund RCUK-CONFAP grant awarded by The Medical Research Council (MRC) and Fundac a o de Amparo a Pesquisa do Estado de Minas Gerais (FAPEMIG) [to D.E.V.P., T.L.B,. and D.B.A.]; Conselho Nacional de Desenvolvimento Cienti fi co e Tecnolo gico (CNPq), and Centro de Pesquisas Rene Rachou (CPqRR/FIOCRUZ Minas), Brazil [to D.E.V.P.]; NHMRC CJ Martin Fellowship [APP1072476 to D.B.A.]; University of Cambridge and The Wellcome Trust for facilities and support [to T.L.B.]. Funding for open access charge: The Wellcome Trust.