Leading Edge Predictors for Drug Discovery

CSLogWS Home

CSLogD Home

CSLogP Home



CSGenoTox Home



     ...Dataset Profile

Dataset Used in the CSLogP  Modeling Process

General Compound Profile Information for the CS LogP Training Set

Our current dataset of LogP values contains 20032 compounds.  The data used was obtained from three principle sources(1,2,3).  Many of the compounds in the CSLogP training set had a value reported in all three sources, and these duplicate values were essentially identical (< 0.1 log unit differences).  If a pH value accompanied the reported LogP, the compound was screened to evaluate the possibility that a LogD value had actually been reported, rather than LogP.  The neural net convergence test was utilized to remove noisy data.  After screening, 16893 compounds from the original 20032 were used to construct CSLogP.

(1).  KOW, Sangster Research Laboratories, Montreal Canada.

(2).  CLoGP, Biobyte Startlist

(3).  PhysProp, Syracuse Research Corp., Syracuse, NY.

CSLogP  Compound Profile

A profile of the initial 20032 compound CSLogP dataset is given below.

CSLogP validation results on these compounds can be found at CSLogP Experimental

Back to: CSLogP  Home Page

user login
contact us

To contact us:

Phone: 978-501-0633

Fax: 781-275-5197

Email:  sales@chemsilico.com

Copyright © 2003 ChemSilico LLC All Rights Reserved

Terms and Conditions of Use | Privacy Policy

ChemSilico is a registered trademark of ChemSilico LLC, Tewksbury, MA 01876