Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Validation of predicitve modelling techniques in drug design – influence of test set composition

Validation of predicitve modelling techniques in drug design – influence of test set composition Chemistry Central Journal Open Access Poster presentation Validation of predicitve modelling techniques in drug design – influence of test set composition M Matz*, S Rohrer and K Baumann Address: Magnus Matz, Institut für Pharmazeutische Chemie, Technische Universität Braunschweig, Beethovenstr. 55, 38106 Braunschweig, Germany * Corresponding author from 4th German Conference on Chemoinformatics Goslar, Germany. 9–11 November 2008 Published: 5 June 2009 Chemistry Central Journal 2009, 3(Suppl 1):P64 doi:10.1186/1752-153X-3-S1-P64 <supplement> <title> <p>4th German Conference on Chemoinformatics: 22. CIC-Workshop</p> </title> <editor>Frank Oellien</editor> <note>Meeting abstracts – A single PDF containing all abstracts in this Supplement is available <a href="http://www.biomedcentral.com/content/files/pdf/1752-153X-3-S1-full.pdf">here</a>.</note> <url>http://www.biomedcentral.com/content/pdf/1752-153X-3-S1-info.pdf</url> </supplement> This abstract is available from: http://www.journal.chemistrycentral.com/content/3/S1/P64 © 2009 Matz et al; licensee BioMed Central Ltd. In chemoinformatics and in the analysis of Quantitative diction error without accounting for the bias introduced Structure-Activity Relationships (QSAR) experimental by the splitting algorithm. This is corrected here and it data of a molecular property of interest are routinely turns out that the commonly accepted best practice is mathematically related to a set of carefully chosen struc- actually not the optimal technique to estimate the true ture descriptors which represent the molecules under prediction error. study. Many different mathematical techniques can be used for this purpose. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Chemistry Central Journal Springer Journals

Validation of predicitve modelling techniques in drug design – influence of test set composition

Chemistry Central Journal , Volume 3 (1) – Jun 5, 2009

Validation of predicitve modelling techniques in drug design – influence of test set composition

Abstract

Chemistry Central Journal Open Access Poster presentation Validation of predicitve modelling techniques in drug design – influence of test set composition M Matz*, S Rohrer and K Baumann Address: Magnus Matz, Institut für Pharmazeutische Chemie, Technische Universität Braunschweig, Beethovenstr. 55, 38106 Braunschweig, Germany * Corresponding author from 4th German Conference on Chemoinformatics Goslar, Germany. 9–11 November 2008 Published: 5 June 2009 Chemistry Central...
Loading next page...
 
/lp/springer-journals/validation-of-predicitve-modelling-techniques-in-drug-design-influence-lqgGyABj0k

References (5)

Publisher
Springer Journals
Copyright
Copyright © 2009 by Matz et al; licensee BioMed Central Ltd.
Subject
Chemistry; Chemistry/Food Science, general
eISSN
1752-153X
DOI
10.1186/1752-153X-3-S1-P64
Publisher site
See Article on Publisher Site

Abstract

Chemistry Central Journal Open Access Poster presentation Validation of predicitve modelling techniques in drug design – influence of test set composition M Matz*, S Rohrer and K Baumann Address: Magnus Matz, Institut für Pharmazeutische Chemie, Technische Universität Braunschweig, Beethovenstr. 55, 38106 Braunschweig, Germany * Corresponding author from 4th German Conference on Chemoinformatics Goslar, Germany. 9–11 November 2008 Published: 5 June 2009 Chemistry Central Journal 2009, 3(Suppl 1):P64 doi:10.1186/1752-153X-3-S1-P64 <supplement> <title> <p>4th German Conference on Chemoinformatics: 22. CIC-Workshop</p> </title> <editor>Frank Oellien</editor> <note>Meeting abstracts – A single PDF containing all abstracts in this Supplement is available <a href="http://www.biomedcentral.com/content/files/pdf/1752-153X-3-S1-full.pdf">here</a>.</note> <url>http://www.biomedcentral.com/content/pdf/1752-153X-3-S1-info.pdf</url> </supplement> This abstract is available from: http://www.journal.chemistrycentral.com/content/3/S1/P64 © 2009 Matz et al; licensee BioMed Central Ltd. In chemoinformatics and in the analysis of Quantitative diction error without accounting for the bias introduced Structure-Activity Relationships (QSAR) experimental by the splitting algorithm. This is corrected here and it data of a molecular property of interest are routinely turns out that the commonly accepted best practice is mathematically related to a set of carefully chosen struc- actually not the optimal technique to estimate the true ture descriptors which represent the molecules under prediction error. study. Many different mathematical techniques can be used for this purpose.

Journal

Chemistry Central JournalSpringer Journals

Published: Jun 5, 2009

There are no references for this article.