Drugs and Drug-Like Compounds: Discriminating Approved Pharmaceuticals from Screening-Library Compounds

Authors:
Amanda C. Schierz;Ross D. King
Affiliations:
Software Systems Research Group, Bournemouth University, Poole BH12 5BB;Computational Biology Research Group, Aberystwyth University, Aberystwyth SY23 3DB
Venue:
PRIB '09 Proceedings of the 4th IAPR International Conference on Pattern Recognition in Bioinformatics
Year:
2009

Citing 3
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
An Introduction to Chemoinformatics

An Introduction to Chemoinformatics
Top-down induction of first-order logical decision trees

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Compounds in drug screening-libraries should resemble pharmaceuticals. To operationally test this, we analysed the compounds in terms of known drug-like filters and developed a novel machine learning method to discriminate approved pharmaceuticals from "drug-like" compounds. This method uses both structural features and molecular properties for discrimination. The method has an estimated accuracy of 91% in discriminating between the Maybridge HitFinder library and approved pharmaceuticals, and 99% between the NATDiverse collection (from Analyticon Discovery) and approved pharmaceuticals. These results show that Lipinski's Rule of 5 for oral absorption is not sufficient to describe "drug-likeness" and be the main basis of screening-library design.