Drugs and drug-like compounds: Discriminating approved pharmaceuticals from screening-library compounds

Amanda C. Schierz, Ross D. King

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    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. © 2009 Springer Berlin Heidelberg.
    Original languageEnglish
    Title of host publicationPattern Recognition in Bioinformatics
    PublisherSpringer Nature
    Number of pages12
    Volume5780
    ISBN (Print)9783642040306, 3642040306
    DOIs
    Publication statusPublished - 2009

    Keywords

    • Compound screening library
    • Drug-likeness
    • Inductive Logic Programming
    • Machine learning
    • Rule of 5

    Fingerprint

    Dive into the research topics of 'Drugs and drug-like compounds: Discriminating approved pharmaceuticals from screening-library compounds'. Together they form a unique fingerprint.

    Cite this