Wassermann, Anne, Lounkine, Eugen, Davies, John, Glick, Meir and Camargo, Miguel (2015) The opportunities of mining historical and collective data in drug discovery. Drug Discovery Today, 20 (4). pp. 422-434. ISSN 13596446

Abstract

Over the past decades, vast amounts of bioactivity data have been generated for small molecules in both public and corporate domains. Biological signatures, either derived from systematic profiling efforts or from existing historical assay data, have been successfully employed for small molecule mechanism-of-action (MoA) elucidation, drug repositioning, hit expansion and screening library design. This article reviews different types of biological descriptors and applications, and we demonstrate how biological data can outlive the original purpose or project for which it was generated. Furthermore, we show that small molecules are not only characterized by their activity in biological assays (compound-centric biological profiles), but biological assays themselves can be characterized by the molecules tested on them (assay-centric compound profiles). By comparing 150 HTS campaigns run at Novartis over the past decade on the basis of their active and inactive chemical matter, we highlight the opportunities and challenges associated with cross-project learning in drug discovery.

Item Type:	Article
Keywords:	assay similarities, biological signatures, collective knowledge, historical knowledge, cross-project learning, data mining, profiling
Date Deposited:	27 May 2016 23:45
Last Modified:	04 Jul 2016 23:45
URI:	https://oak.novartis.com/id/eprint/22389