Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities

Radleigh G. Santos, Marc A. Giulianotti, Richard A. Houghten, José L. Medina-Franco

Research output: Contribution to journalArticlepeer-review

10 Scopus citations

Abstract

Structure-property relationships and structure-activity relationships play an important role in many research areas, such as medicinal chemistry and drug discovery. Such methods, however, have focused on providing post-hoc descriptions of such relationships based on known data. The ability for these descriptions to remain relevant when considering compounds of unknown activity, and thus the prediction of activity and property landscapes using existing data, remains little explored. In this study, we present a novel method of evaluating the ability of a compound comparison methodology to provide accurate information about a set of unknown compounds and also explore the ability of these predicted activity landscapes to prioritize active compounds over inactive. These methods are applied to three distinct and diverse sets of compounds, each with activity data for multiple targets, for a total of eight target-compound set pairs. Six methodologically distinct compound comparison methods were evaluated. We show that overall, all compound comparison methods provided an improvement in structure-activity relationship prediction over random and were able to prioritize compounds in a superior manner to random sampling, but the degree of success and therefore applicability varied markedly.

Original languageEnglish (US)
Pages (from-to)2613-2625
Number of pages13
JournalJournal of Chemical Information and Modeling
Volume53
Issue number10
DOIs
StatePublished - Oct 28 2013
Externally publishedYes

Fingerprint

Dive into the research topics of 'Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities'. Together they form a unique fingerprint.

Cite this