Abstract
The identification of molecular target and mechanism of action of compounds is a key hurdle in drug discovery. Multiplexed techniques for bead-based expression profiling allow the measurement of transcriptional signatures of compound-treated cells in high-throughput mode. Such profiles can be used to gain insight into compounds' mode of action and the protein targets they are modulating. Through the proxy of target prediction from such gene signatures we explored important aspects of the use of transcriptional profiles to capture biological variability of perturbed cellular assays. We found that signatures derived from expression data and signatures derived from biological interaction networks performed equally well, and we showed that gene signatures can be optimised using a genetic algorithm. Gene signatures of approximately 128 genes seemed to be most generic, capturing a maximum of the perturbation inflicted on cells through compound treatment. Moreover, we found evidence for oxidative phosphorylation to be one of the most general ways to capture compound perturbation.
Highlights
Drug discovery research involves target discovery and lead discovery
We explored systematically to what extent transcriptional profiles of compounds can be used for target prediction
This study provided insight into questions such as the following: Is there and what is the minimal gene signature that can be used to reasonably predict molecular targets of compounds? Do designed signatures predict targets better than genes selected at random? How can such signatures be optimised in an automatic way, and what are the results of such an optimisation? We employed machine learning and biologically inspired algorithms implemented on state-of-the-art graphics processing units (GPUs) to answer these questions
Summary
Drug discovery research involves target discovery and lead discovery. Target discovery is concerned with the identification and validation of the disease-relevance of a particular protein. Each molecule is tested against a purified target protein of interest; molecules that are found to significantly affect the assay readout are called hits and are selected for further follow-up experiments such as secondary- or counter-screens. Successful outcomes in those latter screens result in more confidence of having found a true modulator of the target protein, yielding a target-lead pair. Phenotypic assays are a more realistic model for compound administration to living systems but entail the significant post-screen difficulty of target identification and mode of action (MoA) elucidation for any hits identified
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call