Abstract
Recent trends in drug development have been marked by diminishing returns caused by the escalating costs and falling rates of new drug approval. Unacceptable drug toxicity is a substantial cause of drug failure during clinical trials and the leading cause of drug withdraws after release to the market. Computational methods capable of predicting these failures can reduce the waste of resources and time devoted to the investigation of compounds that ultimately fail. We propose an original machine learning method that leverages identity of drug targets and off-targets, functional impact score computed from Gene Ontology annotations, and biological network data to predict drug toxicity. We demonstrate that our method (TargeTox) can distinguish potentially idiosyncratically toxic drugs from safe drugs and is also suitable for speculative evaluation of different target sets to support the design of optimal low-toxicity combinations.
Highlights
The last decade has seen an escalation of drug development costs, and at the same time, the rate at which new successful drugs are released has decreased [1]
One strategy to reduce these costs and improve the efficiency of the drug development is to augment laboratory and clinical testing with computational analysis [5], and the development of accurate methods to predict toxicity is pivotal to this goal [6]
Our analysis indicated that current leading methods developed for clinical trial success prediction and druglikeness do not perform as well in the case of drugs withdrawn from the market (Fig S1)
Summary
The last decade has seen an escalation of drug development costs, and at the same time, the rate at which new successful drugs are released has decreased [1]. Further developments have led to refinements of simple rule-based methods into more granular qualitative measures, such as quantitative estimate for drug-likeness (QED) [9], which uses a desirability function to compute an optimal score across multiple chemistry-based criteria. Most of these efforts were not intended only to identify likely toxicity, but to optimize over a range of relevant properties that can impact efficacy, bioavailability, and pharmacokinetics
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
