In Expert opinion on drug discovery ; h5-index 34.0
BACKGROUND : Despite recent scientific and technological advancements that positively affect various fields of industry, drug development productivity has been declining due to elevated costs and reduced discovery rates. Therefore, pharmaceutical companies have been seeking alternative ways to determine drug candidates with high potential to be successful in the process of drug development.
RESEARCH DESIGN AND METHODS : In this work, we proposed a new computational approach to directly predict the regulatory approval of drug candidates, and implemented it as a method called "DrugApp". To accomplish this task, we employed multiple types of features including molecular and physicochemical properties of drug candidates, together with clinical trial and patent related features, which are then processed by random forest classifiers to train our disease group-specific approval prediction models.
RESULTS : Our evaluations indicated DrugApp has a high and robust prediction performance. Within a use-case study, we showed our method can predict phase IV trial drugs that are later withdrawn from the market due to severe side effects, only using data preceding their regulatory approval. Finally, we used DrugApp models to forecast the approval of drug candidates that are currently in phase I/II/III of clinical trials.
CONCLUSIONS : We hope that the results of our study, together with the programmatic implementation and datasets we provided, will aid the research community in terms of evaluating and improving the process of drug development. All of the datasets, source code, results and pre-trained models of DrugApp are freely available at https://github.com/HUBioDataLab/DrugApp.
Ciray Fulya, Doğan Tunca
2022-Nov-29
Approval of drugs, clinical trials, drug patents, machine learning, molecular structures, physicochemical properties, predictive modeling
