Abstract
Motivation: Bringing a new drug to the market is expensive and time-consuming. To cut the costs and time, computer-aided drug design (CADD) approaches have been increasingly included in the drug discovery pipeline. However, despite traditional docking tools show a good conformational space sampling ability, they are still unable to produce accurate binding affinity predictions. This work presents a novel scoring function for molecular docking seamlessly integrated into DockingApp, a user-friendly graphical interface for AutoDock Vina. The proposed function is based on a random forest model and a selection of specific features to overcome the existing limits of Vina’s original scoring mechanism. A novel version of DockingApp, named DockingApp RF, has been developed to host the proposed scoring function and to automatize the rescoring procedure of the output of AutoDock Vina, even to nonexpert users. Results: By coupling intermolecular interaction, solvent accessible surface area features and Vina’s energy terms, DockingApp RF’s new scoring function is able to improve the binding affinity prediction of AutoDock Vina. Furthermore, comparison tests carried out on the CASF-2013 and CASF-2016 datasets demonstrate that DockingApp RF’s performance is comparable to other state-of-the-art machine-learning- and deep-learning-based scoring functions. The new scoring function thus represents a significant advancement in terms of the reliability and effectiveness of docking compared to AutoDock Vina’s scoring function. At the same time, the characteristics that made DockingApp appealing to a wide range of users are retained in this new version and have been complemented with additional features.
Highlights
Bringing about a new therapeutic compound is an expensive and time-consuming process [1,2]
The best-performing combination of algorithm and features was used in the CASF-2013 and CASF-2016 benchmarks in order to compare its effectiveness with a number of recent competing methods that either employ “classical” scoring function (SF) or machine-learning-based SFs
The scoring function discussed so far was implemented in DockingApp random forest (RF), a desktop application for docking and virtual screening that is meant as a user-friendly interface to AutoDock Vina, taking over from the earlier DockingApp
Summary
Bringing about a new therapeutic compound is an expensive and time-consuming process [1,2]. Molecular docking predicts the binding mode and affinity of a compound (sometimes in the form of a score related to it) for a target, allowing to prioritize top scoring molecules for further processing and subsequent testing. The frequencies of a contact are correlated to its contribution to protein–ligand binding by applying an inverse Boltzmann analysis Scoring functions of this type are implemented in tools such as PMF and DrugScore [14,15]. Compared to classical SFs, ML-based SFs result in an improved binding affinity prediction [26] Despite their performances and advantages, machine-learning-based SFs are not yet routinely used in docking simulations. This work provides a measure of the performance of the proposed scoring function through comparative tests with a number of competitors on the CASF-2013 and the CASF-2016 benchmarks [28,29]
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.
