Abstract
Scoring functions play an important role in structure-based virtual screening. It has been widely accepted that target-specific scoring functions (TSSFs) may achieve better performance compared with universal scoring functions in actual drug research and development processes. A method that can effectively construct TSSFs will be of great value to drug design and discovery. In this work, we proposed a deep learning–based model named DeepScore to achieve this goal. DeepScore adopted the form of PMF scoring function to calculate protein–ligand binding affinity. However, different from PMF scoring function, in DeepScore, the score for each protein–ligand atom pair was calculated using a feedforward neural network. Our model significantly outperformed Glide Gscore on validation data set DUD-E. The average ROC-AUC on 102 targets was 0.98. We also combined Gscore and DeepScore together using a consensus method and put forward a consensus model named DeepScoreCS. The comparison results showed that DeepScore outperformed other machine learning–based TSSFs building methods. Furthermore, we presented a strategy to visualize the prediction of DeepScore. All of these results clearly demonstrated that DeepScore would be a useful model in constructing TSSFs and represented a novel way incorporating deep learning and drug design.
Highlights
Structure-based drug design (SBDD) has been widely used in industry and academia (Andricopulo et al, 2009; Morrow et al, 2012)
The neural network in DeepScore is only used to facilitate the learning of atom-pair potentials; the overall framework of potential of meanforce (PMF) scoring function is preserved
We introduced a novel strategy for training targetspecific protein–ligand scoring functions used for structurebased virtual screening
Summary
Structure-based drug design (SBDD) has been widely used in industry and academia (Andricopulo et al, 2009; Morrow et al, 2012). There are three main categories of tasks for SBDD methods: virtual screening, de novo drug design, and ligand optimization. Virtual screening generally refers to the process of identifying active compounds among molecules selected from a virtual compound library. By utilizing the three-dimensional information of proteins, structure-based virtual screening is believed to be more efficient than traditional virtual screening methods. The key factor for guaranteeing the success of structure-based virtual screening is the quality of scoring functions. A scoring function is capable of predicting the binding affinity of a protein–ligand
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.
