Abstract
Interleukin-1 receptor associated kinase-1 (IRAK1) exhibits important roles in inflammation, infection, and autoimmune diseases; however, only a few inhibitors have been discovered. In this study, at first, a discriminatory structure-based virtual screening (SBVS) was employed, but only one active compound (compound 1, IC50 = 2.25 μM) was identified. The low hit rate (2.63%) which derives from the weak discriminatory power of docking among high-scored molecules was observed in our virtual screening (VS) process for IRAK1 inhibitor. Furthermore, an artificial intelligence (AI) method, which employed a support vector machine (SVM) model, integrated information of molecular docking, pharmacophore scoring and molecular descriptors was constructed to enhance the traditional IRAK1-VS protocol. Using AI, it was found that VS of IRAK1 inhibitors excluded by over 50% of the inactive compounds, which could significantly improve the prediction accuracy of the SBVS model. Moreover, four active molecules (two of which exhibited comparative IC50 with compound 1) were accurately identified from a set of highly similar candidates. Amongst, compounds with better activity exhibited good selectivity against IRAK4. The AI assisted workflow could serve as an effective tool for enhancement of SBVS.
Highlights
In the process of drug discovery, hunting for lead compounds is a starting point, and a very challenging task
In order to select the most effective screening method, we evaluated the performance of different proteins and moleculardocking software
For each monomer of the Interleukin-1 receptor associated kinase-1 (IRAK1) crystal structure (6BFN_A and 6BFN_B from protein data bank) [27], we docked the original ligand into the binding pocket to evaluate the reproducibility of several frequently-used docking methods
Summary
In the process of drug discovery, hunting for lead compounds is a starting point, and a very challenging task. As a complementary approach to HTS [2], VS filters chemicals through ligand- or structure-based approaches by taking advantages of high-performance computers, Discovery of New IRAK1 Inhibitors overcomes some shortcomings of HTS, and remarkably reducing the time, money, and resources involved [3, 4]. The scoring functions of virtual screening are not accurate enough to predict the protein-ligand binding affinity and this leads to a high rate of false results, which needs combined strategies to improve prediction accuracy in a sequential or parallel manner [5, 6]. Tian et al integrated ensemble molecular docking and complex-based pharmacophore searching using Naive Bayesian classification and recursive partitioning, which were of great significance in the discovery of novel ROCK inhibitors and increased the VS hit rate to 28.95% [10].
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.
