Insilico generation of novel ligands for the inhibition of SARS-CoV-2 main protease (3CLpro) using deep learning

Abstract

The recent emergence of novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causing the coronavirus disease (COVID-19) has become a global public health crisis, and a crucial need exists for rapid identification and development of novel therapeutic interventions. In this study, a recurrent neural network (RNN) is trained and optimized to produce novel ligands that could serve as potential inhibitors to the SARS-CoV-2 viral protease: 3 chymotrypsin-like protease (3CLpro). Structure-based virtual screening was performed through molecular docking, ADMET profiling, and predictions of various molecular properties were done to evaluate the toxicity and drug-likeness of the generated novel ligands. The properties of the generated ligands were also compared with current drugs under various phases of clinical trials to assess the efficacy of the novel ligands. Twenty novel ligands were selected that exhibited good drug-likeness properties, with most ligands conforming to Lipinski’s rule of 5, high binding affinity (highest binding affinity: −9.4 kcal/mol), and promising ADMET profile. Additionally, the generated ligands complexed with 3CLpro were found to be stable based on the results of molecular dynamics simulation studies conducted over a 100 ns period. Overall, the findings offer a promising avenue for the rapid identification and development of effective therapeutic interventions to treat COVID-19.

Mining for Potent Inhibitors through Artificial Intelligence and Physics: A Unified Methodology for Ligand Based and Structure Based Drug Design

“…55 Specifically, we looked at the newVina and newIGN score distributions as well as the bioactivity scores used in similar studies. 60,61 In Figure 3a, the distribution of the surviving molecules falls in a similar and, in the case of newIGN, even better range compared to the known experimental binders, indicating that our stringent down-selection with consensus scoring could successfully lead us to molecules that have the potential to form strong interactions with our target protein. In Figure 3b, we examine the various bioactivity scores to show that our molecules are similar to the known binders from a pharmacological perspective.…”

“…Then, 125 molecules were filtered from the consensus scoring for the final analysis to assess their distribution compared to a set of the known experimental binders borrowed from LP-PDBBind . Specifically, we looked at the newVina and newIGN score distributions as well as the bioactivity scores used in similar studies. , …”