Dataset Information

Artificial Intelligence-Guided De Novo Molecular Design Targeting COVID-19.

ABSTRACT: An extensive search for active therapeutic agents against the SARS-CoV-2 is being conducted across the globe. While computational docking simulations remain a popular method of choice for the in silico ligand design and high-throughput screening of therapeutic agents, it is severely limited in the discovery of new candidate ligands owing to the high computational cost and vast chemical space. Here, we present a de novo molecular design strategy that leverages artificial intelligence (AI) to discover new therapeutic agents against SARS-CoV-2. A Monte Carlo tree search algorithm combined with a multitask neural network surrogate model for expensive docking simulations, and recurrent neural networks for rollouts, is used in an iterative search and retrain strategy. Using Vina scores as the target objective to measure binding to either the isolated spike protein (S-protein) at its host receptor region or to the S-protein/angiotensin converting enzyme 2 receptor interface, we generate several (∼100's) new therapeutic agents that outperform Food and Drug Administration (FDA) (∼1000's) and non-FDA molecules (∼million). Our AI strategy is broadly applicable for accelerated design and discovery of chemical molecules with any user-desired functionality.

SUBMITTER: Srinivasan S

PROVIDER: S-EPMC8154149 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial Intelligence-Guided De Novo Molecular Design Targeting COVID-19.

Srinivasan Srilok S Batra Rohit R Chan Henry H Kamath Ganesh G Cherukara Mathew J MJ Sankaranarayanan Subramanian K R S SKRS

ACS omega 20210504 19

An extensive search for active therapeutic agents against the SARS-CoV-2 is being conducted across the globe. While computational docking simulations remain a popular method of choice for the in silico ligand design and high-throughput screening of therapeutic agents, it is severely limited in the discovery of new candidate ligands owing to the high computational cost and vast chemical space. Here, we present a de novo molecular design strategy that leverages artificial intelligenc ...[more]

PMID: 34056406

Similar Datasets

Project description:Recent studies highlight the effectiveness of hybrid Severe Acute Respiratory Syndrome-Coronavirus-2 (SARS-CoV-2) vaccines combining wild-type nucleocapsid and Spike proteins. We have further enhanced this strategy by incorporating delta and omicron variants' spike protein mutations. Both delta and omicron mark the shifts in viral transmissibility and severity in unvaccinated and vaccinated patients. So their mutations are highly crucial for future viral variants also. Omicron is particularly adept at immune evasion by mutating spike epitopes. The rapid adaptations of Omicron and sub-variants to spike-based vaccines and simultaneous transmissibility underline the urgency for new vaccines in the continuous battle against SARS-CoV-2. Therefore, we have added three persistent T-cell-stimulating nucleocapsid peptides similar to homologous sequences from seasonal Human Coronaviruses (HuCoV) and an envelope peptide that elicits a strong T-cell immune response. These peptides are clustered in the hybrid spike's cytoplasmic region with non-immunogenic linkers, enabling systematic arrangement. AlphaFold (Artificial intelligence-based model building) analysis suggests omitting the transmembrane domain enhances these cytoplasmic epitopes' folding efficiency which can ensure persistent immunity for CD4+ structural epitopes. Further molecular dynamics simulations validate the compact conformation of the modeled structures and a flexible C-terminus region. Overall, the structures show stability and less conformational fluctuation throughout the simulation. Also, the AlphaFold predicted structural epitopes maintained their folds during simulation to ensure the specificity of CD4+ T-cell response after vaccination. Our proposed approach may provide options for incorporating diverse anti-viral T-cell peptides, similar to HuCoV, into linker regions. This versatility can be promising to address outbreaks and challenges posed by various viruses for effective management in this era of innovative vaccines.

Dataset Information

Artificial Intelligence-Guided De Novo Molecular Design Targeting COVID-19.

Publications

Artificial Intelligence-Guided <i>De Novo</i> Molecular Design Targeting COVID-19.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets