2024-03-29 07:00:05
Scientists from the Therapeutic Innovation Laboratory have developed a method using artificial intelligence (SpaceDock) to design new drug candidates on demand from billions of possible molecules.
The search for drug candidates is essentially based on experimental screening or digital of the greatest name possible molecules which we believe could have therapeutic virtues. For an experimental screening, it is the number of molecules available for biological testing which determines the perimeter screening, a scope that can be extended to other “theoretical” chemical systems by virtual screening.
The number and therapeutic performance of molecules that can successfully pass biological tests essentially depend on the “chemical space” screened: the larger the bank of molecules in terms of size and chemical diversity, the better the screening efficiency will be. Scientists from the Therapeutic Innovation Laboratory (CNRS-University of Strasbourg) have just designed particularly effective inhibitors of proteins of therapeutic interest by virtually screening ultra-large theoretical chemical spaces (up to 5 billion molecules). The screening method that they implemented point allowed them to target forinstant fifteen drug candidates of which they carried out the synthesis, then the biological evaluation.
Called “SpaceDock”, this innovative approach begins with the identification and localization of the active sites of the protein with which the inhibitors could interact. For the D3 receiver at the dopamine135,000 commercial chemical reagents capable of anchoring to this active site could thus be selected.
Structure of a drug candidate linked to its receptor, generated by artificial intelligence
© Didier Rognan
The scientists then took into account the topological constraints of the three-dimensional structure of the protein, indicating among these reagents which ones could be close enough to interact and form new molecules… Hundreds of billions of connections are thus possible the fate of which can be predicted by following the operating procedures of 40 “classic” organic chemistry reactions. The largest screening bank ever created!
Ultra-fast, selective and reliable, this method, published in the journal ACS Cent. Sci., allows you to predict, synthesize, then test therapeutic molecules by drawing on a range of chemical substances unique in its size, relevance and diversity
Editor: CCdM
Reference:
François Sindt, Anthony Seyller, Merveille Eguida & Didier Rognan.
Protein Structure-Based Organic Chemistry-Driven Ligand Design from Ultralarge Chemical Spaces
ACS Cent. Sci. 2024
1712670515
#Artificial #intelligence #find #drug #candidates #record #speed