Recent advances and current strategies of cheminformatics with artificial intelligence for development of molecular chemistry simulations

Abstract

The major focus of cheminformatic approaches for drug discovery thus far, notably in the medical field, has been on organic molecules. Cheminformatics has been used to analyze the characteristics of molecular compounds before chemical production and experimental assessment. Cheminformatics-inspired approaches employ the structural and chemical properties of molecules and pharmaceuticals to learn crucial information about the qualities of the molecules and materials being examined. The primary data mining methods utilized in cheminformatics intelligence include structural similarity matrices, descriptor computations, and classification algorithms, which are included in the property interpretations. Artificial chemical intelligence's core principles are focused on using it to find and create new drugs. This review investigates the underlying questions of this method by providing real-world case studies of molecules, medications, and practical uses of cheminformatics in drug design and discovery. In many areas of computer-aided drug discovery, including drug repurposing, metallodrugs, chemistry, material informatics, quantitative structure-activity relationship research, de novo drug design, and chemical space visualization, recent advances in cheminformatics and their use in current drug discovery processes have proven to be incredibly helpful.

URN:NBN:sciencein.jmc.2022.440