Skip to main content

Machine Learning-Assisted Fabrication of Polyelemental CNP@MOF Core@Shell Nanostructures for Asymmetric Catalysis


Asymmetric synthesis of single-enantiomer chemicals plays a vital role in producing single-enantiomer drugs in pharmaceutical industry. This project will produce the polyelemental CNP@MOF core@shell nanoparticles as the asymmetric catalysts to trigger the asymmetric synthesis, that is, the heterogeneous asymmetric catalysis. GLAD will be used to fabricate polyelemental CNPs, which will serve as the seeds to guide the growth of MOF to form the polyelemental CNP@MOF nanoparticles. Precursor molecular substrates will be selectively grafted on the core polyelemental CNPs via the diffusion through MOF, followed by the asymmetric catalysis. The shell MOF will function as the molecular filter to enhance the catalytical selectivity and co-catalysts. Chiral HPLC will be operated to analyse an enantiomeric excess (ee) of the enantioselectivity. ML-assisted design of the growth of the CNP@MOF nanoparticles will be operated to maximize the ee values. According to the ML-based design, the enantioselectivity will be experimental optimized.

Required skills

Academic background in Chemistry, Material Science and/or Physics. Experimental experience in nanomaterial fabrication and characterization, as well as chemical synthesis and characterization.

Principal Investigator


Dr. Huang

Prof. Zhifeng Huang

Associate Professor, Department of Physics




Prof. Guo

Prof. Yike Guo

Vice-President (Research & Development)
Professor, Department of Computer Science