Catalyst Design for Green Chemistry with Generative AI

Summary

AI/ML have found applications in all aspect of chemistry-related science. While availability of reliable experimental data is currently the main challenge, the use of modern, high throughput DFT methods can help circumventing this limitation. Studies into applying ML to catalysis has often focused on process optimisation, ligand selection,1 with some statistical modelling based on experimental data. Automated exploration of ligand space has been limited to specific classes of catalyst with small variation to the ligands. This is mainly due to the much smaller number of known ligands (thousands instead of millions) available for training exploration algorithms. Nguyen group has provided an alternative solution to this, exploiting the Cambridge Structural Database (CSD) as the source of potential ligands for catalysis in combination with high throughput DFT calculations to discover new viable ligands for Ullmann-Goldberg coupling reactions. Nevertheless, exploration of novel ligand space is still a key building block for true AI-guided catalyst discovery.

The project will deliver:
(i) A rapid automated workflow which predicts activation energy barrier for catalytic cycles through modern high throughput DFT calculations and AI/Machine Learning with high accuracy (discriminator).
(ii) An automated algorithm to explore chemical space around the most promising ligands/catalysts, based on autoencoders, leading to novel and optimised ligands/catalysts (generator).
(iii) Demonstration of AutoCatD on the Ni- and Fe-catalysed coupling and C-H activation reactions.

The students will benefit from expertise in Nguyen group in catalysis, high-throughput computational chemistry and AI/Machine Learning in chemistry. In addition, the student will benefit from working in the highly interdisciplinary research environment in the iPRD. A seminar programme, where aspects of green chemistry, AI and process engineering are discussed on a monthly basis, will be provided. Opportunities to present work and to network will be provided through the iPRD industrial club meetings, CheM62 meetings and RSC events in addition to inter/national green chemistry and AI conferences.

Applicants to research degree programmes should normally have at least a first class or an upper second class British Bachelors Honours degree (or equivalent) in an appropriate discipline. The criteria for entry for some research degrees may be higher, for example, several faculties, also require a Masters degree. Applicants are advised to check with the relevant School prior to making an application. Applicants who are uncertain about the requirements for a particular research degree are advised to contact the School or Graduate School prior to making an application.

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.