Automation will transform the chemical landscape. Powerful robotic platforms can perform reactions or analyses much more rapidly than traditional approaches.1 Ever faster computers allow huge numbers of molecules to be studied in an automated way using computational chemistry. Even with automated approaches it is not feasible to explore all possibilities. For example, in synthesis there may be thousands of possible combinations of reagents and conditions that could be changed during a reaction optimisation. In computational chemistry, there are vast numbers of ways of arranging atoms with respect to each other when proposing potential intermediates to model during mechanistic studies. A “smart” approach to automation is essential if it is to deliver its potential benefits in many areas. Some recent, high profile, reports have explored aspects of this, but much more needs to be done.2
During their training, chemists learn the many “rules” of chemistry that allow them to interpret data and to make decisions about which of the many possible parts of chemical space should be studied in order to achieve a particular goal. This project is based on a new, ambitious, interdisciplinary collaboration between The Department of Chemistry and the AI group in Computer Science at York. It aims to develop artificial chemical intelligence (ACI) that will mimic chemical training and intuition and allow automated systems to make chemically sensible decisions, allowing human workers to focus on the high-level strategic aspects of a project, dramatically increasing productivity. ACI will be trained to analyse the outputs from high-throughput reaction screening and make decisions about which part of chemical space to explore next. ACI will also be trained, using large structural databases such as the CSD or ChemSpider, to predict the structures of potential reaction intermediates during mechanistic studies, allowing decisions to be made about which parts of chemical space to assess during automated computational chemistry workflows.
The student will study benchmark chemical reactions using experimental and quantum chemical approaches in order to generate robust datasets that can be used to train, or test, ACI algorithms. This will include determination of spectroscopic properties, molecular structures, reaction kinetics and mechanistic details. They will also work on data acquisition, in order to develop methodologies that are ready for automation or that can already be automated using the Chemspeed robot. A key focus will be on data formatting and processing to build a workflow that will allow data to be captured and stored in a way that is ACI ready.
All research students follow our innovative Doctoral Training in Chemistry (iDTC): cohort-based training to support the development of scientific, transferable and employability skills. All research students take the core training package which provides both a grounding in the skills required for their research, and transferable skills to enhance employability opportunities following graduation.
Training will be given in the synthesis of organic and organometallic compounds, many of which are air-and moisture-sensitive and require good synthetic skills and Schlenk techniques to handle. York has a strong background in NMR spectroscopy and will provide thorough training in this area alongside routine spectroscopic techniques (IR, UV/Vis, MS etc.) The project will require the student to develop good skills in analytical chemistry, in particular high-throughput GC/MS and/or LC/MS analysis for which York is well equipped. Throughout the project the student will gain significant skills in the utilisation of high-throughput synthetic approaches, including the use of the Chemspeed robotic synthesis platform in Chemistry. This requires a level of technical skill that few synthetic chemistry PhD graduates have and will set the student apart from others when applying for positions after their studies. Finally, it will be necessary throughout the project to develop skills in crystallisation and crystal structure determination in order to add to databases of existing single-crystal X-ray structures that will be important for training ACI algorithms.
In addition to experimental work, the student will be trained to perform state-of-the-art quantum chemical calculations. York has good expertise in this area and York training will be backed up through external collaborations and through national training.
Links to Computer Science will allow the student to learn about AI and machine learning techniques and to develop programming skills that are in high demand in the workplace.
The Department of Chemistry holds an Athena SWAN Gold Award and is committed to supporting equality and diversity for all staff and students. The Department strives to provide a working environment which allows all staff and students to contribute fully, to flourish, and to excel.
This project is open to students who can fund their own studies or who have been awarded a scholarship separate from this project. The Chemistry Department at York is pleased to offer Wild Fund Scholarships to those from countries outside the UK. Wild Fund Scholarships offer up to full tuition fees for those from countries from outside the European Union. EU students may also be offered £6,000 per year towards living costs. For further information see: View Website
1) A. McNally, C. K. Prier and D. W. C. MacMillan, Science, 2011, 334, 1114-1117;
2) D. T. Ahneman, J. G. Estrada, S. Lin, S. D. Dreher and A. G. Doyle, Science, 2018; J. M. Granda, L. Donina, V. Dragone, D.-L. Long and L. Cronin, Nature, 2018, 559, 377-381;
3) R. D. King, K. E. Whelan, F. M. Jones, P. G. K. Reiser, C. H. Bryant, S. H. Muggleton, D. B. Kell and S. G. Oliver, Nature, 2004, 427, 247;
4) E. Algahtani and D. Kazakov, 28th International Conference on Inductive Logic Programming, 2018;
5) D. Kazakov and T. Tsenova, International Conference on Agents and Artificial Intelligence, Porto, Portugal, 2009; Z. Georgiev and D. Kazakov, IEEE Symposium on Computational Intelligence for Financial Engineering & Economics (CIFEr), Cape Town, 2015.
How good is research at University of York in Chemistry?
FTE Category A staff submitted: 47.06
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities