Welcome to the John Mitchell research group website

We are an Informatics and Computational Chemistry research group. Our group is based in the Purdie building on the North Haugh in St Andrews.

Research areas we are interested in are enzyme catalysis, protein-ligand interactions, modelling epidemics, molecular evolution and structural bioinformatics, computational toxicology, prediction of solubility and other molecular properties, and the classification of drugs used for doping in sport.

News

• Ben Connaughton has started his PhD on using Machine Learning to predict enzyme function.


• John's new presentation: Humanity v The Machines: An AI Challenge.


• Eureka publish an interview with John, discussing AI in chemistry.


• Here are the slides from John's seminar on Random Forest.


• Some of John's more general interest teaching slides are available online. Here are the Science and Religion Lectures from ID1003: Religious Belief and the Rise of Science and Fine Tuning and the God of the Gaps, the History of Atomic Theory from ID1004, and two lectures on scientific writing from CH4431: Scientific Literature: the Languages and Dialects of Science and Writing a Good Review Article.


• The slides from John's Seminar in Edinburgh: First Principles and Machine Learning Calculations of Aqueous Solubility are available.


• In case you ever wondered, we are probably not Sims, according to John's presentation to the Institute for Data-Intensive Research at St Andrews.


• Could AI heal our diseases? Artificial Intelligence in Pharmaceutical Research and Development is published in Future Medicinal Chemistry.
  
  
• Who wins - humankind or AI? Can human experts predict solubility better than computers? is available Open Access in the Journal of Cheminformatics.


• Enzyme function and its evolution is published in Current Opinion in Structural Biology.

Recent publications

Computational Insights into the Catalytic Mechanism of Is-PETase: An Enzyme Capable of Degrading Poly(ethylene) Terephthalate,
E Shrimpton-Phoenix, JBO Mitchell, M Bühl
Physical Review E, 106, 014304 (2022)
doi: 10.1002/chem.202201728

Practical Application of a Bayesian Network Approach to Poultry Epigenetics and Stress,
EAV Rodriguez, F Pertille, C. Guerrero-Bosagna, JBO Mitchell, P Jensen, VA Smith
BMC Bioinformatics, 23, 261 (2022)
doi: 10.1186/s12859-022-04800-0

Degree correlations in graphs with clique clustering,
P Mann, VA Smith, JBO Mitchell, S Dobson
Physical Review E, 105, 044314 (2022)
doi: 10.1103/PhysRevE.105.044314

Allosteric inhibition of Acinetobacter baumannii ATP phosphoribosyltransferase by protein:dipeptide and protein:protein interactions,
BJ Read, G Fisher, OLR Wissett, TFG Machado, J Nicholson, JBO Mitchell, RG da Silva,
ACS Infectious Diseases. 8: 197-209 (2022)
doi: acsinfecdis.1c00539

EAV Rodriguez, JBO Mitchell, VA Smith,
A Bayesian Network Structure Learning Approach to Identify Genes Associated with Stress in Spleens of Chickens,
Scientific Reports 12, 7482 (2022)
doi: 10.1038/s41598-022-11633-7

Toward physics-based solubility computation for pharmaceuticals to rival informatics,
DJ Fowles, DS Palmer, R Guo, SL Price, JBO Mitchell,
J. Chem. Theor. Comput., 17, 3700-3709 (2021)
doi: 10.1021/acs.jctc.1c00130

Exact formula for bond percolation on cliques,
P Mann, VA Smith, JBO Mitchell, CA Jefferson, S Dobson
Physical Review E, 104, 024304 (2021)
doi: 10.1103/PhysRevE.104.024304

Symbiotic and antagonistic disease dynamics on clustered networks using bond percolation,
P Mann, VA Smith, JBO Mitchell, S Dobson
Physical Review E, 104, 024303 (2021)
doi: 10.1103/PhysRevE.104.024303

Two-pathogen model with competition on clustered networks,
P Mann, VA Smith, JBO Mitchell, S Dobson,
Physical Review E, 103, 062308 (2021)
doi: 10.1103/PhysRevE.103.062308

Cooperative coinfection dynamics on clustered networks,
P Mann, VA Smith, JBO Mitchell, S Dobson,
Physical Review E, 103, 042307 (2021)
doi: 10.1103/PhysRevE.103.042307

Percolation in random graphs with higher-order clustering,
P Mann, VA Smith, JBO Mitchell, S Dobson,
Physical Review E, 103, 012313 (2021)
doi: 10.1103/PhysRevE.103.012313

Random graphs with arbitrary clustering and their applications,
P Mann, VA Smith, JBO Mitchell, S Dobson,
Physical Review E, 103, 012309 (2021)
doi: 10.1103/PhysRevE.103.012309

In silico methods to predict solubility,
J. L. McDonagh, J. B. O. Mitchell, D. S. Palmer & R. E. Skyner,
in Solubility in Pharmaceutical Chemistry (Eds C Saal & A Nair), De Gruyter (2020)
ISBN 978-3-11-055983-5

Three machine learning models for the 2019 Solubility Challenge,
J. B. O. Mitchell,
ADMET & DMPK 8, 215-251 (2020)
doi: 10.5599/admet.835

In silico methods to predict solubility,
J. L. McDonagh, J. B. O. Mitchell, D. S. Palmer & R. E. Skyner,
in Solubility in Pharmaceutical Chemistry (Eds C Saal & A Nair), De Gruyter (2020)
ISBN 978-3-11-055983-5

We are probably not Sims
J. B. O. Mitchell
Science & Christian Belief, 32, 45-62 (2020)

Teaching material (sorry, St Andrews access only) for CH1202, CH3441, CH3717, CH4431, CH5714, ID1003, ID1004, ID2005, CRITICAT and SUPACCH.

Thanks to our Sponsors