Tom is applying a range of interpretable machine learning techniques and models to predict properties of crystalline materials.
Outside of work Tom is training for the 2021 Edinburgh marathon. Check back for updates (and sponsorship opportunities).
Tom is a co-founder of – and ‘Big Cheese’ in – The Oxford Cheese Society, and we look forward to welcoming him to the long-running cheesetallography events (when social distancing allows).
Andre is studying property prediction of materials with a focus on method development and relevant and information rich molecular representations.
Publications
Increasing the performance, trustworthiness and practical value of machine learning models (2020) CrystEngComm
Louis is investigating the use of active learning to increase the efficiency of experimental work required to feed into generating best possible predictive models of co-crystal formation.
CrystEngComm, 2017, 19, 5336 – 5340 [ doi:10.1039/C7CE00587C ]
A data-driven approach to predicting co-crystal formation reduces the number of experiments required to successfully produce new co-crystals. A machine learning algorithm trained on an in-house set of co-crystallization experiments results in a 2.6-fold enrichment of successful co-crystal formation in a ranked list of co-formers, using an unseen set of paracetamol test experiments.
CrystEngComm, 2017,19, 3737-3745 [ doi:10.1039/C7CE00738H ]
We present here the crystallisation outcomes for 319 publicly available compounds in up to 18 different solvents spread over 5710 individual single solvent evaporation trials. The recorded data is part of a much larger, corresponding in-house database and includes both positive as well as negative crystallisation outcomes. Such data can be used for statistical analyses of solvent performances, machine learning approaches or investigation of the crystallisation behaviour in structurally similar compound classes.
The presented data suggests that crystallisation behaviour in different solvents is not correlated with chemical similarity among clusters of highly similar compounds. Further, our machine learning models can be used to guide the solvent choice when crystallising a compound. In a retrospective evaluation, these models proved potent to reduce the workload to a third of our initial protocol, while still guaranteeing crystallisation success rates greater than 92%.
Publisher’s copy
J. Chem. Inf. Model., 2016, 56 (12), 2347–2352 doi: 10.1021/acs.jcim.6b00565
A new molecular descriptor, nConf20, based on chemical connectivity, is presented which captures the accessible conformational space of a molecule. Currently the best available 2-dimensional descriptors for quantifying the flexibility of a particular molecule are the rotatable bond count (RBC) and the Kier flexibility index. We present a descriptor which captures this information by sampling the conformational space of a molecule using the RDKit conformer generator. Flexibility has previously been identified as a key feature in determining whether a molecule is likely to crystallize or not. For this application, nConf20 significantly outperforms previously reported single-variable classifiers and also assists rule-based analysis of black-box machine learning classification algorithms.
The 2016 British Crystallographic Meeting Spring Meeting took place at the University of Nottingham from 4th – 7th April. Contributions from Chem. Cryst. staff and students were:
Jerome G. P. Wicker, Bill I. F. David & Richard I. Cooper
When will it Crystallise? (Talk in session: From Amorphous to Crystal)
Jo Baker & Richard I. Cooper
Making and Measuring Photoswitchable Materials (Talk in session: Young Crystallographers’ Satellite)
Pascal Parois, Karim J. Sutton & Richard I. Cooper
On the application of leverage analysis to parameter precision using area detector strategies (Poster)
Oliver Robshaw & Richard I. Cooper
The role of molecular similarity in crystal structure packing (Poster)
Katie McInally & Richard I. Cooper
Linking crystallization prediction, theory and experiment using solubility curve determination (Poster)
Richard I. Cooper, Pascal Parois & David J. Watkin
Non-routine single crystal structure analyses using CRYSTALS (Poster)
Alex Mercer & Richard I. Cooper
Fitting Disordered Crystal Structures by Simulated Annealing of an Ensemble Model (Poster)
Annotated articles are based on research from a range of Royal Society of Chemistry journals that has been re-written into a standard, accessible format.
An annotated article on predicting and controlling the crystallinity of molecular materials by Jerome Wicker and Richard Cooper aims to help readers to understand the research the journal article is based on, and how to read and understand journal articles. Our research article was originally published in CrystEngComm.
CrystEngComm (2015) 17, 1927-1934 [ doi:10.1039/C4CE01912A ]
Machine learning algorithms can be used to create models which separate molecular materials which will form good-quality crystals from those that will not, and predict how synthetic modifications will change the crystallinity.
Chemistry World Article: Will It Crystallise
Publisher’s copy
A-level students from a range of schools attended a one-day course at the Museum of the History of Science and the Department of Chemistry in Oxford to find out about the science and applications of crystallography. In the morning they discovered how symmetry plays important role in the structure and diffraction of crystals in a lecture by Prof. Brian Sutton of King’s College, London. Prof. Richard Cooper then gave an rapid overview of the history of the applications of crystallography from Pasteur’s discovery of chirality in the pre- X-ray diffraction world to Hodgkin’s determination of the structure of penicillin. Prof. Elspeth Garman took the students through the ups and downs of crystallographic research in the decades long attempt to grow one crystal of a virus protein in an attempt to fight the tuberculosis virus.
Split into groups, the students then visited the Department of Chemistry where they visited three different activities:
Meanwhile back in the museum students visited the solar fuels outreach stand where they saw how crystallography can reveal the structures that nature uses to carry out photosynthesis, and, under the careful supervision of Johnny Brooks-Bartlett and Katharina Jungnickel from Biochemistry, they were able to carry out a recrystallisation of the protein lysozyme and watch while it grew in just a few minutes on a microscope slide.