skip to content

Department of Chemical Engineering and Biotechnology

Department of Chemistry

The new Innovation Centre in Digital Molecular Technologies aims to accelerate access to pharmaceuticals, agrochemicals, functional molecules and molecular materials through machine learning and robotics-based synthesis.

Professor Alexei Lapkin from the University of Cambridge Department of Chemical Engineering and Biotechnology is leading the new multimillion-pound research centre, part-funded by the European Regional Development Fund, which aims to spark a digital transformation in the chemical industries.

In partnership with pharmaceutical companies AstraZeneca and Shionogi, the Innovation Centre in Digital Molecular Technologies (iDMT) will set up a new experimental research facility, integrating high-throughput synthesis, analytics, chemical informatics, machine learning, robotics and reaction engineering.

The facility will be housed in the University of Cambridge’s Department of Chemistry. “We are proud to be part of this new innovative chemistry research consortium with the leading research institutes in the United Kingdom. As a pharmaceutical company with strengths in chemistry-driven small molecule drug discovery, we are committed to innovate the digital molecular technology in collaboration with researchers from the partner institutes and companies", said Dr Ryuichi Kiyama, Senior Executive Officer, Pharmaceutical Research Division, Shionogi & Co., Ltd.

“Access to novel functional molecules and materials continues to be a major bottleneck in many chemistry-using industries, such as medicine, food, electronics and energy,” said Professor Alexei Lapkin, Director of iDMT.

“Despite tremendous advances in chemistry, we still cannot always make all of the molecules we need on demand, especially when set against increasingly competitive business-driven timelines, and this means that we often miss out on many potential opportunities to, for example, develop new medicines,” said Professor Matthew Gaunt, co-director of iDMT and Director of the EPSRC SynTech centre for doctoral training, based in the Department of Chemistry.

The iDMT will support collaborative research projects with small and medium enterprises (SMEs) from across the UK, aiming to develop a technology base to support the emerging digital economy in the 3rd largest manufacturing sector in the UK.

Traditional development methods for functional molecules have been tremendously successful in improving healthcare and wellbeing, communications and access to innovative consumer products. Digitalisation of discovery research, development and manufacturing of molecules and materials offers a step-change towards a new model of industry, where access to molecules will be faster, less resource intensive and without negative consequences for the environment.

“The transformational change that we believe is required in the way chemical synthesis is approached is based on a radical increase in the throughput of chemical discovery and process development,” explained Gaunt. “This can be achieved through the automation of largely routine procedures, and the adoption of artificial intelligence to guide synthetic chemists towards successful solutions in a more efficient manner. This frees up the time of scientists to develop new ideas.”

“It is very difficult to predict how chemical processes would behave at an industrial scale. For this reason, development and optimisation of chemical processes usually takes quite a long time”, continued Lapkin. “’AI tools’, can help in solving complex problems of chemical process design speeding up the transition from a working chemical reaction in the lab, to a scaled-up industrial process”.

One of the barriers to digitalisation of the chemical industry is the absence of a central location with the research infrastructure and multi-disciplinary intellectual capital to support providers to develop the necessary commercial, technical and software solutions. The iDMT will support collaborative research projects involving academic and industrial researchers in three key areas:

  • Acceleration of synthesis through AI and automation
  • Equipment for robotic experiments
  • Algorithms and tools for digital process development

The iDMT will support SMEs in developing their understanding of new digital tools and processes in making molecules, and enable them to develop solutions to some of the key challenges facing larger, end-user companies in the pharmaceutical and wider chemical manufacturing sectors.

The centre’s core academic team combines University expertise from the Departments of Chemistry, Physics, and Chemical Engineering and Biotechnology.

“Combining cross-disciplinary expertise from several departments at the University, with state-of-the-art facilities and support from two of the leading companies in this area has the potential to enable the development of many new solutions for the nascent industry of digital molecular technology,” said Lapkin.

“Facilitating knowledge exchange to SMEs so that they can develop the right product offer that would serve the needs of the large end-user companies in the pharma, agritech and wider chemical manufacturing sectors will enable an industry-wide shift in how synthesis, process design and manufacture are carried out.”

Construction of the facility is due to begin shortly, but the centre is already open for projects.

Interested companies should contact Professor Alexei Lapkin for further information.

iDMT academic team

Prof. Alexei Lapkin (CEB)

iDMT Director

Alexei Lapkin’s group is working on innovative manufacturing processes in chemical industries and specifically focusing on clean technology and support of sustainable technologies; the group has extensive industrial links with global chemical companies and has developed ML-based tools for process optimisation.

Prof. Matthew Gaunt (Chemistry)         

iDMT Co-Director

Matthew Gaunt’s group is focussed on the development of new catalytic methods for small and biomacromolecule synthesis and functionalization. They also develop and apply high throughout experimentation strategies to accelerate synthesis and generate chemical data sets for machine learning applications towards predictive chemistry. The group has extensive connections with the global and local pharmaceutical industry and biotech SMEs.

Dr Sebastian Ahnert (CEB)

Sebastian’s research interests lie in the intersection of theoretical physics, biology, mathematics and computer science. He is particularly interested in using algorithmic descriptions of structures and functional systems in order to quantify and classify their complexity. Examples of the application of such approaches include pattern detection in gene expression data, the classification of protein quaternary structure, the structure of genotype-phenotype maps, and the identification of large-scale features in complex networks. Connected to this he is also interested in interdisciplinary applications of network analysis, particularly in the context of digital methods and large-scale data analysis. 

Dr Lucy Colwell (Chemistry)

Lucy Colwell is a researcher in the applied science group at Google and a faculty member in chemistry at the University of Cambridge. Her primary research interests are in the application of machine learning approaches to better understand the relationship between the sequence and function of biological macromolecules. With collaborators Lucy showed that graphical models built from aligned protein sequences can be used to predict protein tertiary structure and functional attributes. Her current work moves beyond this to ask how machine learning models can be applied to optimize biological sequences, to enable the discovery of new proteins and therapeutics.

Prof. Jonathan Goodman (Chemistry)
Jonathan Goodman's group is centred on using computational organic chemistry to understand molecular phenomena and to gain knowledge from molecular data by developing methods to analyse reactions and to predict properties from structure. The group also works with IUPAC and other international bodies to help communicate chemistry effectively 

Dr. Jose Miguel Hernandez Lobato (Engineering)

Miguel, one of the leaders of the Cambridge machine learning group, is interested in probabilistic machine learning and its applications to molecular design. His group works on deep generative models of molecules and their combination with Bayesian optimization techniques for data-efficient automated molecular design. Recent research directions are molecule generation in 3D space and molecule generation via chemical reactions (to guarantee chemical synthesis). Miguel is also interested in using machine learning methods to obtain improved sampling algorithms that can be used to explore the global configuration space of molecules. 

Dr Alpha Lee (Physics)

Alpha Lee’s research group develops predictive models for molecular design, reaction prediction and retrosynthesis planning, integrating physical simulations into the machine learning models. The group has extensive links with the pharma industry. Alpha is also a co-founder of PostEra, a startup that offers medicinal chemistry as a service powered by machine learning. 

iDMT industry team

iDMT management board members from Shionogi:

Dr Kenji Yamawaki

Vice President, Laboratory for Medicinal Chemistry Research, Shionogi & Co., Ltd.

Dr Masami Takayama

Associated Principal Scientist, Shionogi & Co., Ltd.

iDMT management board members from AstraZeneca:

Dr Clive Green

Executive Director, and Head of Global Sample Management, Discovery Sciences, R&D

Dr Michael Kossenjans

Associate Director, Discovery Sciences, R&D


There are no upcoming talks currently scheduled in this series.

This project is funded by

Relevant papers from the academic team

Using attribution to decode binding mechanism in neural network models for chemistryK McCloskey, A Taly, F Monti, MP Brenner, LJ Colwell  Proceedings of the National Academy of Sciences  (2019)  116, 201820657 (DOI: 10.1073/pnas.1820657116)

Optimal Design of Experiments by Combining Coarse and Fine MeasurementsAA Lee, MP Brenner, LJ Colwell  Physical Review Letters  (2017)  119, 208101 (DOI: 10.1103/PhysRevLett.119.208101)

Constrained Bayesian optimization for Automatic Chemical Design Using Variational Autoencoders, Griffiths R.-R. and Hernández-Lobato J. M., Chemical Science, 2019, DOI: 10.1039/c9sc04026a

A General Framework for Constrained Bayesian Optimization using Information-based Search, Hernández Lobato J. M., Gelbart M. A., Adams R. P., Hoffman M. W. and Ghahramani Z., Journal of Machine Learning Research, 17(160):1−53, 2016

Neural network activation similarity: a new measure to assist decision making in chemical toxicology, TEH Allen, AJ Wedlake, E Gelžinytė, C Gong, JM Goodman, S Gutsell,  Paul J Russell, Chemical Science 11 (28), 7335-7348

A new formulation for symbolic regression to identify physico-chemical laws from experimental data, P. Neumann, L. Cao, D. Russo, V.S. Vassiliadis, A.A. Lapkin, Chem. Eng. J., 387 (2020) 123412

Machine learning and molecular descriptors enable rational solvent selection in asymmetric catalysis, Y. Amar, A.M. Schweidtmann, P. Deutsch, L. Cao, A. Lapkin,  Chem. Sci., 10 (2019) 6697-6706

"Impact of Chemist-In-The-Loop Molecular Representations on Machine Learning Outcomes", T. J. Wills, D. A. Polshakov, M. C. Robinson, A. A. Lee, Journal of Chemical Information and Modelling, Journal of Chemical Information and Modelling,  (2020)

"Geometry of energy landscapes and the optimizability of deep neural networks", S. Becker, Y. Zhang, A. A. Lee, Physical Review Letters, 124, 108301 (2020)

“Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction”, P. Schwaller, T. Laino, T. Gaudin, P. Bolgar, C. Bekas, A. A. Lee, ACS Central Science, 5, 1572 (2019)

“Molecular Transformer unifies reaction prediction and retrosynthesis across pharma chemical space”, A. A. Lee, Q. Yang, V. Sresht, P. Bolgar, X. Hou, J. Klug-McLeod and C. Butler, Chemical Communications, 55, 12152 (2019)

“Ligand biological activity predicted by cleaning positive and negative chemical correlations”, A. A. Lee, Q. Yang, A. Bassyouni, C. R. Butler, X. Hou, S. Jenkinson, D. A. Price, Proceedings of the National Academy of Sciences, 116, 3373 (2019)