AI/ML in formulation design – Opportunities and Challenges

Andrei Leonard Nicusan is a researcher at the University of Birmingham focusing on data-driven engineering across scales. He published featured articles and Scientific Highlights on machine learning-based positron emission particle tracking algorithms. His work on evolutionary algorithms for simulation calibration, optimisation and physics discovery has raised more than £260,000 from research and industrial funding bodies. His frameworks are actively being used in projects with JM, GranuTools, JDE, FMC, Recycling Technologies.

Dr. Carl Reynolds is a research fellow in the Energy Materials Group at the University of Birmingham. Carl is interested in using novel metrology to understand industrial problems, particularly involving rheology and complex flow. He has worked with industrial partners including Michelin, BP and Unilever on topics ranging from polymer processing to volcanic eruptions. He is currently part of the Faraday Institution Nextrode project, applying novel techniques to optimise battery electrode manufacture, by elucidating the physical relationships between process parameters and outputs.

Dr. Christoph Kreisbeck is Chief Commercial Officer at Kebotix and oversees business development, sales, marketing, and product envisioning. Christoph is passionate about disruptive technologies and bringing tough tech to the commercial world. Out of Harvard, he co-founded Kebotix to build the world’s first autonomous materials discovery platform, accelerating the industry's transition to a new era of digital R&D. Between 2014 and 2016, he worked as a software developer within a spearhead project on self-driving cars. As he likes to say: "From self-driving cars to self-driving labs.” Among other achievements, Dr. Kreisbeck is the lead architect of the high-performance software 'GPU-HEOM', which is used by more than 200 scientists worldwide for research on novel design concepts of next-generation solar cells.

Hannah Melia is a Product Management Consultant to Citrine Informatics, the world leader in AI for Materials and Chemicals. She studied Materials Science and Metallurgy at the University of Cambridge. Since then she has worked in various technology-based industries in Germany, the UK, and the USA. For the last 13 years she has worked in Materials Information software, first at Granta Design (now Granta Ansys) and now for Citrine.

John Overington is a VP of Discovery Informatics at Exscientia, and a visiting professor at University College London.

He earned a PhD in Computational Structural Biology from Birkbeck College, University of London. Previously, he was CIO at the Medicines Discovery Catapult, an SVP at Benevolent AI, Head of Chemistry Services at EMBL-EBI, an SVP at Inpharmatica Ltd, and Head of Molecular Informatics Structure and Design at Pfizer. He has published broadly across many areas of drug discovery informatics including ca. 150 publications and been responsible for the development of some of the core foundational resources for machine learning in drug discovery, for example the ChEMBL database.

Laura Filion has a masters in physics from McMaster University, Canada, and a PhD from Utrecht University, Netherlands. After working as a post-doc at Cambridge University, UK, she moved back to Utrecht University, where she currently works as an associate professor in soft condensed matter. Her research focuses on using classical statistical physics, computer simulations and machine learning to examine the self-assembly of colloidal particles, both in and out of equilibrium. She is well known for her work on self-assembly in entropy-driven systems (including binary hard-sphere mixtures), defects in colloidal crystals, and crystal nucleation. One of her main research lines currently is the design of efficient and light-weight machine learning methods to aid in the study of soft matter.

Linjiang’s research focuses on Data-driven Materials Exploration and Optimization (DaMEO) by fusing chemical knowledge with state-of-the-art computation ranging from quantum mechanics to data-driven heuristics. Linjiang leads the DaMEO group, whose current mission is to build step-change computational capabilities at the intersection of chemistry, chemical engineering, and computer science to redefine our ability to position atoms and molecules for function.

Linjiang was awarded his PhD in molecular modelling from the University of Edinburgh in 2014. From 2013 to 2017, Linjiang was a postdoctoral research associate with Prof Andy Cooper at the University of Liverpool, followed by a research fellow and theme lead position in the Leverhulme Research Centre for Functional Materials Design, until February 2022. In March 2022, Linjiang joined the School of Chemistry at the University of Birmingham, as a lecturer in computational chemistry.

Mark has 30 years experience of lab automation, instrumentation development, data management and data analytics gained from the academic, SME and large corporate sectors. At CPI he established a team focusing on application of a number digital technologies in service of industrial formulation, including high throughput experimentation, process analytics and model-based process control, and data analytics. His current role as Chief Technologist is leading the further strategic and collaborative development of these technologies and horizon-scanning for digital technologies that can be applied for benefit of CPI’s industrial customers.

Project leader & senior data-scientist in biotechnological and chemical R&D with broad spectrum of interests in technical & organic chemistry, biotechnology, analytics and formulation. Currently responsible for shaping future vision & projects for data science`s role in product formulation design together with associated partners.

Tom is Head of Machine Learning at Intellegens, a machine learning spin-out from the University of Cambridge that specialises in handling sparse and noisy experimental data. He joined Intellegens from his PhD in theoretical physics at the University of Cambridge, and is now leading the application of Intellegens' novel deep learning approaches to a wide variety of industrial applications. Tom is interested in developing machine learning approaches to solve previously intractable problems in a variety of scientific and engineering fields including industrial chemistry.