Are you developing new chemical compounds, designing formulations, or aiming to improve or manage a chemical process?
In each of these examples, you will need to optimise the impact of multiple parameters. And you will be doing this based on data from experiment, simulation, or production that you are constantly seeking to understand and improve. The Alchemite software can help. Find out how you can apply it to guide your experimental programs, getting better results in less time, and to get vital insights into what is driving the performance of your products or processes, ensuring quality and enabling effective innovation.
White paper
7 examples of how materials and chemicals companies innovate with AI
Case studies and resources
Catalyst applications at Johnson Matthey
Johnson Matthey have used Alchemite™ to design catalysts and related processes with applications in clean air and life sciences. Project successes have included a 4% increase in yield on one key process, with significant cost and energy benefits on scale-up, and 50-80% efficiency increases in experimental programmes.
Sensory properties of compounds with Optibrium and IFF
Scientists from Intellegens, Optibrium, and IFF have published a paper in the Journal of Computer-Aided Molecular Design that applies Alchemite™ machine learning to the sensory properties of chemical compounds. The team successfully predicted sensory properties using physicochemical and sensory data, demonstrating a higher accuracy than conventional QSAR or neural network methods. Such work can provide guidance on compound selection, saving costly experimental time and resources.
Chemical discovery – lubricants example
Lubricants are a commercially-important class of chemical which are predominantly mixtures of alkanes. Yet understanding of how to improve key properties is still relatively poor. In an Alchemite study, the relatively sparse experimental data was combined with results from molecular dynamics simulations. Alchemite was able to exploit property-property correlations in this data to predict the physical properties of known and new alkanes.
Ink formulations – Domino Printing Sciences case study
Domino Printing Sciences applied Alchemite to help guide testing and find optimal formulations for their inks. This case study shows how to reduce time-to-market, identify new candidate formulations, and enable reformulation in response to market, environmental, or regulatory drivers.
White paper: Machine learning for adaptive experimental design
Identifying the optimal ingredients, chemistry, and processing parameters to achieve commercial performance goals as quickly as possible is the key objective of formulation and chemical design projects. Machine learning identifies improved products with 50-80% fewer experiments than traditional DOE approaches, by focusing experimental effort directly on options that will lead to successful products in as few experimental cycles as possible.
Alchemite for chemistry and chemical processes
- Gap-fill and validate sparse, noisy data from suppliers, experiment, simulation, and production
- Auto-generate models that identify key structure-property-process relationships
- Quantify uncertainty to support a rational business case for key decisions
- Design experimental programs to achieve objectives with the fewest experiments
- Identify new candidate compounds that meet target properties
- Optimise process parameters to improve quality and performance
With the Alchemite software, chemists, chemical engineers, and data scientists can apply powerful deep learning methods to get more from their data. You could use Alchemite to:
