Chemical manufacturers currently test green solvents—safer, more sustainable alternatives to hazardous organic solvents—only late in the process, forcing costly re-optimisation of reactions. This project trains machine-learning models to predict how reactions will behave in green solvents using existing data from traditional solvents, bypassing the scarcity of direct green-solvent reaction data. The problem is that switching solvents early could save time and reduce waste, but chemists lack the tools to forecast changes in yield, selectivity, or impurity profiles. Without reliable predictions, manufacturers stick with familiar but harmful solvents, slowing the adoption of greener chemistry. If the models succeed, drug companies and fine-chemical manufacturers could design synthetic routes around green solvents from the start, cutting development timelines and simplifying purification. The project’s industrial partners—including AstraZeneca and CatSci—will guide the outputs toward real-world use in high-value chemical manufacturing. The work is applied, not fundamental: it directly targets a bottleneck in sustainable production, with no immediate consumer-facing impact but clear benefits for industrial efficiency and environmental safety.
View original technical description
The switch from traditional organic solvents, many of which are hazardous, volatile or non-sustainable, to modern green solvents is one of the key sustainability objectives in High Value Chemical Manufacture. Currently, the use of green solvents is often explored at process development stage, instead of discovery stage. This necessitates re-optimisation of processes, due to changes in yield, selectivity, impurity profile and purification. These lead to longer development time, cost, and additional uncertainty. On the other hand, selecting the right solvent early may enhance chemoselectivity, avoid additional reaction steps, and simplify purification of the products. Predicting these changes is an important underpinning capability for wider adaptation of green solvents in manufacturing. Unfortunately, the scarcity of reaction data in green solvents is a key obstacle in developing this capability. Thus, there is an urgent need for ML models which predict reactivity in green solvents based on available data in traditional solvents. In addition to addressing the short time-scale of early-stage process development, these will increase the confidence in utilising green solvents at discovery stage, support sophisticated synthetic routes planning tools which takes into account side products, impurity and purification methods, and act as valuable regulatory tools for assessing hazardous impurities. This project will address these challenges through the following objectives: O1 Addressing the scarcity of reactivity data in the literature through curation of reaction data with reliable reaction time and inclusion of rate laws. O2 Developing solvent-dependent reactivity and reaction selectivity prediction models for green solvents. O3 Producing a set of standard substrates based on cheminformatics analysis of industrially relevant reactions and collecting their reactivity data in green solvents. These outputs will have transformative impacts in the chemical manufacture industry, delivering rapid, more sustainable and better quality-controlled processes through shorter development time, and confidence in predicting reaction outcomes in green solvents. The project will be carried out with support from industrial partners working in the field of cheminformatics and AI/Machine learning, e.g. Lhasa Ltd. and Molecule One. Its outputs will be guided and exploited by partners who are end-users in the High Value Chemical Manufacturing sectors: AstraZeneca, CatSci, and Concept Life Science.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know