"If I ask an organic chemist to make me a random new molecule, they can't do it," says Lee Cronin, a professor of chemistry at the University of Glasgow. "It's not because they are stupid. They will ask me what type of molecule and what specification. It could take them one week or ten years. Cronin realised that even though that's a difficult ask for a human being, it probably wasn't such a difficult project for a machine learning robot to undertake.
Scientists can only do so much to discover new chemical reactions on their own. Short of happy accidents, it can take years to find new drugs that might save lives. They might have a better way at the University of Glasgow, though: let robots do the hard work. A research team at the school has developed a "robot chemist" (below) that uses machine learning to accelerate discoveries of chemical reactions and molecules. The bot uses machine learning to predict the outcomes of chemical reactions based on what it gleans from direct experience with just a fraction of those interactions.
To manufacture medicines, chemists must find the right combinations of chemicals to make the necessary chemical structures. This is more complicated than it sounds, as typical chemical reactions employ several different components, and each chemical involved in a reaction adds another dimension to the calculations.
The use of machine learning has allowed us to solve many of our problems. It can allow us to effectively manage bandwidth, possibly predict solar flares, automate the rooting out of weeds, and so much more. The ability to learn and experience the world much as humans do allows our machines to be better at the tasks we give them. Sometimes, they're even better than humans are. US chemists have created a machine-learning algorithm that studies successful and failed experiments in order to beat humans at predicting ways to make crystals.
In the fine chemicals industry, reaction screening and optimisation are essential to development of new products. However, this screening can be extremely time and labor intensive, especially when intuition is used. Machine learning offers a solution through iterative suggestions of new experiments based on past experimental data, but knowing which machine learning strategy to apply in a particular case is still difficult. Here, we develop chemically-motivated virtual benchmarks for reaction optimisation and compare several strategies on these benchmarks. The benchmarks and strategies are encompassed in an open source framework named Summit.