Today we’re honoured to be named as one of MIT Technology Review’s top 10 breakthrough technologies of 2020.
The prestigious list, curated by MIT Technology Review’s editorial team, is subject to meticulous research and a rigorous process of elimination in order to identify the ten most important technology breakthroughs of the year which are expected to have the biggest impact on human life in the decade ahead.
AI-enabled molecules feature as one of the technologies on the 2020 list, where we’re proud to be recognised for our work in AI-driven chemical design. Our compound design is based on complex multiparametric optimisations set by medicinal chemists working alongside our AI scientists, with a scoring function that factors in all the properties we are seeking to optimise for that molecule.
David Rotman, Editor at Large, MIT Technology on the importance of AI-discovered molecules.:
"The ability of deep learning and other AI tools to find novel molecules with desirable properties will transform drug discovery. It promises to make the development of new medicines far faster and more effective, and is an important new tool in the hunt for better drugs."
Last year, we also released 'GuacaMol', an open-source Python framework that enables the entire research community to access generative chemistry models for benchmarking de novo molecular design.
Drug discovery scientists using our AI platform can select the most promising molecules. They can adapt and optimise compounds using interactive design tools and take them into synthesis and biological testing. Drug discovery scientists apply their knowledge (and bias) but, equally, they can become inspired by the AI and take their design in unexplored directions. Our aim is to empower scientists through the AI platform, believing that the best results come from feeding the interplay between scientists and AI.
The result is that drug discovery scientists can test a more accurate, smaller sample of compounds - cutting the time and cost of designing a drug by years. Our chemical design process is one component of a bigger integrated approach that spans from data collection, target identification up to clinical trials.Designing better medicines using AI and big data. Our team of scientists and AI experts present a ‘behind the scenes’ introduction to show how our latest advancements in machine learning and AI can better understand the underlying causes of diseases, and redefine the way in which new medicines are discovered and brought to patients.